Bump version to 0.16.4

.bumpversion.cfg

@@ -1,16 +1,5 @@
 [bumpversion]
-current_version = 0.17.0
-commit = True
-parse = (?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(?:-(?P<prerel>rc)\.(?P<prerelversion>\d+))?
-serialize = 
-	{major}.{minor}.{patch}-{prerel}.{prerelversion}
-	{major}.{minor}.{patch}
-
-[bumpversion:part:prerel]
-optional_value = release
-values = 
-	rc
-	release
+current_version = 0.16.4
 
 [bumpversion:file:setup.py]
 search = version="{current_version}"
@@ -20,6 +9,6 @@ replace = version="{new_version}"
 search = "version": "{current_version}"
 replace = "version": "{new_version}"
 
-[bumpversion:file:backend/server/__init__.py]
+[bumpversion:file:server/__init__.py]
 search = __version__ = "{current_version}"
 replace = __version__ = "{new_version}"

.dockerignore

@@ -2,4 +2,4 @@ bin
 client
 dist
 docs
-backend
+server

.github/workflows/canary-deploy.yml

@@ -1,13 +0,0 @@
-name: Deploy canary via single cell infra repo
-
-on:
-  push:
-    branches: main-canary
-
-jobs:
-  deploy:
-    runs-on: ubuntu-latest
-    steps:
-      - name: repository dispatch
-        run: |
-          curl -XPOST -u czi-sci-single-cell-eng:${{secrets.SCI_GITHUB_TOKEN}} -H "Accept: application/vnd.github.everest-preview+json"  -H "Content-Type: application/json" https://api.github.com/repos/chanzuckerberg/single-cell-infra/dispatches --data '{"event_type": "canary-hook"}'

.github/workflows/codeql-analysis.yml

@@ -1,67 +0,0 @@
-# For most projects, this workflow file will not need changing; you simply need
-# to commit it to your repository.
-#
-# You may wish to alter this file to override the set of languages analyzed,
-# or to provide custom queries or build logic.
-#
-# ******** NOTE ********
-# We have attempted to detect the languages in your repository. Please check
-# the `language` matrix defined below to confirm you have the correct set of
-# supported CodeQL languages.
-#
-name: "CodeQL Scan"
-
-on:
-  push:
-    branches: [ main ]
-  pull_request:
-    # The branches below must be a subset of the branches above
-    branches: [ main ]
-  schedule:
-    - cron: '0 8 * * *'
-
-jobs:
-  analyze:
-    name: Analyze
-    runs-on: ubuntu-latest
-
-    strategy:
-      fail-fast: false
-      matrix:
-        language: [ 'javascript', 'python' ]
-        # CodeQL supports [ 'cpp', 'csharp', 'go', 'java', 'javascript', 'python' ]
-        # Learn more:
-        # https://docs.github.com/en/free-pro-team@latest/github/finding-security-vulnerabilities-and-errors-in-your-code/configuring-code-scanning#changing-the-languages-that-are-analyzed
-
-    steps:
-    - name: Checkout repository
-      uses: actions/checkout@v2
-
-    # Initializes the CodeQL tools for scanning.
-    - name: Initialize CodeQL
-      uses: github/codeql-action/init@v1
-      with:
-        languages: ${{ matrix.language }}
-        # If you wish to specify custom queries, you can do so here or in a config file.
-        # By default, queries listed here will override any specified in a config file.
-        # Prefix the list here with "+" to use these queries and those in the config file.
-        # queries: ./path/to/local/query, your-org/your-repo/queries@main
-
-    # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
-    # If this step fails, then you should remove it and run the build manually (see below)
-    - name: Autobuild
-      uses: github/codeql-action/autobuild@v1
-
-    # ℹ️ Command-line programs to run using the OS shell.
-    # 📚 https://git.io/JvXDl
-
-    # ✏️ If the Autobuild fails above, remove it and uncomment the following three lines
-    #    and modify them (or add more) to build your code if your project
-    #    uses a compiled language
-
-    #- run: |
-    #   make bootstrap
-    #   make release
-
-    - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@v1

.github/workflows/compatibility_tests.yml

@@ -25,11 +25,10 @@ jobs:
   cellxgene-main-with-python-and-anndata-versions:
     name: python versions x anndata versions
     runs-on: ubuntu-latest
-    continue-on-error: true
     strategy:
       matrix:
         python-version: [3.6, 3.7, 3.8]
-        anndata-version: [0.7.6]
+        anndata-version: [0.6.22.post1, 0.7.1]
         test-suite: [smoke-test, smoke-test-annotations]
     steps:
     - uses: actions/checkout@v2
@@ -41,12 +40,14 @@ jobs:
       run: |
         # 1. only install the dev requirements on top of what is in the cellxgene pip package
         sudo apt-get update && sudo apt-get install -y libhdf5-serial-dev
-        sed -i 's/-r requirements.txt//' backend/server/requirements-dev.txt
-        pip install -r backend/server/requirements-dev.txt
+        sed -i 's/-r requirements.txt//' server/requirements-dev.txt
+        pip install -r server/requirements-dev.txt
         # 2. install cellxgene
         make pydist install-dist
         # 3. install anndata
         pip install anndata==${{ matrix.anndata-version }}
+        # workaround for anndata 0.6.22.post1 bug
+        [[ "0.6.22.post1" = "${{ matrix.anndata-version }}" ]] && pip install h5py==2.9.0 || true
     - name: Tests
       run: make unit-test ${{ matrix.test-suite }}
 
@@ -66,17 +67,22 @@ jobs:
         uses: actions/checkout@v2
         with:
           path: cellxgene
+      - name: Checkout tools repo
+        uses: actions/checkout@v2
+        with:
+          repository: theislab/anndata
+          path: anndata
       - name: Install dependencies
         run: |
           cd cellxgene
           # 1. only install the dev requirements on top of what is in the cellxgene pip package
           make dev-env-client
-          sed -i 's/-r requirements.txt//' backend/server/requirements-dev.txt
-          pip install -r backend/server/requirements-dev.txt
+          sed -i 's/-r requirements.txt//' server/requirements-dev.txt
+          pip install -r server/requirements-dev.txt
           # 2. install cellxgene
           pip install --upgrade cellxgene
           # 3. install anndata
-          pip install git+https://github.com/theislab/anndata
+          cd ../anndata && pip install -e .
       - name: Tests
         run: cd cellxgene && make unit-test ${{ matrix.test-suite }}
 
@@ -96,11 +102,17 @@ jobs:
         uses: actions/checkout@v2
         with:
           path: cellxgene
+      - name: Checkout tools repo
+        uses: actions/checkout@v2
+        with:
+          repository: theislab/anndata
+          path: anndata
       - name: Install dependencies
         run: |
           cd cellxgene
-          sed -i -E 's/^anndata[>=]=[0-9]+.[0-9]+.[0-9]+$/anndata/g' backend/server/requirements.txt
+          sed -i -E 's/^anndata[>=]=[0-9]+.[0-9]+.[0-9]+$/anndata/g' server/requirements.txt
           make pydist install-dist dev-env
-          pip install git+https://github.com/theislab/anndata
+          cd ../anndata
+          pip install -e .
       - name: Tests
         run: cd cellxgene && make unit-test ${{ matrix.test-suite }}

.github/workflows/push_tests.yml

@@ -31,16 +31,15 @@ jobs:
       - name: Install dependencies
         run: |
           pip install flake8
-          pip install black
           cd client
           npm install
-      - name: Format with black and lint with flake8
+      - name: Lint with flake8
         run: |
-          make lint-servers
+          make lint-server
       - name: Lint src with eslint
         working-directory: ./client
         run: |
-          npx eslint src __tests__
+          make lint
 
   unit-test:
     runs-on: ubuntu-latest
@@ -68,38 +67,8 @@ jobs:
         run: make pydist install-dist dev-env-server
       - name: Unit tests
         run: |
-          make unit-test-server
-          bash <(curl -s https://codecov.io/bash) -y .codecov.yml -k backend/server -cF backend,python,unitTest
-          cd client && ./node_modules/codecov/bin/codecov --yml=../.codecov.yml --root=../ --gcov-root=../ -C -F frontend,javascript,unitTest
-
-  unit-test-czi-hosted:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v2
-      - name: Set up Python 3.7
-        uses: actions/setup-python@v1
-        with:
-          python-version: 3.7
-      - name: Python cache
-        uses: actions/cache@v1
-        with:
-          path: ~/.cache/pip
-          key: ${{ runner.os }}-pip-${{ hashFiles('**/requirements*.txt') }}
-          restore-keys: |
-            ${{ runner.os }}-pip-
-      - name: Node cache
-        uses: actions/cache@v1
-        with:
-          path: ~/.npm
-          key: ${{ runner.os }}-node-${{ hashFiles('**/package-lock.json') }}
-          restore-keys: |
-            ${{ runner.os }}-node-
-      - name: Install dependencies
-        run: make pydist-czi-hosted install-dist dev-env-czi-hosted
-      - name: Unit tests
-        run: |
-          make unit-test-czi-hosted
-          bash <(curl -s https://codecov.io/bash) -y .codecov.yml -k backend/czi-hosted -cF backend,python,unitTest
+          make unit-test
+          bash <(curl -s https://codecov.io/bash) -y .codecov.yml -k server -cF backend,python,unitTest
           cd client && ./node_modules/codecov/bin/codecov --yml=../.codecov.yml --root=../ --gcov-root=../ -C -F frontend,javascript,unitTest
 
   smoke-tests:
@@ -126,7 +95,7 @@ jobs:
           restore-keys: |
             ${{ runner.os }}-node-
       - name: Install dependencies
-        run: make pydist-czi-hosted install-dist
+        run: make pydist install-dist
       - name: Smoke tests (without annotations feature)
         run: |
           cd client && make smoke-test

.github/workflows/sastisfaction.yml

@@ -1,27 +0,0 @@
-name: Run SASTisfaction
-on:
-  - pull_request
-
-jobs:
-  sastisfaction:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v2
-      - uses: actions/checkout@v2
-        with:
-          repository: chanzuckerberg/sastisfaction
-          ref: main
-          path: .github/actions/sastisfaction
-          ssh-key: ${{ secrets.SASTISFACTION_READ_KEY }}
-      - name: Login to GitHub Container Registry
-        uses: docker/login-action@v1
-        with:
-          registry: ghcr.io
-          username: ${{ github.actor }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-      - name: Docker pull
-        run: docker pull ghcr.io/chanzuckerberg/sastisfaction:main
-      - name: Run SASTisfaction
-        uses: ./.github/actions/sastisfaction
-        with:
-          snowflake_private_key: ${{ secrets.SASTISFACTION_RSA_KEY }}

.github/workflows/scale-test.yml

@@ -1,30 +0,0 @@
-name: "Scale test cellxgene APIs for initial loading"
-
-on:
-  schedule:
-    - cron: "0 0 * * Sun"
-
-jobs:
-  locust-build:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v2
-      - name: Set up Python 3.7
-        uses: actions/setup-python@v1
-        with:
-          python-version: 3.7
-      - name: Install dependencies
-        run: |
-          pip install -r backend/test/test_czi_hosted/locust/requirements-locust.txt
-      - name: Dev Scale Test
-        run: |
-          locust -f backend/test/test_czi_hosted/locust/locustfile.py --headless -u 30 -r 10 --host https://api.cellxgene.dev.single-cell.czi.technology/cellxgene/e/ --run-time 5m 2>&1 | tee locust_dev_stats.txt
-      - name: Slack success webhook
-        env:
-          SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
-        run: |
-          DEV_STATS=$(tail -n 15 locust_dev_stats.txt)
-          DEV_MSG="\`\`\`CELLXGENE EXPLORER DEV SCALE TEST RESULTS: ${DEV_STATS}\`\`\`"
-          curl -X POST -H 'Content-type: application/json' --data "{'text':'${DEV_MSG}'}" $SLACK_WEBHOOK
-
-

.gitignore

@@ -19,13 +19,9 @@ venv/
 cellxgene/
 
 # client build
-backend/server/common/web/static/*
-backend/server/common/web/templates/
-backend/server/common/web/csp-hashes.json
-
-backend/czi_hosted/common/web/static/*
-backend/czi_hosted/common/web/templates/
-backend/czi_hosted/common/web/csp-hashes.json
+server/common/web/static/*
+server/common/web/templates/
+server/common/web/csp-hashes.json
 
 # eb build
 artifact.dir

LICENSE.txt

@@ -1,6 +1,6 @@
 The MIT License (MIT)
 
-Copyright (c) 2017-2021 Chan Zuckerberg Initiative
+Copyright (c) 2013
 
 Permission is hereby granted, free of charge, to any person obtaining a copy of
 this software and associated documentation files (the "Software"), to deal in
@@ -17,4 +17,4 @@ IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS
 FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR
 COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER
 IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
-CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

MANIFEST.in

@@ -1,7 +1,5 @@
-recursive-include backend/server/common/web/templates *
-recursive-include backend/server/common/web/static *
+recursive-include server/common/web/templates *
+recursive-include server/common/web/static *
 
-include backend/server/requirements.txt
-include backend/server/requirements-prepare.txt
-include backend/server/converters/schema/hgnc_complete_set.txt.gz
-include backend/server/converters/schema/schema_definitions/*
+include server/requirements.txt
+include server/requirements-prepare.txt

MANIFEST_hosted.in

@@ -1,7 +0,0 @@
-recursive-include backend/czi_hosted/common/web/templates *
-recursive-include backend/czi_hosted/common/web/static *
-
-include backend/czi_hosted/requirements.txt
-include backend/czi_hosted/requirements-prepare.txt
-include backend/czi_hosted/converters/schema/hgnc_complete_set.txt.gz
-include backend/czi_hosted/converters/schema/schema_definitions/*

Makefile

@@ -2,32 +2,23 @@ include common.mk
 
 BUILDDIR := build
 CLIENTBUILD := $(BUILDDIR)/client
-CZIHOSTEDBUILD := $(BUILDDIR)/backend/czi_hosted
-SERVERBUILD := $(BUILDDIR)/backend/server
+SERVERBUILD := $(BUILDDIR)/server
 CLEANFILES :=  $(BUILDDIR)/ client/build build dist cellxgene.egg-info
 
 PART ?= patch
 
 # CLEANING
 .PHONY: clean
-clean: clean-lite clean-czi-hosted clean-server clean-client
+clean: clean-lite clean-server clean-client
 
 # cleaning the client's node_modules is the longest one, so we avoid that if possible
 .PHONY: clean-lite
 clean-lite:
 	rm -rf $(CLEANFILES)
 
-.PHONY: clean-client
-clean-client:
-	cd client && $(MAKE) clean
+clean-%:
+	cd $(*) && $(MAKE) clean
 
-.PHONY: clean-server
-clean-server:
-	cd backend/server && $(MAKE) clean
-
-.PHONY: clean-czi-hosted
-clean-czi-hosted:
-	cd backend/czi_hosted && $(MAKE) clean
 
 # BUILDING PACKAGE
 
@@ -37,71 +28,29 @@ build-client:
 
 .PHONY: build
 build: clean build-client
-	git ls-files backend/server/ | grep -v 'backend/server/test/' | cpio -pdm $(BUILDDIR)
+	git ls-files server/ | grep -v 'server/test/' | cpio -pdm $(BUILDDIR)
 	cp -r client/build/  $(CLIENTBUILD)
 	$(call copy_client_assets,$(CLIENTBUILD),$(SERVERBUILD))
-	cp backend/__init__.py $(BUILDDIR)
-	cp backend/__init__.py $(BUILDDIR)/backend
-	cp -r backend/common $(BUILDDIR)/backend/common
 	cp MANIFEST.in README.md setup.cfg setup.py $(BUILDDIR)
 
-.PHONY: build-czi-hosted
-build-czi-hosted: clean build-client
-	git ls-files backend/czi_hosted/ | grep -v 'backend/czi_hosted/test/' | cpio -pdm $(BUILDDIR)
-	cp -r client/build/  $(CLIENTBUILD)
-	$(call copy_client_assets,$(CLIENTBUILD),$(CZIHOSTEDBUILD))
-	cp -r backend/common $(BUILDDIR)/backend/common
-	cp backend/__init__.py $(BUILDDIR)
-	cp backend/__init__.py $(BUILDDIR)/backend
-	cp MANIFEST_hosted.in README.md setup.cfg setup_hosted.py $(BUILDDIR)
-	mv $(BUILDDIR)/setup_hosted.py $(BUILDDIR)/setup.py
-	mv $(BUILDDIR)/MANIFEST_hosted.in $(BUILDDIR)/MANIFEST.in
-
 # If you are actively developing in the server folder use this, dirties the source tree
 .PHONY: build-for-server-dev
 build-for-server-dev: clean-server build-client
-	$(call copy_client_assets,client/build,backend/server)
-
-.PHONY: build-for-czi-hosted-dev
-build-for-czi-hosted-dev: clean-czi-hosted build-client
-	$(call copy_client_assets,client/build,backend/czi_hosted)
+	$(call copy_client_assets,client/build,server)
 
 .PHONY: copy-client-assets
 copy-client-assets:
-	$(call copy_client_assets,client/build,backend/server)
-
-.PHONY: copy-client-assets-czi-hosted
-copy-client-assets-czi-hosted:
-	$(call copy_client_assets,client/build,backend/czi_hosted)
+	$(call copy_client_assets,client/build,server)
 
 # TESTING
 .PHONY: test
 test: unit-test smoke-test
 
 .PHONY: unit-test
-unit-test: unit-test-server unit-test-client unit-test-common
+unit-test: unit-test-server unit-test-client
 
-.PHONY: test-server
-test-server: unit-test-server smoke-test
-
-.PHONY: test-czi-hosted
-test-czi-hosted: unit-test-czi-hosted smoke-test
-
-.PHONY: unit-test-client
-unit-test-client:
-	cd client && $(MAKE) unit-test
-
-.PHONY: unit-test-czi-hosted
-unit-test-czi-hosted:
-	cd backend/czi_hosted && $(MAKE) unit-test
-
-.PHONY: unit-test-server
-unit-test-server:
-	cd backend/server && $(MAKE) unit-test
-
-.PHONY: unit-test-common
-unit-test-common:
-	cd backend/common && $(MAKE) unit-test
+unit-test-%:
+	cd $(*) && $(MAKE) unit-test
 
 .PHONY: smoke-test
 smoke-test:
@@ -113,11 +62,12 @@ smoke-test-annotations:
 
 .PHONY: test-db
 test-db:
-	cd backend/czi_hosted && $(MAKE) test-db
+	cd server && $(MAKE) test-db
+
 
 # FORMATTING CODE
 
-.PHONY: fmt
+.PHOHY: fmt
 fmt: fmt-client fmt-py
 
 .PHONY: fmt-client
@@ -129,18 +79,11 @@ fmt-py:
 	black .
 
 .PHONY: lint
-lint: lint-servers lint-client
-
-.PHONY: lint-servers
-lint-servers: lint-server lint-czi-hosted-server
+lint: lint-server lint-client
 
 .PHONY: lint-server
-lint-server: fmt-py
-	flake8 backend/server --per-file-ignores='backend/test/fixtures/dataset_config_outline.py:F821 backend/test/fixtures/server_config_outline.py:F821 backend/server/test/performance/scale_test_annotations.py:E501'
-
-.PHONY: lint-czi-hosted-server
-lint-czi-hosted-server: fmt-py
-	flake8 backend/czi_hosted --per-file-ignores='backend/test/fixtures/czi_hosted_dataset_config_outline.py:F821 backend/test/fixtures/czi_hosted_server_config_outline.py:F821 backend/test/performance/scale_test_annotations.py:E501'
+lint-server:
+	flake8 server
 
 .PHONY: lint-client
 lint-client:
@@ -153,40 +96,25 @@ pydist: build
 	cd $(BUILDDIR); python setup.py sdist -d ../dist
 	@echo "done"
 
-.PHONY: pydist-czi-hosted
-pydist-czi-hosted: build-czi-hosted
-	cd $(BUILDDIR); python setup.py sdist -d ../dist
-	@echo "done"
-
 
 # RELEASE HELPERS
 
-# Create new version to commit to main
-.PHONY: create-release-candidate
-create-release-candidate: dev-env bump-version clean-lite gen-package-lock
+# create new version to commit to main
+.PHONY: release-stage-1
+release-stage-1: dev-env bump clean-lite gen-package-lock
 	@echo "Version bumped part:$(PART) and client built. Ready to commit and push"
 
-# Bump the release candidate version if needed (i.e. the previous release candidate had errors).
-.PHONY: recreate-release-candidate
-recreate-release-candidate: dev-env bump-release-candidate clean-lite gen-package-lock
-	@echo "Version bumped part:$(PART) and client built. Ready to commit and push"
-
-# Build dist and release to Test PyPI
-.PHONY: release-candidate-to-test-pypi
-release-candidate-to-test-pypi: dev-env pydist twine
+# build dist and release to dev pypi
+.PHONY: release-stage-2
+release-stage-2: dev-env pydist twine
 	@echo "Dist built and uploaded to test.pypi.org"
 	@echo "Test the install:"
 	@echo "    make install-release-test"
+	@echo "Then upload to Pypi prod:"
+	@echo "    make twine-prod"
 
-# Build final dist (gets rid of the rc tag) and release final candidate to TestPyPI
-.PHONY: release-final-to-test-pypi
-release-final-to-test-pypi: dev-env bump-release clean-lite gen-package-lock pydist twine
-	@echo "Final release dist built and uploaded to test.pypi.org"
-	@echo "Test the install:"
-	@echo "    make install-release-test"
-
-.PHONY: release-final
-release-final: twine-prod
+.PHONY: release-stage-final
+release-stage-final: twine-prod
 	@echo "Release uploaded to pypi.org"
 
 # DANGER: releases directly to prod
@@ -206,27 +134,13 @@ dev-env-client:
 
 .PHONY: dev-env-server
 dev-env-server:
-	pip install -r backend/server/requirements-dev.txt
+	pip install -r server/requirements-dev.txt
 
-.PHONY: dev-env-czi-hosted
-dev-env-czi-hosted:
-	pip install -r backend/czi_hosted/requirements-dev.txt
-# Set PART=[major, minor, patch] as param to make bump.
-# This will create a release candidate. (i.e. 0.16.1 -> 0.16.2-rc.0 for a patch bump)
-.PHONY: bump-version
-bump-version:
+# give PART=[major, minor, part] as param to make bump
+.PHONY: bump
+bump:
 	bumpversion --config-file .bumpversion.cfg $(PART)
 
-# Increments the release candidate version (i.e. 0.16.2-rc.1 -> 0.16.2-rc.2)
-.PHONY: bump-release-candidate
-bump-release-candidate:
-	bumpversion --config-file .bumpversion.cfg prerelversion --allow-dirty
-
-# Finalizes the release candidate by removing the release candidate tag (i.e. 0.16.2-rc.2 -> 0.16.2).
-.PHONY: bump-release
-bump-release:
-	bumpversion --config-file .bumpversion.cfg prerel --allow-dirty
-
 .PHONY: twine
 twine:
 	twine upload --repository-url https://test.pypi.org/legacy/ dist/*

PULL_REQUEST_TEMPLATE.md

@@ -1,11 +0,0 @@
-#### Reviewers
-**Functional:** 
-
-**Readability:** 
-
----
-
-## Changes
-- add
-- remove
-- modify

README.md

@@ -52,6 +52,7 @@ cellxgene currently supports the following browsers:
 - Google Chrome 61+
 - Edge 15+
 - Firefox 60+
+- Safari 10.1+
 
 Please [file an issue](https://github.com/chanzuckerberg/cellxgene/issues/new/choose) if you would like us to add support for an unsupported browser.
 
@@ -66,30 +67,37 @@ For any errors, [report bugs on Github](https://github.com/chanzuckerberg/cellxg
 
 ### Contributing
 
-We warmly welcome contributions from the community! Please see our [contributing guide](https://chanzuckerberg.github.io/cellxgene/posts/contribute) and don't hesitate to open an issue or send a pull request to improve cellxgene. Please see the [dev_docs](https://github.com/chanzuckerberg/cellxgene/tree/main/dev_docs) for pull request suggestions, unit test details, local documentation preview, and other development specifics. 
+We warmly welcome contributions from the community! Please see our [contributing guide](https://chanzuckerberg.github.io/cellxgene/posts/contribute) and don't hesitate to open an issue or send a pull request to improve cellxgene.
 
 This project adheres to the Contributor Covenant [code of conduct](https://github.com/chanzuckerberg/.github/blob/master/CODE_OF_CONDUCT.md). By participating, you are expected to uphold this code. Please report unacceptable behavior to opensource@chanzuckerberg.com.
 
 ### Reuse
 
-This project was started with the sole goal of empowering the scientific community to explore and understand their data. 
-As such, we encourage other scientific tool builders in academia or industry to adopt the patterns, tools, and code from 
-this project. All code is freely available for reuse under the [MIT license](https://opensource.org/licenses/MIT).
-
-
-Before extending cellxgene, we encourage you to reach out to us with ideas or questions. It might be possible that an 
-extension could be directly contributed, which would make it available for a wider audience, or that it's on our 
-[roadmap](./docs/posts/roadmap.md) and under active development. 
-
-See the [cellxgene extensions](./docs/posts/extensions.md) section of our documentation for examples of community use and cellxgene extensions. 
+This project was started with the sole goal of empowering the scientific community to explore and understand their data. As such, we encourage other scientific tool builders in academia or industry to adopt the patterns, tools, and code from this project, and reach out to us with ideas or questions. All code is freely available for reuse under the [MIT license](https://opensource.org/licenses/MIT).
 
 ### Security
 
 If you believe you have found a security issue, we would appreciate notification. Please send email to <security@chanzuckerberg.com>.
 
-# Inspiration
+# About
 
-We've been heavily inspired by several other related single-cell visualization projects, including the [UCSC Cell Browser](http://cells.ucsc.edu/), [Cytoscape](http://www.cytoscape.org/), [Xena](https://xena.ucsc.edu/), [ASAP](https://asap.epfl.ch/), [GenePattern](http://genepattern-notebook.org/), and many others. We hope to explore collaborations where useful as this community works together on improving interactive visualization for single-cell data.
+### Core team
+
+The current core team:
+
+- Colin Megill, frontend & product design
+- Bruce Martin, software engineer
+- Sidney Bell, computational biologist
+- Lia Prins, designer
+- Severiano Badajoz, software engineer
+
+We would also like to gratefully acknowledge contributions from past core team members:
+
+- Charlotte Weaver, software engineer
+
+### Inspiration
+
+We've been heavily inspired by several other related single-cell visualization projects, including the [UCSC Cell Browswer](http://cells.ucsc.edu/), [Cytoscape](http://www.cytoscape.org/), [Xena](https://xena.ucsc.edu/), [ASAP](https://asap.epfl.ch/), [Gene Pattern](http://genepattern-notebook.org/), and many others. We hope to explore collaborations where useful as this community works together on improving interactive visualization for single-cell data.
 
 We were inspired by Mike Bostock and the [crossfilter](https://github.com/crossfilter) team for the design of our filtering implementation.
 

backend/common/Makefile

@@ -1,11 +0,0 @@
-
-.PHONY: unit-test
-unit-test:
-	PYTHONWARNINGS=ignore:ResourceWarning coverage run \
-		--source=fbs,utils \
-		--omit=.coverage,data_common/fbs/NetEncoding,venv \
-		-m unittest discover \
-		--start-directory ../test/test_common/unit \
-		--top-level-directory ../../ \
-		--verbose; test_result=$$?; \
-	exit $$test_result \

backend/common/compute/estimate_distribution.py

@@ -1,87 +0,0 @@
-import numba
-import concurrent.futures
-import numpy as np
-from scipy import sparse
-from backend.common.constants import XApproximateDistribution
-
-
-@numba.njit(error_model="numpy", nogil=True)
-def min_max(arr: np.ndarray):
-    """Return (min, max) values for the ndarray."""
-
-    # initialize to first finite value in array.  Normally,
-    # this will exit on the first value.
-    for i in range(arr.size):
-        min_val = max_val = arr[i]
-        if np.isfinite(min_val):
-            break
-
-    # now find min/max, unrolled by two
-    odd = arr.size % 2
-    unrolled_loop_limit = arr.size - 1 if odd else arr.size
-    i = 0
-    while i < unrolled_loop_limit:
-        x = arr[i]
-        y = arr[i + 1]
-
-        # ignore non-finites
-        x = x if np.isfinite(x) else min_val
-        y = y if np.isfinite(y) else min_val
-
-        if x > y:
-            x, y = y, x
-        min_val = min(x, min_val)
-        max_val = max(y, max_val)
-        i += 2
-
-    # handle the tail if any
-    if odd:
-        x = arr[arr.size - 1]
-
-        # ignore non-finites
-        x = x if np.isfinite(x) else min_val
-
-        min_val = min(x, min_val)
-        max_val = max(x, max_val)
-
-    return min_val, max_val
-
-
-def estimate_approximate_distribution(X) -> XApproximateDistribution:
-    """
-    Estimate the distribution (normal, count) of the X matrix.
-
-    Currently this is based upon the assumption that scRNA-seq data is
-    exponentially distributed in its raw (count) form, and when logged,
-    any (max-min) range in excess of 24 is implies tens of millions of
-    observations of a single feature and so is extremely unlikely.
-    """
-    if X.dtype.kind not in ["i", "u", "f"]:
-        raise TypeError(f"Unsupported matrix dtype: {X.dtype.name}")
-
-    if X.size == 0:
-        # default for empty array
-        return XApproximateDistribution.NORMAL
-
-    if sparse.isspmatrix_csc(X) or sparse.isspmatrix_csr(X):
-        Xdata = X.data
-    elif type(X) is np.ndarray:
-        Xdata = X.reshape(
-            X.size,
-        )
-    else:
-        raise TypeError(f"Unsupported matrix format: {str(type(X))}")
-
-    CHUNKSIZE = 1 << 24
-    if Xdata.size > CHUNKSIZE:
-        min_val = max_val = Xdata[0]
-        with concurrent.futures.ThreadPoolExecutor() as tp:
-            for (_min, _max) in tp.map(min_max, [Xdata[i : i + CHUNKSIZE] for i in range(0, Xdata.size, CHUNKSIZE)]):
-                min_val = min(_min, min_val)
-                max_val = max(_max, max_val)
-
-    else:
-        min_val, max_val = min_max(Xdata)
-
-    excess_range = (max_val - min_val) > 24
-    return XApproximateDistribution.COUNT if excess_range else XApproximateDistribution.NORMAL

backend/common/genesets.py

@@ -1,239 +0,0 @@
-"""
-Utility code for gene sets handling
-"""
-
-import re
-import csv
-import hashlib
-
-from .errors import AnnotationsError
-
-
-GENESETS_TIDYCSV_HEADER = [
-    "gene_set_name",
-    "gene_set_description",
-    "gene_symbol",
-    "gene_description",
-]
-
-
-def read_gene_sets_tidycsv(gs_locator, context=None):
-    """
-    Read & parse the Tidy CSV format, applying validation checks for mandatory
-    values, and de-duping rules.
-
-    Format is a four-column CSV, with a mandatory header row, and optional "#" prefixed
-    comments.  Format:
-
-        gene_set_name, gene_set_description, gene_symbol, gene_description
-
-    gene_set_name must be non-null; others are optional.
-
-    Returns: a dictionary of the shape (values in angle-brackets vary):
-
-        {
-            <string, a gene set name>: {
-                "geneset_name": <string, a gene set name>,
-                "geneset_description": <a string or None>,
-                "genes": [
-                    {
-                        "gene_symbol": <string, a gene symbol or name>,
-                        "gene_description": <a string or None>
-                    },
-                    ...
-                ]
-            },
-            ...
-        }
-    """
-
-    class myDialect(csv.excel):
-        skipinitialspace = False
-
-    def just(n, seq):
-        it = iter(seq)
-        for _ in range(n - 1):
-            yield next(it, "")
-        yield tuple(it)
-
-    messagefn = context["messagefn"] if context else (lambda x: None)
-
-    gene_sets = {}
-    with gs_locator.local_handle() as fname:
-        with open(fname, newline="") as f:
-            reader = csv.reader(f, dialect=myDialect())
-            haveReadHeader = False
-            lineno = 0
-            for row in reader:
-                lineno += 1
-                # ignore empty rows
-                if len(row) == 0:
-                    continue
-                # if row starts with '#' it is a comment
-                if row[0].startswith("#"):
-                    continue
-                # if this is the first non-comment row, assume it is a header and validate
-                # column names.  OK if the user has extra columns after our initial set.
-                if not haveReadHeader:
-                    if row[0:len(GENESETS_TIDYCSV_HEADER)] != GENESETS_TIDYCSV_HEADER:
-                        raise AnnotationsError("Gene set CSV file missing the required column header.")
-                    haveReadHeader = True
-                    continue
-
-                geneset_name, geneset_description, gene_symbol, gene_description, _ = just(5, row)
-                if not geneset_name:
-                    raise AnnotationsError(f"Gene set CSV missing required gene set name on line {lineno}")
-                if (not gene_symbol) and gene_description:
-                    messagefn(f"Warning: Missing gene name in gene set name {geneset_name} on line {lineno}.")
-
-                if geneset_name in gene_sets:
-                    gs = gene_sets[geneset_name]
-                else:
-                    gs = gene_sets[geneset_name] = {
-                        "geneset_name": geneset_name,
-                        "geneset_description": geneset_description,
-                        "genes": [],
-                    }
-                # Use first geneset_description with a value
-                if not gs["geneset_description"] and geneset_description:
-                    gs["geneset_description"] = geneset_description
-                # add the gene if the gene_symbol is defined
-                if gene_symbol:
-                    gs["genes"].append(
-                        {
-                            "gene_symbol": gene_symbol,
-                            "gene_description": gene_description,
-                        }
-                    )
-
-    return gene_sets
-
-
-def write_gene_sets_tidycsv(f, genesets):
-    """
-    Convert the internal gene sets format (returned by read_gene_set_tidycsv) into
-    the simple Tidy CSV.
-    """
-    writer = csv.writer(f, dialect="excel")
-    writer.writerow(GENESETS_TIDYCSV_HEADER)
-    for geneset in genesets:
-        # genes may be empty, in which case we skip the gene set entirely
-        genes = geneset["genes"]
-        if not genes:
-            writer.writerow([geneset["geneset_name"], geneset.get("geneset_description", ""), "", ""])
-        else:
-            writer.writerows(
-                [
-                    [
-                        geneset["geneset_name"],
-                        geneset.get("geneset_description", ""),
-                        gene["gene_symbol"],
-                        gene.get("gene_description", ""),
-                    ]
-                    for gene in genes
-                ]
-            )
-
-
-def summarizeQueryHash(raw_query):
-    """ generate a cache key (hash) from the raw query string """
-    return hashlib.sha1(raw_query).hexdigest()
-
-
-def validate_gene_sets(genesets, var_names, context=None):
-    """
-    Check validity of gene sets, return if correct, else raise error.
-    May also modify the gene set for conditions that should be resolved,
-    but which do not warrant a hard error.
-
-    Argument gene sets may be either the REST OTA format (list of dicts) or the internal
-    format (dict of dicts, keyed by the gene set name).
-
-    Will return a modified gene sets (eg, remove warnings) of the same type as the
-    provided argument. Ie, dict->dict, list->list
-
-    Rules:
-
-    0. All gene set names must be unique. [error]
-    1. Gene set names must conform to the following: [error]
-        * Names must be comprised of 1 or more ASCII characters 32-126
-        * No leading or trailing spaces (ASCII 32)
-        * No multi-space (ASCII 32) runs
-    2. Gene symbols must be part of the current var_index. [warning]
-       If gene symbol is not in the var_index, generate a warning and remove the symbol
-       from the gene sets.
-    3. Gene symbols must not be duplicated in a gene set.  [warning]
-       Duplications will be silently de-duped.
-
-    Items marked [error] will generate a hard error, causing the validation to fail.
-
-    Items marked [warning] will generate a warning, and will be resolved without failing
-    the validation (typically by removing the offending item from the gene sets).
-    """
-
-    messagefn = context["messagefn"] if context else (lambda x: None)
-
-    # accept genesets args as either the internal (dict) or REST (list) format,
-    # as they are identical except for the dict being keyed by geneset_name.
-    if not isinstance(genesets, dict) and not isinstance(genesets, list):
-        raise ValueError("Gene sets must be either dict or list.")
-    genesets_iterable = genesets if isinstance(genesets, list) else genesets.values()
-
-    # 0. check for uniqueness of geneset names
-    geneset_names = [gs["geneset_name"] for gs in genesets_iterable]
-    if len(set(geneset_names)) != len(geneset_names):
-        raise KeyError("All gene set names must be unique.")
-
-    # 1. check gene set character set and format
-    illegal_name = re.compile(r"^\s|  |[\u0000-\u001F\u007F-\uFFFF]|\s$")
-    for name in geneset_names:
-        if type(name) != str or len(name) == 0:
-            raise KeyError("Gene set names must be non-null string.")
-        if illegal_name.search(name):
-            messagefn(
-                "Error: "
-                f"Gene set name {name} "
-                "is not valid. Leading, trailing, and multiple spaces within a name are not allowed."
-            )
-            raise KeyError(
-                "Gene set name is not valid. Leading, trailing, and multiple spaces within a name are not allowed."
-            )
-
-    # 2. & 3. check for duplicate gene symbols, and those not present in the dataset. They will
-    # generate a warning and be removed.
-    for geneset in genesets_iterable:
-        if not isinstance(geneset, dict):
-            raise ValueError("Each gene set must be a dict.")
-        geneset_name = geneset["geneset_name"]
-        genes = geneset["genes"]
-        if not isinstance(genes, list):
-            raise ValueError("Gene set genes field must be a list")
-        geneset.setdefault("geneset_description", "")
-        gene_symbol_already_seen = set()
-        new_genes = []
-        for gene in genes:
-            gene_symbol = gene["gene_symbol"]
-            if not isinstance(gene_symbol, str) or len(gene_symbol) == 0:
-                raise ValueError("Gene symbol must be non-null string.")
-            if gene_symbol in gene_symbol_already_seen:
-                # duplicate check
-                messagefn(
-                    f"Warning: a duplicate of gene {gene_symbol} was found in gene set {geneset_name}, "
-                    "and will be ignored."
-                )
-                continue
-
-            if gene_symbol not in var_names:
-                messagefn(
-                    f"Warning: {gene_symbol}, used in gene set {geneset_name}, "
-                    "was not found in the dataset and will be ignored."
-                )
-                continue
-
-            gene_symbol_already_seen.add(gene_symbol)
-            gene.setdefault("gene_description", "")
-            new_genes.append(gene)
-
-        geneset["genes"] = new_genes
-
-    return genesets

backend/common/utils/aws_secret_utils.py

@@ -1,23 +0,0 @@
-import logging
-
-import boto3
-from flask import json
-
-from backend.common.errors import SecretKeyRetrievalError
-
-
-def get_secret_key(region_name, secret_name):
-    session = boto3.session.Session()
-    client = session.client(service_name="secretsmanager", region_name=region_name)
-
-    try:
-        get_secret_value_response = client.get_secret_value(SecretId=secret_name)
-        if "SecretString" in get_secret_value_response:
-            var = get_secret_value_response["SecretString"]
-            secret = json.loads(var)
-            return secret
-    except Exception as e:
-        logging.critical(f"Caught exception during get_secret_key, {e}", exc_info=True)
-        raise SecretKeyRetrievalError(str(e))
-
-    return None

backend/common/utils/type_conversion_utils.py

@@ -1,191 +0,0 @@
-from typing import Union, Tuple
-import logging
-
-import numpy as np
-import pandas as pd
-
-"""
-These routines drive all type inference for the schema generation and the
-FBS (REST OTA) encoding. They are also used for CXG generation.
-
-
-H5AD Type                       REST              REST
-(ndarray, Series, Index)        FBS encoding      schema type       ERROR/exceptions
-----------------------------    --------------    ---------------   ----------------------
-bool_/bool                      uint8             boolean
-(u)int8, (u)int16, int32        int32             int32
-uint32, (u)int64                int32             int32             CHECKS value bounds
-float16, float32, float64       float32           float32[0]
-
-categorical[T is numeric[4]]:
-    hasna = False               T                 categorical[1]
-    hasna = True                float32           categorical[1]    CHECKS value bounds
-
-categorical[T not numeric]      JSON/str          categorical[1,2]
-
-(other object)                  JSON/str          string
-
-(all other)                                                         Always an ERROR[3]
-
-
-Notes:
-[0] IEEE format, includes non-finite numbers (NaN, Inf, ...)
-[1] with NO categories enumerated (client side does it to handle rounding)
-[2] NA (undefined) categories are assigned a JSON null value
-[3] Includes all other numpy types:  datetime, complex, etc.
-[4] means float, int, uint (dtype.kind in ['i','u','f'])
-
-"""
-
-
-def get_dtypes_and_schemas_of_dataframe(dataframe: pd.DataFrame):
-    dtypes_by_column_name = {}
-    schema_type_hints_by_column_name = {}
-
-    for column_name, column_values in dataframe.items():
-        (
-            dtypes_by_column_name[column_name],
-            schema_type_hints_by_column_name[column_name],
-        ) = get_dtype_and_schema_of_array(column_values)
-
-    return dtypes_by_column_name, schema_type_hints_by_column_name
-
-
-def get_encoding_dtype_of_array(array: Union[np.ndarray, pd.Series, pd.Index]) -> np.dtype:
-    return _get_type_info(array)[0]
-
-
-def get_schema_type_hint_of_array(array: Union[np.ndarray, pd.Series, pd.Index]) -> dict:
-    return _get_type_info(array)[1]
-
-
-def get_dtype_and_schema_of_array(array: Union[np.ndarray, pd.Series, pd.Index]) -> Tuple[np.dtype, dict]:
-    """Return tuple (encoding_dtype, schema_type_hint)"""
-    return _get_type_info(array)
-
-
-def get_schema_type_hint_from_dtype(dtype) -> dict:
-    res = _get_type_info_from_dtype(dtype)
-    if res is None:
-        raise TypeError(f"Annotations of type {dtype} are unsupported.")
-    else:
-        return res[1]
-
-
-def _get_type_info_from_dtype(dtype) -> Union[Tuple[np.dtype, dict], None]:
-    """
-    Best-effort to determine encoding type and schema hint from a dtype.
-    If this is not possible, or the type is unsupported, return None.
-
-    This should be a subset of the cases which are supported by
-    _get_type_info().  The latter should be preferred if the array (values)
-    are available for typing.
-    """
-    if dtype.kind == "b":
-        return (np.uint8, {"type": "boolean"})
-
-    if dtype.kind == "U":
-        return (np.dtype(str), {"type": "string"})
-
-    if dtype.kind in ["i", "u"]:
-        if np.can_cast(dtype, np.int32):
-            return (np.int32, {"type": "int32"})
-
-    if dtype.kind == "f":
-        _float64_warning(dtype)
-        return (np.float32, {"type": "float32"})
-
-    if dtype.kind == "O" and not dtype.name == "category":
-        return (np.dtype(str), {"type": "string"})
-
-    return None
-
-
-def _get_type_info(array: Union[np.ndarray, pd.Series, pd.Index]) -> Tuple[np.dtype, dict]:
-    """
-    Determine encoding type and schema hint from an array.  This allows more
-    flexible casting than may be possible by using just the dtype, as it can
-    account for category types and array values.
-    """
-    if (
-        not isinstance(array, np.ndarray)
-        and not isinstance(array, pd.Series)
-        and not isinstance(array, pd.Index)
-        and not hasattr(array, "dtype")
-    ):
-        raise TypeError("Unsupported data type.")
-
-    dtype = array.dtype
-
-    res = _get_type_info_from_dtype(dtype)
-    if res is not None:
-        return res
-
-    if dtype.kind == "O":
-        if dtype.name == "category":
-            # Sometimes CategoricalDType can be encoded as int or float without further fuss.
-            # Do not specify the categories in the schema - let the client-side figure it out
-            # on its own.  Utilize Series.to_numpy() to do casting that handles categorical
-            # NA/NaN (missing or undefined) categories.
-            if dtype.categories.dtype.kind in ["f", "i", "u"]:
-                return (
-                    _get_type_info(array.to_numpy())[0],
-                    {"type": "categorical"},
-                )
-            else:
-                return (np.dtype(str), {"type": "categorical", "categories": dtype.categories.to_list()})
-
-        # all other extension types are str-encoded
-        return (np.dtype(str), {"type": "string"})
-
-    if dtype.kind in ["i", "u"] and _can_cast_array_values_to_int32(array):
-        return (np.int32, {"type": "int32"})
-
-    if dtype.kind == "f":
-        _float64_warning(array.dtype)
-        return (np.float32, {"type": "float32"})
-
-    raise TypeError(f"Annotations of type {dtype} are unsupported.")
-
-
-def _float64_warning(dtype):
-    """
-    Warn the user if we are down-casting a float64 to float32, and may potentially lose information.
-    """
-    if dtype.kind == "f" and not np.can_cast(dtype, np.float32):
-        logging.warning(f"Type {dtype.name} will be converted to 32 bit float and may lose precision.")
-
-
-def _can_cast_array_values_to_int32(array: Union[np.ndarray, pd.Series, pd.Index]) -> bool:
-    """
-    Return true if the (U)INT array values can be safely cast to int32.  We allow size reducing
-    casts (ie, int64 to int32) if no actual values require the larger size (ie, actual values
-    can be represented by the smaller type).
-    """
-    assert array.dtype.kind in ["u", "i"]
-
-    if np.can_cast(array.dtype, np.int32):
-        return True
-
-    if array.size == 0:
-        return True
-
-    int32_machine_limits = np.iinfo(np.int32)
-    if array.min() >= int32_machine_limits.min and array.max() <= int32_machine_limits.max:
-        return True
-
-    return False
-
-
-def convert_string_to_value(value: str):
-    """convert a string to value with the most appropriate type"""
-    if value.lower() == "true":
-        return True
-    if value.lower() == "false":
-        return False
-    if value == "null":
-        return None
-    try:
-        return eval(value)
-    except:  # noqa E722
-        return value

backend/czi_hosted/Makefile

@@ -1,49 +0,0 @@
-include ../../common.mk
-
-.PHONY: clean
-clean:
-	rm -f common/web/templates/index.html
-	rm -rf common/web/static
-	rm -f common/web/csp-hashes.json
-
-.PHONY: unit-test
-unit-test: create-test-db
-	PYTHONWARNINGS=ignore:ResourceWarning coverage run \
-		--source=app,auth,cli,common,compute,converters,data_anndata,data_common,data_cxg,eb \
-		--omit=.coverage,venv \
-		-m unittest discover \
-		--start-directory ../test/test_czi_hosted/unit \
-		--top-level-directory ../.. \
-		--verbose; test_result=$$?; \
-	$(MAKE) clean-test-db; \
-	exit $$test_result \
-
-
-.PHONY: test-db
-test-db: create-test-db
-	PYTHONWARNINGS=ignore:ResourceWarning coverage run \
-		--source=db \
-		--omit=.coverage,venv \
-		-m unittest discover \
-		--start-directory ../test/test_czi_hosted/test_database \
-		--top-level-directory ../.. \
-		--verbose; test_result=$$?; \
-	$(MAKE) clean-test-db; \
-	exit $$test_result
-
-.PHONY: create-test-db
-create-test-db:
-	-docker run -d -p 5432:5432 --name test_db -e POSTGRES_PASSWORD=test_pw postgres
-
-.PHONY: clean-test-db
-clean-test-db:
-	-docker stop test_db
-	-docker rm test_db
-
-.PHONY: test-annotations-performance
-test-annotations-performance:
-	python ../test/test_czi_hosted/performance/performance_test_annotations_backend.py
-
-.PHONY: test-annotations-scale
-test-annotations-scale:
-	locust -f ../test/test_czi_hosted/performance/scale_test_annotations.py --headless -u 30 -r 10 --host https://api.cellxgene.dev.single-cell.czi.technology/cellxgene/e/ --run-time 5m 2>&1 | tee locust_dev_stats.txt

backend/czi_hosted/__init__.py

@@ -1,15 +0,0 @@
-import logging
-import sys
-from backend.common.utils.utils import import_plugins
-
-__version__ = "0.16.7"
-
-
-display_version = "cellxgene v" + __version__
-
-try:
-    import_plugins("backend.czi_hosted.plugins")
-except Exception as e:
-    # Make sure to exit in this case, as the server may not be configured as expected.
-    logging.critical(f"Error in import_plugins: {str(e)}")
-    sys.exit(1)

backend/czi_hosted/__main__.py

@@ -1,14 +0,0 @@
-# Work around bug https://github.com/pallets/werkzeug/issues/461
-if __package__ is None:
-    import sys
-    from pathlib import Path
-
-    PKG_PATH = Path(__file__).parent
-    sys.path.insert(0, str(PKG_PATH.parent))
-    import backend.czi_hosted # noqa F401
-    __package__ = PKG_PATH.name
-
-# Main thing
-from .cli.cli import cli  # noqa F402
-
-cli()

backend/czi_hosted/auth/__init__.py

@@ -1,6 +0,0 @@
-# import the built in auth types so they can be registered
-
-import backend.czi_hosted.auth.auth_test  # noqa: F401
-import backend.czi_hosted.auth.auth_session  # noqa: F401
-import backend.czi_hosted.auth.auth_oauth  # noqa: F401
-import backend.czi_hosted.auth.auth_none  # noqa: F401

backend/czi_hosted/auth/auth.py

@@ -1,91 +0,0 @@
-from abc import ABC, abstractmethod
-
-
-class AuthTypeBase(ABC):
-    """Base type for all authentication types."""
-
-    def __init__(self):
-        super().__init__()
-
-    @abstractmethod
-    def is_valid_authentication_type(self):
-        """Return True if the auth type is valid, e.g. it can return userinfo and username.
-          (AuthTypeNone is the only one type that returns False)"""
-        pass
-
-    def requires_client_login(self):
-        """Return True if the user needs to login from the client (e.g. Login button is shown)"""
-        return False
-
-    @abstractmethod
-    def complete_setup(self, app):
-        """complete any setup that may be needed by this auth type.  The Flask app is passed in.
-        This is the last auth function called before the server starts to run."""
-        pass
-
-    @abstractmethod
-    def is_user_authenticated(self):
-        """Return True if the user is authenticated"""
-        pass
-
-    @abstractmethod
-    def get_user_id(self):
-        """Return the id for this user (string)"""
-        pass
-
-    @abstractmethod
-    def get_user_name(self):
-        """Return the name of the user (string)"""
-        pass
-
-    @abstractmethod
-    def get_user_email(self):
-        """Return the name of the user (string)"""
-        pass
-
-    def get_user_picture(self):
-        """Return the location to the user's picture"""
-        return None
-
-
-class AuthTypeClientBase(AuthTypeBase):
-    """Base type for all authentication types that require the client to login"""
-
-    def __init__(self):
-        super().__init__()
-
-    def requires_client_login(self):
-        return True
-
-    @abstractmethod
-    def add_url_rules(self, selfapp):
-        """Add url rules to the app (like /login, /logout, etc)"""
-        pass
-
-    @abstractmethod
-    def get_login_url(self, data_adaptor):
-        """Return the url for the login route"""
-        pass
-
-    @abstractmethod
-    def get_logout_url(self, data_adaptor):
-        """Return the url for the logout route"""
-        pass
-
-
-class AuthTypeFactory:
-    """Factory class to create an authentication type"""
-
-    auth_types = {}
-
-    @staticmethod
-    def register(name, auth_type):
-        assert issubclass(auth_type, AuthTypeBase)
-        AuthTypeFactory.auth_types[name] = auth_type
-
-    @staticmethod
-    def create(name, app_config):
-        auth_type = AuthTypeFactory.auth_types.get(name)
-        if auth_type is None:
-            return None
-        return auth_type(app_config)

backend/czi_hosted/auth/auth_none.py

@@ -1,27 +0,0 @@
-from backend.czi_hosted.auth.auth import AuthTypeBase, AuthTypeFactory
-
-
-class AuthTypeNone(AuthTypeBase):
-    def __init__(self, app_config):
-        super().__init__()
-
-    def is_valid_authentication_type(self):
-        return False
-
-    def complete_setup(self, app):
-        pass
-
-    def is_user_authenticated(self):
-        return True
-
-    def get_user_id(self):
-        return None
-
-    def get_user_name(self):
-        return None
-
-    def get_user_email(self):
-        return None
-
-
-AuthTypeFactory.register(None, AuthTypeNone)

backend/czi_hosted/auth/auth_session.py

@@ -1,40 +0,0 @@
-from flask import session
-from uuid import uuid4
-
-from backend.czi_hosted.auth.auth import AuthTypeBase, AuthTypeFactory
-
-
-class AuthTypeSession(AuthTypeBase):
-    """Session based authentication.  The user is always logged.  The user id is a random number
-    associated with the session.  This is a good choice for desktop servers."""
-
-    # key in the session token for userid
-    CXGUID = "cxguid"
-
-    def __init__(self, app_config):
-        super().__init__()
-
-    def is_valid_authentication_type(self):
-        return True
-
-    def complete_setup(self, app):
-        pass
-
-    def is_user_authenticated(self):
-        # always authenticated
-        return True
-
-    def get_user_id(self):
-        if self.CXGUID not in session:
-            session[self.CXGUID] = uuid4().hex
-            session.permanent = True
-        return session[self.CXGUID]
-
-    def get_user_name(self):
-        return "anonymous"
-
-    def get_user_email(self):
-        return None
-
-
-AuthTypeFactory.register("session", AuthTypeSession)

backend/czi_hosted/cli/schema.py

@@ -1,72 +0,0 @@
-import click
-
-from backend.czi_hosted.converters.schema import remix, validate
-
-
-@click.group(
-    name="schema",
-    subcommand_metavar="COMMAND <args>",
-    short_help="Apply and validate the cellxgene data integration schema to an h5ad file.",
-    context_settings=dict(max_content_width=85, help_option_names=["-h", "--help"]),
-)
-def schema_cli():
-    try:
-        import scanpy  # noqa: F401
-    except ImportError:
-        raise click.ClickException(
-            "[cellxgene] cellxgene schema requires scanpy"
-        )
-
-
-@click.command(
-    name="apply",
-    short_help="(experimental) Apply the cellxgene data integration schema to an h5ad.",
-    help="(experimental) Using a yaml file that describes schema values to insert or convert and in input "
-    "h5ad file, apply the schema changes and create a new, conforming h5ad.",
-)
-@click.option(
-    "--source-h5ad",
-    help="Input h5ad file.",
-    nargs=1,
-    required=True,
-    type=click.Path(exists=True, dir_okay=False),
-)
-@click.option(
-    "--remix-config",
-    help="Config yaml with information on how to apply the schema.",
-    nargs=1,
-    required=True,
-    type=click.Path(exists=True, dir_okay=False),
-)
-@click.option(
-    "--output-filename",
-    help="Filename for the new, schema-conforming h5ad file.",
-    required=True,
-    nargs=1
-)
-def schema_apply(source_h5ad, remix_config, output_filename):
-    remix.apply_schema(source_h5ad, remix_config, output_filename)
-
-
-@click.command(
-    name="validate",
-    short_help="(experimental) Check that an h5ad follows the cellxgene data integration schema.",
-)
-@click.argument(
-    "h5ad",
-    nargs=1,
-    type=click.Path(exists=True, dir_okay=False),
-)
-@click.option(
-    "--shallow",
-    help="When true, just check that the correct version information is present.",
-    default=False,
-    show_default=True,
-    is_flag=True,
-)
-def schema_validate(h5ad, shallow):
-    validate.validate(h5ad, shallow)
-
-
-schema_cli.add_command(schema_apply)
-schema_cli.add_command(schema_validate)

backend/czi_hosted/cli/upgrade.py

@@ -1,85 +0,0 @@
-import re
-
-import click
-import requests
-from requests.exceptions import ConnectionError
-
-from .. import __version__
-
-# Official SemVer regex: https://semver.org/
-SEMVER_FORMAT = re.compile(
-    r"^(?P<major>0|[1-9]\d*)\.(?P<minor>0|[1-9]\d*)\.(?P<patch>0|[1-9]\d*)(?:-(?P<prerelease>(?:0|[1-9]\d*|\d*["
-    r"a-zA-Z-][0-9a-zA-Z-]*)(?:\.(?:0|[1-9]\d*|\d*[a-zA-Z-][0-9a-zA-Z-]*))*))?(?:\+(?P<buildmetadata>[0-9a-zA-Z-]+("
-    r"?:\.[0-9a-zA-Z-]+)*))?$"
-)
-
-
-def log_upgrade_check():
-    # Sanity-check that the CLI version is a properly-formatted SemVer string
-    assert validate_version_str(__version__, release_only=False)
-
-    # Get the current latest release
-    try:
-        release_tag_generator = (r["tag_name"] for r in _request_cellxgene_releases())
-        latest_release = next(release_tag_generator, lambda tag_name: validate_version_str(tag_name))
-        if version_gt(latest_release, __version__):
-            click.echo(f"There's a new version of cellxgene available ({latest_release})!", err=True)
-            click.echo("To upgrade, run the following: pip install --upgrade cellxgene\n", err=True)
-    except (ConnectionError, RateLimitException):
-        click.echo("Upgrade check failed.\n")
-
-
-class RateLimitException(Exception):
-    """
-    Github API Rate Limit Exception
-    """
-
-
-def _request_cellxgene_releases():
-    def raise_on_rate_limit(response):
-        if response.status_code == 403 and res.headers.get("X-RateLimit-Remaining") == "0":
-            raise RateLimitException
-
-    url = "https://api.github.com/repos/chanzuckerberg/cellxgene/releases"
-    res = requests.get(url)
-    raise_on_rate_limit(res)
-    for release in res.json():
-        yield release
-    while "next" in res.links.keys():
-        res = requests.get(res.links["next"]["url"])
-        raise_on_rate_limit(res)
-        for release in res.json():
-            yield release
-
-
-def validate_version_str(version_str, release_only=True):
-    """
-    Test if a string conforms to SemVer format (https://semver.org/)
-    :param version_str: a string to be validated
-    :param release_only: only declare releases (not prereleases) valid
-    :return: True if the version string is of a valid SemVer format else False
-    """
-    match = SEMVER_FORMAT.match(version_str)
-    has_match = match is not None
-    if has_match and release_only:
-        return not match.group("prerelease")
-    return has_match
-
-
-def split_version(version_string):
-    """
-    Split a SemVer-formatted string into its component integers
-    :param version_string: a SemVer string to be split
-    :return: an array of three integers
-    """
-    match = SEMVER_FORMAT.match(version_string)
-    return [int(match.group(group)) for group in ["major", "minor", "patch"]]
-
-
-def version_gt(left_version, right_version):
-    for left, right in zip(split_version(left_version), split_version(right_version)):
-        if left > right:
-            return True
-        elif right > left:
-            return False
-    return False

backend/czi_hosted/common/annotations/annotations.py

@@ -1,110 +0,0 @@
-import os
-
-from flask import current_app, has_request_context
-
-from backend.common.errors import DisabledFeatureError
-from backend.common.utils.type_conversion_utils import get_schema_type_hint_of_array
-from backend.common.genesets import write_gene_sets_tidycsv, read_gene_sets_tidycsv, validate_gene_sets
-from backend.common.utils.data_locator import DataLocator
-from backend.common.utils.utils import path_join
-
-
-class Annotations:
-    """baseclass for annotations and genesets"""
-
-    def __init__(self, config={}):
-        self.config = config
-
-    def user_annotations_enabled(self):
-        return self.config.get("user-annotations", False)
-
-    def check_user_annotations_enabled(self):
-        if not self.user_annotations_enabled():
-            raise DisabledFeatureError("User annotations are disabled.")
-
-    def get_schema(self, data_adaptor):
-        schema = []
-        labels = self.read_labels(data_adaptor)
-        if labels is not None and not labels.empty:
-            for col in labels.columns:
-                col_schema = dict(name=col, writable=True)
-                col_schema.update(get_schema_type_hint_of_array(labels[col]))
-                schema.append(col_schema)
-
-        return schema
-
-    def set_collection(self, name):
-        """set or create a new annotation collection"""
-        raise NotImplementedError
-
-    def read_labels(self, data_adaptor):
-        """Return the labels as a pandas.DataFrame"""
-        raise NotImplementedError
-
-    def write_labels(self, df, data_adaptor):
-        """Write the labels (df) to a persistent storage such that it can later be read"""
-        raise NotImplementedError
-
-    def update_parameters(self, parameters, data_adaptor):
-        """Update configuration parameters that describe information about the annotations feature"""
-        params = {}
-        params["annotations_genesets_readonly"] = True
-        params["annotations_genesets_name_is_read_only"] = True
-        parameters.update(params)
-
-    @staticmethod
-    def gene_sets_to_csv(genesets):
-        """
-        Convert the internal genesets format (returned by read_gene_set) into
-        the simple Tidy CSV.
-        """
-        from io import StringIO
-
-        if isinstance(genesets, dict):
-            genesets = genesets.values()
-
-        with StringIO() as sio:
-            write_gene_sets_tidycsv(sio, genesets)
-            return sio.getvalue()
-
-    @staticmethod
-    def gene_sets_to_response(genesets):
-        """
-        Convert the internal genesets format (returned by read_gene_set) into
-        the dict expected by the JSON REST API
-        """
-        return list(genesets.values())
-
-    def read_gene_sets(self, data_adaptor, context=None):
-        if has_request_context():
-            if not current_app.auth.is_user_authenticated():
-                return ({}, 0)
-
-        gene_sets_uri_or_path = dataset_uri_to_geneset_uri(data_adaptor.data_locator.uri_or_path)
-
-        server_config = data_adaptor.server_config
-        region_name = None if server_config is None else server_config.data_locator__s3__region_name
-        gene_sets_locator = DataLocator(gene_sets_uri_or_path, region_name=region_name)
-        if not gene_sets_locator.exists():
-            return ({}, 0)
-
-        gene_sets = read_gene_sets_tidycsv(gene_sets_locator, context)
-        schema = data_adaptor.get_schema()
-        var_index = schema["annotations"]["var"].get("index", "index")
-        var_names = set(data_adaptor.query_var_array(var_index))
-
-        gene_sets = validate_gene_sets(gene_sets, var_names)
-        return (gene_sets, 0)
-
-
-def dataset_uri_to_geneset_uri(data_uri_or_path):
-    """given a dataset URI, return the associated gene set URI"""
-    data_basename = os.path.basename(data_uri_or_path)
-    base, ext = os.path.splitext(data_basename)
-    if ext is not None:  # strip extension, if any
-        data_basename = base
-
-    genesets_basename = f"{data_basename}-genesets.csv"
-    gene_sets_uri_or_path = path_join(data_uri_or_path, "..", genesets_basename)
-
-    return gene_sets_uri_or_path

backend/czi_hosted/common/config/__init__.py

@@ -1,4 +0,0 @@
-from backend.common.utils.aws_secret_utils import get_secret_key  # noqa F504
-
-DEFAULT_SERVER_PORT = 5005
-BIG_FILE_SIZE_THRESHOLD = 100 * 2 ** 20  # 100MB

backend/czi_hosted/common/config/app_config.py

@@ -1,247 +0,0 @@
-import yaml
-from flatten_dict import unflatten
-
-from backend.czi_hosted.common.config.external_config import ExternalConfig
-from backend.czi_hosted.common.config.dataset_config import DatasetConfig
-from backend.czi_hosted.common.config.server_config import ServerConfig
-from backend.common.errors import ConfigurationError
-from backend.czi_hosted.default_config import get_default_config
-
-
-class AppConfig(object):
-    """
-    AppConfig stores all the configuration for cellxgene.
-    AppConfig contains one or more DatasetConfig(s) and one ServerConfig.
-    The server_config contains attributes that refer to the server process as a whole.
-    The default_dataset_config refers to attributes that are associated with the features and
-    presentations of a dataset.
-    The dataset config attributes can be overridden depending on the url by which the
-    dataset was accessed.  These are stored in dataroot_config.
-    AppConfig has methods to initialize, modify, and access the configuration.
-    """
-
-    def __init__(self):
-
-        # the default configuration (see default_config.py)
-        # TODO @madison -- if we always read from the default config (hard coded path) can we set those values as
-        #  defaults within the config class?
-        self.default_config = get_default_config()
-        # the server configuration
-        self.server_config = ServerConfig(self, self.default_config["server"])
-        # the dataset config, unless overridden by an entry in dataroot_config
-        self.default_dataset_config = DatasetConfig(None, self, self.default_config["dataset"])
-        # a dictionary of keys to DatasetConfig objects.  Each key must exist in the multi_dataset__dataroot
-        # attribute of the server_config. The default dataset config will apply to all datasets unless a different set
-        # of config vars was passed for a specific dataset under the multidataset config. For example:
-        """
-        per_dataset_config:
-            d1:
-               user_annotations:
-                   enable:  false
-            d2:
-               user_annotations:
-                   enable:  true
-         """
-        #   dataroot config
-        self.dataroot_config = {}
-
-        #  external config
-        self.external_config = ExternalConfig(self, self.default_config["external"])
-
-        # Set to true when config_completed is called
-        self.is_completed = False
-
-    def get_dataset_config(self, dataroot_key):
-        if self.server_config.single_dataset__datapath:
-            return self.default_dataset_config
-        else:
-            return self.dataroot_config.get(dataroot_key, self.default_dataset_config)
-
-    def check_config(self):
-        """Verify all the attributes in the config have been type checked"""
-        if not self.is_completed:
-            raise ConfigurationError("The configuration has not been completed")
-        self.server_config.check_config()
-        self.default_dataset_config.check_config()
-        for dataset_config in self.dataroot_config.values():
-            dataset_config.check_config()
-        self.external_config.check_config()
-
-    def update_server_config(self, **kw):
-        self.server_config.update(**kw)
-        self.is_completed = False
-
-    def update_default_dataset_config(self, **kw):
-        self.default_dataset_config.update(**kw)
-        # update all the other dataset configs, if any
-        for value in self.dataroot_config.values():
-            value.update(**kw)
-        self.is_completed = False
-
-    def update_single_config_from_path_and_value(self, path, value):
-        """Update a single config parameter with the value.
-        Path is a list of string, that gives a path to the config parameter to be updated.
-        For example, path may be ["server","app","port"].
-        """
-        self.is_completed = False
-        if not isinstance(path, list):
-            raise ConfigurationError(f"path must be a list of strings, got '{str(path)}'")
-        for part in path:
-            if not isinstance(part, str):
-                raise ConfigurationError(f"path must be a list of strings, got '{str(path)}'")
-
-        if len(path) < 1 or path[0] not in ("server", "dataset", "per_dataset_config"):
-            raise ConfigurationError("path must start with 'server', 'dataset', or 'per_dataset_config'")
-
-        if path[0] == "server":
-            attr = "__".join(path[1:])
-            try:
-                self.update_server_config(**{attr: value})
-            except ConfigurationError:
-                raise ConfigurationError(f"unknown config parameter at path: '{str(path)}'")
-        elif path[0] == "dataset":
-            attr = "__".join(path[1:])
-            try:
-                self.update_default_dataset_config(**{attr: value})
-            except ConfigurationError:
-                raise ConfigurationError(f"unknown config parameter at path: '{str(path)}'")
-
-        elif path[0] == "per_dataset_config":
-            if len(path) < 2:
-                raise ConfigurationError(f"missing dataroot when using per_dataset_config: got '{path}'")
-            dataroot = path[1]
-            if dataroot not in self.dataroot_config:
-                dataroots = str(list(self.dataroot_config.keys()))
-                raise ConfigurationError(
-                    f"unknown dataroot when using per_dataset_config: got '{path}',"
-                    f" dataroots specified in config are {dataroots}"
-                )
-
-            attr = "__".join(path[2:])
-            try:
-                self.dataroot_config[dataroot].update(**{attr: value})
-            except ConfigurationError:
-                raise ConfigurationError(f"unknown config parameter at path: '{str(path)}'")
-
-    def update_from_config_file(self, config_file):
-        try:
-            with open(config_file) as yml_file:
-                config = yaml.safe_load(yml_file)
-        except yaml.YAMLError as e:
-            raise ConfigurationError(f"The specified config file contained an error: {e}")
-        except OSError as e:
-            raise ConfigurationError(f"Issue retrieving the specified config file: {e}")
-
-        if config.get("server"):
-            self.server_config.update_from_config(config["server"], "server")
-        if config.get("dataset"):
-            self.default_dataset_config.update_from_config(config["dataset"], "dataset")
-
-        per_dataset_config = config.get("per_dataset_config", {})
-        for key, dataroot_config in per_dataset_config.items():
-            # first create and initialize the dataroot with the default config
-            self.add_dataroot_config(key, **config["dataset"])
-            # then apply the per dataset configuration
-            self.dataroot_config[key].update_from_config(dataroot_config, f"per_dataset_config__{key}")
-
-        if config.get("external"):
-            self.external_config.update_from_config(config["external"], "external")
-
-        self.is_completed = False
-
-    def config_to_dict(self):
-        """return the configuration as an unflattened dict"""
-        server = self.server_config.create_mapping(self.server_config.default_config)
-        dataset = self.default_dataset_config.create_mapping(self.default_dataset_config.default_config)
-        external = self.external_config.create_mapping(self.external_config.default_config)
-        config = dict(server={}, dataset={})
-        for attrname in server.keys():
-            config["server__" + attrname] = getattr(self.server_config, attrname)
-        for attrname in dataset.keys():
-            config["dataset__" + attrname] = getattr(self.default_dataset_config, attrname)
-        if self.dataroot_config:
-            config["per_dataset_config"] = {}
-        for dataroot_tag, dataroot_config in self.dataroot_config.items():
-            dataset = dataroot_config.create_mapping(dataroot_config.default_config)
-            for attrname in dataset.keys():
-                config[f"per_dataset_config__{dataroot_tag}__" + attrname] = getattr(dataroot_config, attrname)
-        for attrname in external.keys():
-            config["external__" + attrname] = getattr(self.external_config, attrname)
-
-        config = unflatten(config, splitter=lambda key: key.split("__"))
-        return config
-
-    def write_config(self, config_file):
-        """output the config to a yaml file"""
-        config = self.config_to_dict()
-        yaml.dump(config, open(config_file, "w"))
-
-    def changes_from_default(self):
-        """Return all the attribute that are different from the default"""
-        diff_server = self.server_config.changes_from_default()
-        diff_dataset = self.default_dataset_config.changes_from_default()
-        diff_external = self.external.changes_from_default()
-        diff = dict(server=diff_server, dataset=diff_dataset, external=diff_external)
-        return diff
-
-    def add_dataroot_config(self, dataroot_tag, **kw):
-        """Create a new dataset config object based on the default dataset config, and kw parameters"""
-        if dataroot_tag in self.dataroot_config:
-            raise ConfigurationError(f"dataroot config already exists: {dataroot_tag}")
-        if type(self.server_config.multi_dataset__dataroot) != dict:
-            raise ConfigurationError("The server__multi_dataset__dataroot must be a dictionary")
-        if dataroot_tag not in self.server_config.multi_dataset__dataroot:
-            raise ConfigurationError(f"The dataroot_tag ({dataroot_tag}) not found in server__multi_dataset__dataroot")
-
-        self.is_completed = False
-        self.dataroot_config[dataroot_tag] = DatasetConfig(dataroot_tag, self, self.default_config["dataset"])
-        flat_config = self.default_dataset_config.create_mapping(self.default_dataset_config.default_config)
-        config = {key: value[1] for key, value in flat_config.items()}
-        self.dataroot_config[dataroot_tag].update(**config)
-        self.dataroot_config[dataroot_tag].update_from_config(kw, dataroot_tag)
-
-    def complete_config(self, messagefn=None):
-        """The configure options are checked, and any additional setup based on the config
-        parameters is done"""
-
-        if messagefn is None:
-
-            def noop(message):
-                pass
-
-            messagefn = noop
-
-        # TODO: to give better error messages we can add a mapping between where each config
-        # attribute originated (e.g. command line argument or config file), then in the error
-        # messages we can give correct context for attributes with bad value.
-        context = dict(messagefn=messagefn)
-
-        # complete config for external_config first, since this may update values in the other sections
-        self.external_config.complete_config(context)
-        self.server_config.complete_config(context)
-        self.default_dataset_config.complete_config(context)
-        for dataroot_config in self.dataroot_config.values():
-            dataroot_config.complete_config(context)
-
-        self.is_completed = True
-        self.check_config()
-
-    def get_matrix_data_cache_manager(self):
-        return self.server_config.matrix_data_cache_manager
-
-    def is_multi_dataset(self):
-        return self.server_config.multi_dataset__dataroot is not None
-
-    def get_title(self, data_adaptor):
-        return (
-            self.server_config.single_dataset__title
-            if self.server_config.single_dataset__title
-            else data_adaptor.get_title()
-        )
-
-    def get_about(self, data_adaptor):
-        return (
-            self.server_config.single_dataset__about
-            if self.server_config.single_dataset__about
-            else data_adaptor.get_about()
-        )

backend/czi_hosted/common/config/base_config.py

@@ -1,132 +0,0 @@
-import copy
-
-from flatten_dict import flatten
-from backend.common.errors import ConfigurationError
-
-
-class BaseConfig(object):
-    """
-    This class handles the mechanics of updating and checking attributes.
-    Derived classes are expected to store the actual attributes
-    Currently DatasetConfig and ServerConfig both inherit from BaseConfig.
-    """
-
-    def __init__(self, app_config, default_config, dictval_cases={}):
-        # reference back to the app_config
-        self.app_config = app_config
-        # the complete set of attributes and their default values (unflattened)
-        self.default_config = default_config
-        # attributes where the value may be a dict (and therefore are not flattened)
-        self.dictval_cases = dictval_cases
-        # used to make sure every attribute value is checked
-        self.attr_checked = {key_name: False for key_name in self.create_mapping(default_config).keys()}
-
-    def create_mapping(self, config):
-        """
-        Create a dictionary where the keys are the name of attributes (using double underscore convention)
-        For example: authentication__type
-
-        The values are a tuple,
-        - the first item of the tuple is a tuple of path elements (location in config 'tree')
-        - the second item is the value of the config parameter
-
-        For example: (('authentication', 'type'), 'session'))
-        """
-        config_copy = copy.deepcopy(config)
-        mapping = {}
-
-        # special cases where the value could be a dict.
-        # If its value is not None, the entry is added to the mapping, and not included
-        # in the flattening below.
-        for dictval_case in self.dictval_cases:
-            cur = config_copy
-            for part in dictval_case[:-1]:
-                cur = cur.get(part, {})
-            val = cur.get(dictval_case[-1])
-            if val is not None:
-                key = "__".join(dictval_case)
-                mapping[key] = (dictval_case, val)
-                del cur[dictval_case[-1]]
-
-        flat_config = flatten(config_copy)
-        for key, value in flat_config.items():
-            # name of the attribute
-            attr = "__".join(key)
-            mapping[attr] = (key, value)
-
-        return mapping
-
-    def validate_correct_type_of_configuration_attribute(self, attrname, vtype):
-        val = getattr(self, attrname)
-        if type(vtype) in (list, tuple):
-            if type(val) not in vtype:
-                tnames = ",".join([x.__name__ for x in vtype])
-                raise ConfigurationError(
-                    f"Invalid type for attribute: {attrname}, expected types ({tnames}), got {type(val).__name__}"
-                )
-        else:
-            if type(val) != vtype:
-                raise ConfigurationError(
-                    f"Invalid type for attribute: {attrname}, "
-                    f"expected type {vtype.__name__}, got {type(val).__name__}"
-                )
-
-        self.attr_checked[attrname] = True
-
-    def check_config(self):
-        mapping = self.create_mapping(self.default_config)
-        for key in mapping.keys():
-            if not self.attr_checked[key]:
-                raise ConfigurationError(f"The attr '{key}' has not been checked")
-
-    def update(self, **kw):
-        """Update the attributes defined in kw with their new values."""
-        for key, value in kw.items():
-            if not hasattr(self, key):
-
-                # check if the key is setting into a dictval entry.
-                found_dictval = False
-                for dictval in self.dictval_cases:
-                    dictvalname = "__".join(dictval)
-                    if dictvalname + "__" in key:
-                        dictkey = key[len(dictvalname) + 2 :]
-                        curdictval = getattr(self, dictvalname)
-                        if curdictval is None:
-                            setattr(self, dictvalname, dict(dictkey=value))
-                        else:
-                            curdictval[dictkey] = value
-
-                        found_dictval = True
-                        break
-
-                if found_dictval:
-                    continue
-                raise ConfigurationError(f"unknown config parameter {key}.")
-            try:
-                if type(value) == tuple:
-                    # convert tuple values to list values
-                    value = list(value)
-                setattr(self, key, value)
-            except KeyError:
-                raise ConfigurationError(f"Unable to set config parameter {key}.")
-
-            self.attr_checked[key] = False
-
-    def update_from_config(self, config, prefix):
-        mapping = self.create_mapping(config)
-        for attr, (key, value) in mapping.items():
-            if not hasattr(self, attr):
-                raise ConfigurationError(f"Unknown key from config file: {prefix}__{attr}")
-            setattr(self, attr, value)
-
-            self.attr_checked[attr] = False
-
-    def changes_from_default(self):
-        """Return all the attribute that are different from the default"""
-        mapping = self.create_mapping(self.default_config)
-        diff = []
-        for attrname, (key, defval) in mapping.items():
-            curval = getattr(self, attrname)
-            if curval != defval:
-                diff.append((attrname, curval, defval))
-        return diff

backend/czi_hosted/common/config/client_config.py

@@ -1,121 +0,0 @@
-from backend.czi_hosted import display_version as cellxgene_display_version
-
-
-def get_client_config(app_config, data_adaptor):
-    """
-    Return the configuration as required by the /config REST route
-    """
-
-    server_config = app_config.server_config
-    dataset_config = data_adaptor.dataset_config
-    annotation = dataset_config.user_annotations
-    auth = server_config.auth
-
-    # FIXME The current set of config is not consistently presented:
-    # we have camalCase, hyphen-text, and underscore_text
-
-    # make sure the configuration has been checked.
-    app_config.check_config()
-
-    # display_names
-    title = app_config.get_title(data_adaptor)
-    about = app_config.get_about(data_adaptor)
-
-    display_names = dict(engine=data_adaptor.get_name(), dataset=title)
-
-    # library_versions
-    library_versions = {}
-    library_versions.update(data_adaptor.get_library_versions())
-    library_versions["cellxgene"] = cellxgene_display_version
-
-    # links
-    links = {"about-dataset": about}
-
-    # parameters
-    parameters = {
-        "layout": dataset_config.embeddings__names,
-        "max-category-items": dataset_config.presentation__max_categories,
-        "obs_names": server_config.single_dataset__obs_names,
-        "var_names": server_config.single_dataset__var_names,
-        "diffexp_lfc_cutoff": dataset_config.diffexp__lfc_cutoff,
-        "backed": server_config.adaptor__anndata_adaptor__backed,
-        "disable-diffexp": not dataset_config.diffexp__enable,
-        "annotations": False,
-        "annotations_file": None,
-        "annotations_dir": None,
-        "annotations_genesets": True,  # feature flag
-        "annotations_genesets_readonly": True,
-        "annotations_genesets_summary_methods": ["mean"],
-        "custom_colors": dataset_config.presentation__custom_colors,
-        "diffexp-may-be-slow": False,
-        "about_legal_tos": dataset_config.app__about_legal_tos,
-        "about_legal_privacy": dataset_config.app__about_legal_privacy,
-    }
-
-    # corpora dataset_props
-    # TODO/Note: putting info from the dataset into the /config is not ideal.
-    # However, it is definitely not part of /schema, and we do not have a top-level
-    # route for data properties.  Consider creating one at some point.
-    corpora_props = data_adaptor.get_corpora_props()
-    if corpora_props and "default_embedding" in corpora_props:
-        default_embedding = corpora_props["default_embedding"]
-        if isinstance(default_embedding, str) and default_embedding.startswith("X_"):
-            default_embedding = default_embedding[2:]  # drop X_ prefix
-        if default_embedding in data_adaptor.get_embedding_names():
-            parameters["default_embedding"] = default_embedding
-
-    data_adaptor.update_parameters(parameters)
-    if annotation:
-        annotation.update_parameters(parameters, data_adaptor)
-
-    # gather it all together
-    client_config = {}
-    config = client_config["config"] = {}
-    config["displayNames"] = display_names
-    config["library_versions"] = library_versions
-    config["links"] = links
-    config["parameters"] = parameters
-    config["corpora_props"] = corpora_props
-    config["limits"] = {
-        "column_request_max": server_config.limits__column_request_max,
-        "diffexp_cellcount_max": server_config.limits__diffexp_cellcount_max,
-    }
-
-    if dataset_config.app__authentication_enable and auth.is_valid_authentication_type():
-        config["authentication"] = {
-            "requires_client_login": auth.requires_client_login(),
-        }
-        if auth.requires_client_login():
-            config["authentication"].update(
-                {
-                    # Todo why are these stored on the data_adaptor?
-                    "login": auth.get_login_url(data_adaptor),
-                    "logout": auth.get_logout_url(data_adaptor),
-                }
-            )
-
-    return client_config
-
-
-def get_client_userinfo(app_config, data_adaptor):
-    """
-    Return the userinfo as required by the /userinfo REST route
-    """
-
-    server_config = app_config.server_config
-    dataset_config = data_adaptor.dataset_config
-    auth = server_config.auth
-
-    # make sure the configuration has been checked.
-    app_config.check_config()
-
-    if dataset_config.app__authentication_enable and auth.is_valid_authentication_type():
-        userinfo = {}
-        userinfo["userinfo"] = {
-            "is_authenticated": auth.is_user_authenticated(),
-            "username": auth.get_user_name(),
-            "user_id": auth.get_user_id(),
-            "email": auth.get_user_email(),
-            "picture": auth.get_user_picture(),
-        }
-        return userinfo

backend/czi_hosted/common/config/dataset_config.py

@@ -1,211 +0,0 @@
-import os
-from os.path import splitext, isdir
-
-from backend.czi_hosted.common.annotations.annotations import Annotations
-from backend.czi_hosted.common.annotations.hosted_tiledb import AnnotationsHostedTileDB
-from backend.czi_hosted.common.annotations.local_file_csv import AnnotationsLocalFile
-from backend.czi_hosted.common.config.base_config import BaseConfig
-from backend.common.errors import ConfigurationError
-from backend.czi_hosted.db.db_utils import DbUtils
-
-
-class DatasetConfig(BaseConfig):
-    """Manages the config attribute associated with a dataset."""
-
-    def __init__(self, tag, app_config, default_config):
-        super().__init__(app_config, default_config)
-        self.tag = tag
-        try:
-            self.app__scripts = default_config["app"]["scripts"]
-            self.app__inline_scripts = default_config["app"]["inline_scripts"]
-            self.app__about_legal_tos = default_config["app"]["about_legal_tos"]
-            self.app__about_legal_privacy = default_config["app"]["about_legal_privacy"]
-            self.app__authentication_enable = default_config["app"]["authentication_enable"]
-
-            self.presentation__max_categories = default_config["presentation"]["max_categories"]
-            self.presentation__custom_colors = default_config["presentation"]["custom_colors"]
-
-            self.user_annotations__enable = default_config["user_annotations"]["enable"]
-            self.user_annotations__type = default_config["user_annotations"]["type"]
-            self.user_annotations__local_file_csv__directory = default_config["user_annotations"]["local_file_csv"][
-                "directory"
-            ]
-            self.user_annotations__local_file_csv__file = default_config["user_annotations"]["local_file_csv"]["file"]
-            self.user_annotations__hosted_tiledb_array__db_uri = default_config["user_annotations"][
-                "hosted_tiledb_array"
-            ]["db_uri"]
-            self.user_annotations__hosted_tiledb_array__hosted_file_directory = default_config["user_annotations"][
-                "hosted_tiledb_array"
-            ]["hosted_file_directory"]
-
-            self.embeddings__names = default_config["embeddings"]["names"]
-
-            self.diffexp__enable = default_config["diffexp"]["enable"]
-            self.diffexp__lfc_cutoff = default_config["diffexp"]["lfc_cutoff"]
-            self.diffexp__top_n = default_config["diffexp"]["top_n"]
-
-            self.X_approximate_distribution = default_config["X_approximate_distribution"]
-
-        except KeyError as e:
-            raise ConfigurationError(f"Unexpected config: {str(e)}")
-
-        # Create the default annotation, which supports gene set reading without
-        # further configuration. Depending on configuration options, `complete_config`
-        # may create a more specialized annotation object and replace this default.
-        self.user_annotations = Annotations()
-
-    def complete_config(self, context):
-        self.handle_app()
-        self.handle_presentation()
-        self.handle_user_annotations(context)
-        self.handle_embeddings()
-        self.handle_diffexp(context)
-        self.handle_X_approximate_distribution()
-
-    def handle_app(self):
-        self.validate_correct_type_of_configuration_attribute("app__scripts", list)
-        self.validate_correct_type_of_configuration_attribute("app__inline_scripts", list)
-        self.validate_correct_type_of_configuration_attribute("app__about_legal_tos", (type(None), str))
-        self.validate_correct_type_of_configuration_attribute("app__about_legal_privacy", (type(None), str))
-        self.validate_correct_type_of_configuration_attribute("app__authentication_enable", bool)
-
-        # scripts can be string (filename) or dict (attributes). Convert string to dict.
-        scripts = []
-        for script in self.app__scripts:
-            try:
-                if isinstance(script, str):
-                    scripts.append({"src": script})
-                elif isinstance(script, dict) and isinstance(script["src"], str):
-                    scripts.append(script)
-                else:
-                    raise Exception
-            except Exception as e:
-                raise ConfigurationError(f"Scripts must be string or a dict containing an src key: {e}")
-
-        self.app__scripts = scripts
-
-    def handle_presentation(self):
-        self.validate_correct_type_of_configuration_attribute("presentation__max_categories", int)
-        self.validate_correct_type_of_configuration_attribute("presentation__custom_colors", bool)
-
-    def handle_user_annotations(self, context):
-        self.validate_correct_type_of_configuration_attribute("user_annotations__enable", bool)
-        self.validate_correct_type_of_configuration_attribute("user_annotations__type", str)
-        self.validate_correct_type_of_configuration_attribute(
-            "user_annotations__local_file_csv__directory", (type(None), str)
-        )
-        self.validate_correct_type_of_configuration_attribute(
-            "user_annotations__local_file_csv__file", (type(None), str)
-        )
-        self.validate_correct_type_of_configuration_attribute(
-            "user_annotations__hosted_tiledb_array__db_uri", (type(None), str)
-        )
-        self.validate_correct_type_of_configuration_attribute(
-            "user_annotations__hosted_tiledb_array__hosted_file_directory", (type(None), str)
-        )
-        if self.user_annotations__enable:
-            server_config = self.app_config.server_config
-            if not self.app__authentication_enable:
-                raise ConfigurationError("user annotations requires authentication to be enabled")
-            if not server_config.auth.is_valid_authentication_type():
-                auth_type = server_config.authentication__type
-                raise ConfigurationError(f"authentication method {auth_type} is not compatible with user annotations")
-
-            if self.user_annotations__type == "local_file_csv":
-                self.handle_local_file_csv_annotations()
-            elif self.user_annotations__type == "hosted_tiledb_array":
-                self.handle_hosted_tiledb_annotations()
-            else:
-                raise ConfigurationError('The only annotation type support is "local_file_csv" or "hosted_tiledb_array')
-        else:
-            self.check_annotation_config_vars_not_set(context)
-
-    def handle_local_file_csv_annotations(self):
-        dirname = self.user_annotations__local_file_csv__directory
-        filename = self.user_annotations__local_file_csv__file
-        if filename is not None and dirname is not None:
-            raise ConfigurationError("'annotations-file' and 'annotations-dir' may not be used together.")
-
-        if filename is not None:
-            lf_name, lf_ext = splitext(filename)
-            if lf_ext and lf_ext != ".csv":
-                raise ConfigurationError(f"annotation file type must be .csv: {filename}")
-
-        if dirname is not None and not isdir(dirname):
-            try:
-                os.mkdir(dirname)
-            except OSError:
-                raise ConfigurationError("Unable to create directory specified by --annotations-dir")
-
-        anno_config = {
-            "user-annotations": self.user_annotations__enable,
-            "genesets-save": False,
-        }
-        self.user_annotations = AnnotationsLocalFile(anno_config, dirname, filename)
-
-        # if the user has specified a fixed label file, go ahead and validate it
-        # so that we can remove errors early in the process.
-        server_config = self.app_config.server_config
-        if server_config.single_dataset__datapath and self.user_annotations__local_file_csv__file:
-            with server_config.matrix_data_cache_manager.data_adaptor(
-                self.tag, server_config.single_dataset__datapath, self.app_config
-            ) as data_adaptor:
-                data_adaptor.check_new_labels(self.user_annotations.read_labels(data_adaptor))
-
-    def handle_hosted_tiledb_annotations(self):
-        self.validate_correct_type_of_configuration_attribute("user_annotations__hosted_tiledb_array__db_uri", str)
-        self.validate_correct_type_of_configuration_attribute(
-            "user_annotations__hosted_tiledb_array__hosted_file_directory", str
-        )
-        anno_config = {
-            "user-annotations": self.user_annotations__enable,
-            "genesets-save": False,
-        }
-        self.user_annotations = AnnotationsHostedTileDB(
-            anno_config,
-            directory_path=self.user_annotations__hosted_tiledb_array__hosted_file_directory,
-            db=DbUtils(self.user_annotations__hosted_tiledb_array__db_uri),
-        )
-
-    def check_annotation_config_vars_not_set(self, context):
-        if self.user_annotations__type is not None:
-            dirname = self.user_annotations__local_file_csv__directory
-            filename = self.user_annotations__local_file_csv__file
-            db_uri = self.user_annotations__hosted_tiledb_array__db_uri
-            hosted_file_dirname = self.user_annotations__hosted_tiledb_array__hosted_file_directory
-            if filename is not None:
-                context["messagefn"]("Warning: --annotations-file ignored as annotations are disabled.")
-            if dirname is not None:
-                context["messagefn"]("Warning: --annotations-dir ignored as annotations are disabled.")
-            if db_uri is not None:
-                context["messagefn"]("Warning: db_uri ignored as annotations are disabled.")
-            if hosted_file_dirname is not None:
-                context["messagefn"](
-                    "Warning: hosted_file_directory for hosted_tiledb_array ignored as annotations are disabled."
-                )
-
-    def handle_embeddings(self):
-        self.validate_correct_type_of_configuration_attribute("embeddings__names", list)
-
-    def handle_diffexp(self, context):
-        self.validate_correct_type_of_configuration_attribute("diffexp__enable", bool)
-        self.validate_correct_type_of_configuration_attribute("diffexp__lfc_cutoff", float)
-        self.validate_correct_type_of_configuration_attribute("diffexp__top_n", int)
-
-        server_config = self.app_config.server_config
-        if server_config.single_dataset__datapath:
-            with server_config.matrix_data_cache_manager.data_adaptor(
-                self.tag, server_config.single_dataset__datapath, self.app_config
-            ) as data_adaptor:
-                if self.diffexp__enable and data_adaptor.parameters.get("diffexp_may_be_slow", False):
-                    context["messagefn"](
-                        "CAUTION: due to the size of your dataset, "
-                        "running differential expression may take longer or fail."
-                    )
-
-    def handle_X_approximate_distribution(self):
-        self.validate_correct_type_of_configuration_attribute("X_approximate_distribution", str)
-        if self.X_approximate_distribution not in ["normal", "count"]:
-            raise ConfigurationError(
-                "X_approximate_distribution has unknown value -- must be 'normal' or 'count'."
-            )

backend/czi_hosted/common/config/external_config.py

@@ -1,95 +0,0 @@
-import os
-
-from backend.czi_hosted.common.config.base_config import BaseConfig
-from backend.common.errors import ConfigurationError, SecretKeyRetrievalError
-from backend.common.utils.aws_secret_utils import get_secret_key
-from backend.common.utils.type_conversion_utils import convert_string_to_value
-
-
-class ExternalConfig(BaseConfig):
-    """Manages the config attribute associated with external configuration sources, such as
-    environment variables or the AWS Secrets Manager."""
-
-    def __init__(self, app_config, default_config):
-        super().__init__(app_config, default_config)
-        try:
-            self.environment = default_config["environment"]
-            self.aws_secrets_manager__region = default_config["aws_secrets_manager"]["region"]
-            self.aws_secrets_manager__secrets = default_config["aws_secrets_manager"]["secrets"]
-
-        except KeyError as e:
-            raise ConfigurationError(f"Unexpected config: {str(e)}")
-
-    def complete_config(self, context):
-        self.handle_environment(context)
-        self.handle_aws_secrets_manager(context)
-
-    def handle_environment(self, context):
-        """For each environment variable defined, get the value (if it is set),
-        and set the specified config parameter"""
-        self.validate_correct_type_of_configuration_attribute("environment", list)
-        for envdict in self.environment:
-            name = envdict.get("name")
-            if name is None:
-                raise ConfigurationError("environment: 'name' is missing")
-            required = envdict.get("required", False)
-            if type(required) != bool:
-                raise ConfigurationError("environment: 'required' must be a bool")
-            path = envdict.get("path")
-            if path is None:
-                raise ConfigurationError("environment: 'path' is missing")
-
-            value = os.environ.get(name)
-            if value is None:
-                if required:
-                    raise ConfigurationError(f"required environment variable '{name}' not set")
-            else:
-                value = convert_string_to_value(value)
-                self.app_config.update_single_config_from_path_and_value(path, value)
-
-    def handle_aws_secrets_manager(self, context):
-        """For each aws secret defined, get the key/values, and set the specified config parameter"""
-        self.validate_correct_type_of_configuration_attribute("aws_secrets_manager__region", (type(None), str))
-        self.validate_correct_type_of_configuration_attribute("aws_secrets_manager__secrets", list)
-
-        if not self.aws_secrets_manager__secrets:
-            return
-
-        self.validate_correct_type_of_configuration_attribute("aws_secrets_manager__region", str)
-
-        for secret in self.aws_secrets_manager__secrets:
-            secret_name = secret.get("name")
-            if secret_name is None:
-                raise ConfigurationError("aws_secrets_manager: 'name' is missing")
-            if not isinstance(secret_name, str):
-                raise ConfigurationError("aws_secrets_manager: 'name' must be a string")
-
-            try:
-                secret_dict = get_secret_key(self.aws_secrets_manager__region, secret_name)
-            except SecretKeyRetrievalError as e:
-                raise ConfigurationError(f"Unable to retrieve secret {secret_name}: {str(e)}")
-
-            values = secret.get("values")
-            if values is None:
-                raise ConfigurationError("aws_secrets_manager: 'values' is missing")
-            if not isinstance(values, list):
-                raise ConfigurationError("aws_secrets_manager: 'values' must be a list")
-
-            for value in values:
-                key = value.get("key")
-                if key is None:
-                    raise ConfigurationError(f"missing 'key' in secret values: {secret_name}")
-                path = value.get("path")
-                if path is None:
-                    raise ConfigurationError(f"missing 'path' in secret values: {secret_name}")
-                required = value.get("required", False)
-                if type(required) != bool:
-                    raise ConfigurationError(f"wrong type for 'required' in secret values: {secret_name}")
-
-                secret_value = secret_dict.get(key)
-                if secret_value is None:
-                    if required:
-                        raise ConfigurationError(f"required secret '{secret_name}:{key}' not set")
-                else:
-                    secret_value = convert_string_to_value(secret_value)
-                    self.app_config.update_single_config_from_path_and_value(path, secret_value)

backend/czi_hosted/common/config/server_config.py

@@ -1,387 +0,0 @@
-import os
-import sys
-import warnings
-from os.path import basename
-from urllib.parse import urlparse, quote_plus
-
-from backend.czi_hosted.auth.auth import AuthTypeFactory
-from backend.czi_hosted.common.config import DEFAULT_SERVER_PORT, BIG_FILE_SIZE_THRESHOLD
-from backend.czi_hosted.common.config.base_config import BaseConfig
-from backend.common.utils.data_locator import discover_s3_region_name
-from backend.common.errors import ConfigurationError, DatasetAccessError
-from backend.common.utils.utils import is_port_available, find_available_port, custom_format_warning
-from backend.czi_hosted.compute import diffexp_cxg as diffexp_tiledb
-from backend.czi_hosted.data_common.matrix_loader import MatrixDataCacheManager, MatrixDataLoader, MatrixDataType
-
-
-class ServerConfig(BaseConfig):
-    """Manages the config attribute associated with the server."""
-
-    def __init__(self, app_config, default_config):
-        dictval_cases = [
-            ("app", "csp_directives"),
-            ("authentication", "params_oauth", "cookie"),
-            ("authentication", "params_oauth", "jwt_decode_options"),
-            ("adaptor", "cxg_adaptor", "tiledb_ctx"),
-            ("multi_dataset", "dataroot"),
-        ]
-        super().__init__(app_config, default_config, dictval_cases)
-
-        try:
-            self.app__verbose = default_config["app"]["verbose"]
-            self.app__debug = default_config["app"]["debug"]
-            self.app__host = default_config["app"]["host"]
-            self.app__port = default_config["app"]["port"]
-            self.app__open_browser = default_config["app"]["open_browser"]
-            self.app__force_https = default_config["app"]["force_https"]
-            self.app__flask_secret_key = default_config["app"]["flask_secret_key"]
-            self.app__generate_cache_control_headers = default_config["app"]["generate_cache_control_headers"]
-            self.app__server_timing_headers = default_config["app"]["server_timing_headers"]
-            self.app__csp_directives = default_config["app"]["csp_directives"]
-            self.app__api_base_url = default_config["app"]["api_base_url"]
-            self.app__web_base_url = default_config["app"]["web_base_url"]
-
-            self.authentication__type = default_config["authentication"]["type"]
-            self.authentication__insecure_test_environment = default_config["authentication"][
-                "insecure_test_environment"
-            ]
-            self.authentication__params_oauth__oauth_api_base_url = default_config["authentication"]["params_oauth"][
-                "oauth_api_base_url"
-            ]
-            self.authentication__params_oauth__client_id = default_config["authentication"]["params_oauth"]["client_id"]
-            self.authentication__params_oauth__client_secret = default_config["authentication"]["params_oauth"][
-                "client_secret"
-            ]
-            self.authentication__params_oauth__jwt_decode_options = default_config["authentication"]["params_oauth"][
-                "jwt_decode_options"
-            ]
-            self.authentication__params_oauth__session_cookie = default_config["authentication"]["params_oauth"][
-                "session_cookie"
-            ]
-            self.authentication__params_oauth__cookie = default_config["authentication"]["params_oauth"]["cookie"]
-
-            self.multi_dataset__dataroot = default_config["multi_dataset"]["dataroot"]
-            self.multi_dataset__index = default_config["multi_dataset"]["index"]
-            self.multi_dataset__allowed_matrix_types = default_config["multi_dataset"]["allowed_matrix_types"]
-            self.multi_dataset__matrix_cache__max_datasets = default_config["multi_dataset"]["matrix_cache"][
-                "max_datasets"
-            ]
-            self.multi_dataset__matrix_cache__timelimit_s = default_config["multi_dataset"]["matrix_cache"][
-                "timelimit_s"
-            ]
-
-            self.single_dataset__datapath = default_config["single_dataset"]["datapath"]
-            self.single_dataset__obs_names = default_config["single_dataset"]["obs_names"]
-            self.single_dataset__var_names = default_config["single_dataset"]["var_names"]
-            self.single_dataset__about = default_config["single_dataset"]["about"]
-            self.single_dataset__title = default_config["single_dataset"]["title"]
-
-            self.diffexp__alg_cxg__max_workers = default_config["diffexp"]["alg_cxg"]["max_workers"]
-            self.diffexp__alg_cxg__cpu_multiplier = default_config["diffexp"]["alg_cxg"]["cpu_multiplier"]
-            self.diffexp__alg_cxg__target_workunit = default_config["diffexp"]["alg_cxg"]["target_workunit"]
-
-            self.data_locator__s3__region_name = default_config["data_locator"]["s3"]["region_name"]
-
-            self.adaptor__cxg_adaptor__tiledb_ctx = default_config["adaptor"]["cxg_adaptor"]["tiledb_ctx"]
-            self.adaptor__anndata_adaptor__backed = default_config["adaptor"]["anndata_adaptor"]["backed"]
-
-            self.limits__diffexp_cellcount_max = default_config["limits"]["diffexp_cellcount_max"]
-            self.limits__column_request_max = default_config["limits"]["column_request_max"]
-
-        except KeyError as e:
-            raise ConfigurationError(f"Unexpected config: {str(e)}")
-
-        # The matrix data cache manager is created during the complete_config and stored here.
-        self.matrix_data_cache_manager = None
-
-        # The authentication object
-        self.auth = None
-
-    def complete_config(self, context):
-        self.handle_app(context)
-        self.handle_data_source()
-        self.handle_authentication()
-        self.handle_data_locator()
-        self.handle_adaptor()  # may depend on data_locator
-        self.handle_single_dataset(context)  # may depend on adaptor
-        self.handle_multi_dataset()  # may depend on adaptor
-        self.handle_diffexp()
-        self.handle_limits()
-
-        self.check_config()
-
-    def handle_app(self, context):
-        self.validate_correct_type_of_configuration_attribute("app__verbose", bool)
-        self.validate_correct_type_of_configuration_attribute("app__debug", bool)
-        self.validate_correct_type_of_configuration_attribute("app__host", str)
-        self.validate_correct_type_of_configuration_attribute("app__port", (type(None), int))
-        self.validate_correct_type_of_configuration_attribute("app__open_browser", bool)
-        self.validate_correct_type_of_configuration_attribute("app__force_https", bool)
-        self.validate_correct_type_of_configuration_attribute("app__flask_secret_key", str)
-        self.validate_correct_type_of_configuration_attribute("app__generate_cache_control_headers", bool)
-        self.validate_correct_type_of_configuration_attribute("app__server_timing_headers", bool)
-        self.validate_correct_type_of_configuration_attribute("app__csp_directives", (type(None), dict))
-        self.validate_correct_type_of_configuration_attribute("app__api_base_url", (type(None), str))
-        self.validate_correct_type_of_configuration_attribute("app__web_base_url", (type(None), str))
-
-        if self.app__port:
-            try:
-                if not is_port_available(self.app__host, self.app__port):
-                    raise ConfigurationError(
-                        f"The port selected {self.app__port} is in use, please configure an open port."
-                    )
-            except OverflowError:
-                raise ConfigurationError(f"Invalid port: {self.app__port}")
-        else:
-            try:
-                default_server_port = int(os.environ.get("CXG_SERVER_PORT", DEFAULT_SERVER_PORT))
-            except ValueError:
-                raise ConfigurationError(
-                    "Invalid port from environment variable CXG_SERVER_PORT: " + os.environ.get("CXG_SERVER_PORT")
-                )
-            try:
-                self.app__port = find_available_port(self.app__host, default_server_port)
-            except OverflowError:
-                raise ConfigurationError(f"Invalid port: {default_server_port}")
-
-        if self.app__debug:
-            context["messagefn"]("in debug mode, setting verbose=True and open_browser=False")
-            self.app__verbose = True
-            self.app__open_browser = False
-        else:
-            warnings.formatwarning = custom_format_warning
-
-        if not self.app__verbose:
-            sys.tracebacklimit = 0
-
-        # CSP Directives are a dict of string: list(string) or string: string
-        if self.app__csp_directives is not None:
-            for k, v in self.app__csp_directives.items():
-                if not isinstance(k, str):
-                    raise ConfigurationError("CSP directive names must be a string.")
-                if isinstance(v, list):
-                    for policy in v:
-                        if not isinstance(policy, str):
-                            raise ConfigurationError("CSP directive value must be a string or list of strings.")
-                elif not isinstance(v, str):
-                    raise ConfigurationError("CSP directive value must be a string or list of strings.")
-
-        if self.app__web_base_url is None:
-            self.app__web_base_url = self.app__api_base_url
-
-    def handle_authentication(self):
-        self.validate_correct_type_of_configuration_attribute("authentication__type", (type(None), str))
-        self.validate_correct_type_of_configuration_attribute("authentication__insecure_test_environment", bool)
-
-        if self.authentication__type == "test" and not self.authentication__insecure_test_environment:
-            raise ConfigurationError("Test auth can only be used in an insecure test environment")
-
-        # oauth
-        ptypes = str if self.authentication__type == "oauth" else (type(None), str)
-        self.validate_correct_type_of_configuration_attribute(
-            "authentication__params_oauth__oauth_api_base_url", ptypes
-        )
-        self.validate_correct_type_of_configuration_attribute("authentication__params_oauth__client_id", ptypes)
-        self.validate_correct_type_of_configuration_attribute("authentication__params_oauth__client_secret", ptypes)
-        self.validate_correct_type_of_configuration_attribute(
-            "authentication__params_oauth__jwt_decode_options", (type(None), dict)
-        )
-        self.validate_correct_type_of_configuration_attribute("authentication__params_oauth__session_cookie", bool)
-
-        if self.authentication__params_oauth__session_cookie:
-            self.validate_correct_type_of_configuration_attribute(
-                "authentication__params_oauth__cookie", (type(None), dict)
-            )
-        else:
-            self.validate_correct_type_of_configuration_attribute("authentication__params_oauth__cookie", dict)
-
-        self.auth = AuthTypeFactory.create(self.authentication__type, self)
-        if self.auth is None:
-            raise ConfigurationError(f"Unknown authentication type: {self.authentication__type}")
-
-    def handle_data_locator(self):
-        self.validate_correct_type_of_configuration_attribute("data_locator__s3__region_name", (type(None), bool, str))
-        if self.data_locator__s3__region_name is True:
-            path = self.single_dataset__datapath or self.multi_dataset__dataroot
-
-            if type(path) == dict:
-                # if multi_dataset__dataroot is a dict, then use the first key
-                # that is in s3.   NOTE:  it is not supported to have dataroots
-                # in different regions.
-                paths = [val.get("dataroot") for val in path.values()]
-                for path in paths:
-                    if path.startswith("s3://"):
-                        break
-            if path.startswith("s3://"):
-                region_name = discover_s3_region_name(path)
-                if region_name is None:
-                    raise ConfigurationError(f"Unable to discover s3 region name from {path}")
-            else:
-                region_name = None
-            self.data_locator__s3__region_name = region_name
-
-    def handle_data_source(self):
-        self.validate_correct_type_of_configuration_attribute("single_dataset__datapath", (str, type(None)))
-        self.validate_correct_type_of_configuration_attribute("multi_dataset__dataroot", (type(None), dict, str))
-
-        if self.single_dataset__datapath and self.multi_dataset__dataroot:
-            raise ConfigurationError(
-                "You must supply either a datapath (for single datasets) or a dataroot (for multidatasets). Not both"
-            )
-        if self.single_dataset__datapath is None and self.multi_dataset__dataroot is None:
-            raise ConfigurationError("You must specify a datapath for a single dataset or a dataroot for multidatasets")
-
-    def handle_single_dataset(self, context):
-        self.validate_correct_type_of_configuration_attribute("single_dataset__datapath", (str, type(None)))
-        self.validate_correct_type_of_configuration_attribute("single_dataset__title", (str, type(None)))
-        self.validate_correct_type_of_configuration_attribute("single_dataset__about", (str, type(None)))
-        self.validate_correct_type_of_configuration_attribute("single_dataset__obs_names", (str, type(None)))
-        self.validate_correct_type_of_configuration_attribute("single_dataset__var_names", (str, type(None)))
-
-        if self.single_dataset__datapath is None:
-            return
-
-        # create the matrix data cache manager:
-        if self.matrix_data_cache_manager is None:
-            self.matrix_data_cache_manager = MatrixDataCacheManager(max_cached=1, timelimit_s=None)
-
-        # preload this data set
-        matrix_data_loader = MatrixDataLoader(self.single_dataset__datapath, app_config=self.app_config)
-        try:
-            matrix_data_loader.pre_load_validation()
-        except DatasetAccessError as e:
-            raise ConfigurationError(str(e))
-
-        file_size = matrix_data_loader.file_size()
-        file_basename = basename(self.single_dataset__datapath)
-        if file_size > BIG_FILE_SIZE_THRESHOLD:
-            context["messagefn"](f"Loading data from {file_basename}, this may take a while...")
-        else:
-            context["messagefn"](f"Loading data from {file_basename}.")
-
-        if self.single_dataset__about:
-
-            def url_check(url):
-                try:
-                    result = urlparse(url)
-                    if all([result.scheme, result.netloc]):
-                        return True
-                    else:
-                        return False
-                except ValueError:
-                    return False
-
-            if not url_check(self.single_dataset__about):
-                raise ConfigurationError(
-                    "Must provide an absolute URL for --about. (Example format: http://example.com)"
-                )
-
-    def handle_multi_dataset(self):
-        self.validate_correct_type_of_configuration_attribute("multi_dataset__dataroot", (type(None), dict, str))
-        self.validate_correct_type_of_configuration_attribute("multi_dataset__index", (type(None), bool, str))
-        self.validate_correct_type_of_configuration_attribute("multi_dataset__allowed_matrix_types", list)
-        self.validate_correct_type_of_configuration_attribute("multi_dataset__matrix_cache__max_datasets", int)
-        self.validate_correct_type_of_configuration_attribute(
-            "multi_dataset__matrix_cache__timelimit_s", (type(None), int, float)
-        )
-
-        if self.multi_dataset__dataroot is None:
-            return
-
-        if type(self.multi_dataset__dataroot) == str:
-            default_dict = dict(base_url="d", dataroot=self.multi_dataset__dataroot)
-            self.multi_dataset__dataroot = dict(d=default_dict)
-
-        for tag, dataroot_dict in self.multi_dataset__dataroot.items():
-            if "base_url" not in dataroot_dict:
-                raise ConfigurationError(f"error in multi_dataset__dataroot: missing base_url for tag {tag}")
-            if "dataroot" not in dataroot_dict:
-                raise ConfigurationError(f"error in multi_dataset__dataroot: missing dataroot, for tag {tag}")
-
-            base_url = dataroot_dict["base_url"]
-
-            # sanity check for well formed base urls
-            bad = False
-            if type(base_url) != str:
-                bad = True
-            elif os.path.normpath(base_url) != base_url:
-                bad = True
-            else:
-                base_url_parts = base_url.split("/")
-                if [quote_plus(part) for part in base_url_parts] != base_url_parts:
-                    bad = True
-                if ".." in base_url_parts:
-                    bad = True
-            if bad:
-                raise ConfigurationError(f"error in multi_dataset__dataroot base_url {base_url} for tag {tag}")
-
-        # verify all the base_urls are unique
-        base_urls = [d["base_url"] for d in self.multi_dataset__dataroot.values()]
-        if len(base_urls) > len(set(base_urls)):
-            raise ConfigurationError("error in multi_dataset__dataroot:  base_urls must be unique")
-
-        # error checking
-        for mtype in self.multi_dataset__allowed_matrix_types:
-            try:
-                MatrixDataType(mtype)
-            except ValueError:
-                raise ConfigurationError(f'Invalid matrix type in "allowed_matrix_types": {mtype}')
-
-        # create the matrix data cache manager:
-        if self.matrix_data_cache_manager is None:
-            self.matrix_data_cache_manager = MatrixDataCacheManager(
-                max_cached=self.multi_dataset__matrix_cache__max_datasets,
-                timelimit_s=self.multi_dataset__matrix_cache__timelimit_s,
-            )
-
-    def handle_diffexp(self):
-        self.validate_correct_type_of_configuration_attribute("diffexp__alg_cxg__max_workers", (str, int))
-        self.validate_correct_type_of_configuration_attribute("diffexp__alg_cxg__cpu_multiplier", int)
-        self.validate_correct_type_of_configuration_attribute("diffexp__alg_cxg__target_workunit", int)
-
-        max_workers = self.diffexp__alg_cxg__max_workers
-        cpu_multiplier = self.diffexp__alg_cxg__cpu_multiplier
-        cpu_count = os.cpu_count()
-        max_workers = min(max_workers, cpu_multiplier * cpu_count)
-        diffexp_tiledb.set_config(max_workers, self.diffexp__alg_cxg__target_workunit)
-
-    def handle_adaptor(self):
-        # cxg
-        self.validate_correct_type_of_configuration_attribute("adaptor__cxg_adaptor__tiledb_ctx", dict)
-        regionkey = "vfs.s3.region"
-        if regionkey not in self.adaptor__cxg_adaptor__tiledb_ctx:
-            if type(self.data_locator__s3__region_name) == str:
-                self.adaptor__cxg_adaptor__tiledb_ctx[regionkey] = self.data_locator__s3__region_name
-
-        from backend.czi_hosted.data_cxg.cxg_adaptor import CxgAdaptor
-
-        CxgAdaptor.set_tiledb_context(self.adaptor__cxg_adaptor__tiledb_ctx)
-
-        # anndata
-        self.validate_correct_type_of_configuration_attribute("adaptor__anndata_adaptor__backed", bool)
-
-    def handle_limits(self):
-        self.validate_correct_type_of_configuration_attribute("limits__diffexp_cellcount_max", (type(None), int))
-        self.validate_correct_type_of_configuration_attribute("limits__column_request_max", (type(None), int))
-
-    def exceeds_limit(self, limit_name, value):
-        limit_value = getattr(self, "limits__" + limit_name, None)
-        if limit_value is None:  # disabled
-            return False
-        return value > limit_value
-
-    def get_api_base_url(self):
-        if self.app__api_base_url == "local":
-            return f"http://{self.app__host}:{self.app__port}"
-        if self.app__api_base_url and self.app__api_base_url.endswith("/"):
-            return self.app__api_base_url[:-1]
-        return self.app__api_base_url
-
-    def get_web_base_url(self):
-        if self.app__web_base_url == "local":
-            return f"http://{self.app__host}:{self.app__port}"
-        if self.app__web_base_url is None:
-            return self.get_api_base_url()
-        if self.app__web_base_url.endswith("/"):
-            return self.app__web_base_url[:-1]
-        return self.app__web_base_url

backend/czi_hosted/converters/schema/gene_symbol.py

@@ -1,211 +0,0 @@
-"""Helpers for converting and checking HGNC gene symbols."""
-
-import argparse
-import enum
-import logging
-import os
-import re
-import numpy as np
-import pandas as pd
-
-
-def get_upgraded_var_index(var, hgnc_path=None):
-    """Given an anndata var dataframe, return a new index for the dataframe
-    where human gene symbols have been upgraded to the current HGNC set.
-    """
-
-    if not hgnc_path:
-        hgnc_path = os.path.join(os.path.dirname(os.path.realpath(__file__)), "hgnc_complete_set.txt.gz")
-
-    hgnc_symbol_checker = HGNCSymbolChecker.from_hgnc_records(hgnc_path)
-
-    return pd.Index([hgnc_symbol_checker.upgrade_symbol(s) for s in var.index])
-
-
-class SymbolStatus(enum.Enum):
-    """The status of a symbol in the HGNC database.
-
-    APPROVED: Currently a valid symbol
-    WITHDRAWN: A previously approved HGNC symbol for a gene that has since been shown
-               not to exist _unless_ that symbol is also approved
-    AMBIGUOUS: A symbol that is not approved but is an alias or previous symbol for
-               multiple approved symbols
-    UPGRADABLE: A symbol that is not approved but unambiguously maps to an approved
-                symbol
-    UNKNOWN: A symbol that does not appear in HGNC
-    """
-
-    APPROVED = 1
-    WITHDRAWN = 2
-    AMBIGUOUS = 3
-    UPGRADABLE = 4
-    UNKNOWN = 5
-
-
-class HGNCSymbolChecker:
-    """Handle checking and correcting HGNC symbols."""
-
-    def __init__(self, approved_symbols, withdrawn_symbols, ambiguous_symbols, symbol_map):
-        self.approved_symbols = approved_symbols
-        self.withdrawn_symbols = withdrawn_symbols
-        self.ambiguous_symbols = ambiguous_symbols
-        self.symbol_map = symbol_map
-
-    def print_symbol_map(self):
-        """Print out a map from old symbol to new symbol."""
-
-        for symbol_pair in self.symbol_map.items():
-            print("\t".join(symbol_pair))
-
-    def check_symbol(self, symbol):
-        """See if a symbol if approved or something else."""
-        if symbol in self.approved_symbols:
-            return SymbolStatus.APPROVED
-
-        if symbol in self.withdrawn_symbols:
-            return SymbolStatus.WITHDRAWN
-
-        if symbol in self.ambiguous_symbols:
-            return SymbolStatus.AMBIGUOUS
-
-        if symbol in self.symbol_map:
-            return SymbolStatus.UPGRADABLE
-
-        return SymbolStatus.UNKNOWN
-
-    def upgrade_symbol(self, symbol):
-        """Return the approved symbol for the given symbol.
-
-        If the symbol cannot be upgraded, just return the original symbol.
-        """
-
-        fixed_symbol, stripped_symbol = format_symbol(symbol)
-
-        if fixed_symbol in self.approved_symbols:
-            return fixed_symbol
-        elif fixed_symbol in self.symbol_map:
-            return self.symbol_map[fixed_symbol]
-        elif stripped_symbol in self.approved_symbols:
-            return stripped_symbol
-        elif stripped_symbol in self.symbol_map:
-            return self.symbol_map[stripped_symbol]
-
-        return symbol
-
-    @classmethod
-    def from_hgnc_records(cls, hgnc_dataset_path):
-        """Parse a hgnc database download into a HGNCSymbolChecker object."""
-
-        def all_symbols(record):
-            """Get all the symbols associated with an HGNC record including previous, alias,
-            and approved."""
-            yield format_symbol(record["symbol"])[0]
-            for symbol in alias_and_previous_symbols(record):
-                yield symbol
-
-        def alias_and_previous_symbols(record):
-            """Get alias and previous symbols from an HGNC record."""
-            for field in ("alias_symbol", "prev_symbol"):
-                if record[field] is not np.nan:
-                    for symbol in record[field].split("|"):
-                        yield format_symbol(symbol)[0]
-            # Sometimes something like HGNC:1234 appears in datasets, which we
-            # want to fix as well.
-            yield record["hgnc_id"]
-
-        hgnc_records = pd.read_csv(hgnc_dataset_path, sep="\t", header=0, low_memory=False).to_dict("records")
-
-        # Get all symbols that are currently approved.
-        approved_symbols = set()
-        for record in hgnc_records:
-            if record["status"] == "Approved":
-                approved_symbols.add(format_symbol(record["symbol"])[0])
-
-        # Get all symbols that have been withdrawn
-        withdrawn_symbols = set()
-        for record in hgnc_records:
-            if record["status"] == "Entry Withdrawn":
-                for symbol in all_symbols(record):
-                    withdrawn_symbols.add(symbol)
-
-        # If a symbol is both approved and withdrawn, be optimistic and call it approved
-        logging.warning(
-            f"Some symbols are simulaneously withdrawn and approved\n"
-            f"We will treat them at approved:\n"
-            f"{withdrawn_symbols.intersection(approved_symbols)}"
-        )
-        withdrawn_symbols = withdrawn_symbols.difference(approved_symbols)
-
-        # Now try to map from symbols that are not approved but are an alias or previous symbol for an approved symbol
-        alias_previous_to_approved = {}
-        ambiguous_symbols = set()
-
-        for record in hgnc_records:
-            if record["status"] == "Approved":
-
-                # The approved symbol is what we'll map to
-                approved_symbol = format_symbol(record["symbol"])[0]
-
-                for symbol in alias_and_previous_symbols(record):
-
-                    # If the alias or previous symbol is also an approved symbol,
-                    # we'll just leave it alone
-                    if symbol in approved_symbols:
-                        continue
-
-                    # If the alias or previous symbol maps to a different approved symbol, mark it as ambiguous
-                    if symbol in alias_previous_to_approved and alias_previous_to_approved[symbol] != approved_symbol:
-                        ambiguous_symbols.add(symbol)
-                    else:
-                        alias_previous_to_approved[symbol] = approved_symbol
-
-        # Remove all the ambiguous symbols from the map
-        for ambiguous_symbol in ambiguous_symbols:
-            alias_previous_to_approved.pop(ambiguous_symbol)
-
-        return HGNCSymbolChecker(approved_symbols, withdrawn_symbols, ambiguous_symbols, alias_previous_to_approved)
-
-
-def format_symbol(symbol):
-    """HGNC rules say symbols should all be upper case except for C#orf#. However, case is
-    variable in both alias and previous symbols as well as in the symbols we get in
-    submissions. So, upper case everything except for the one situation where mixed-case
-    is allowed, which are the genes like C2orf157.
-
-    Also, seurat and scanpy append ".1" or "-1" to duplicated gene names, and these altered
-    names persist throughout the life of the object. They won't match against the HGNC database
-    and we want to merge them, so we need to strip off the suffix and try matching again.
-
-    This function takes a symbol and returns the symbol with the fixed case and also with the
-    seurat/scanpy suffix stripped off.
-    """
-
-    match = re.match(r"^(C)(\d+)(orf)(\d+)$", symbol, re.IGNORECASE)
-
-    if match:
-        fixed_case = f"C{match.group(2)}orf{match.group(4)}"
-    else:
-        fixed_case = symbol.upper()
-
-    suffix_stripped = re.sub(r"[\.\-]\d+$", "", fixed_case)
-
-    return fixed_case, suffix_stripped
-
-
-def main():
-    """When called as main, parse a given hgnc download and print out a map from old to new
-    symbol.
-    """
-    parser = argparse.ArgumentParser()
-    parser.add_argument(
-        "hgnc_dataset", help="HGNC dataset tsv, available from www.genenames.org/download/statistics-and-files/"
-    )
-    args = parser.parse_args()
-
-    hgnc_symbol_checker = HGNCSymbolChecker.from_hgnc_records(args.hgnc_dataset)
-
-    hgnc_symbol_checker.print_symbol_map()
-
-
-if __name__ == "__main__":
-    main()

backend/czi_hosted/converters/schema/ontology.py

@@ -1,86 +0,0 @@
-"""Methods for working with ontologies and the OLS."""
-from urllib.parse import quote_plus
-
-import requests
-
-OLS_API_ROOT = "http://www.ebi.ac.uk/ols/api"
-
-# Curie means something like CL:0000001
-
-
-def _ontology_name(curie):
-    """Get the name of the ontology from the curie, CL or UBERON for example."""
-    return curie.split(":")[0]
-
-
-def _ontology_value(curie):
-    """Get the id component of the curie, 0000001 from CL:0000001 for example."""
-    return curie.split(":")[1]
-
-
-def _double_encode(url):
-    """Double url encode a url. This is required by the OLS API."""
-    return quote_plus(quote_plus(url))
-
-
-def _iri(curie):
-    """Get the iri from a curie. This is a bit hopeful that they all map to purl.obolibrary.org"""
-    if _ontology_name(curie) == "EFO":
-        return f"http://www.ebi.ac.uk/efo/EFO_{_ontology_value(curie)}"
-    return f"http://purl.obolibrary.org/obo/{_ontology_name(curie)}_{_ontology_value(curie)}"
-
-
-class OntologyLookupError(Exception):
-    """Exception for some problem with looking up ontology information."""
-
-
-def _ontology_info_url(curie):
-    """Get the to make a GET to to get information about an ontology term."""
-
-    # If the curie is empty, just return an empty string. This happens when there is no
-    # valid ontology value.
-    if not curie:
-        return ""
-    else:
-        return f"{OLS_API_ROOT}/ontologies/{_ontology_name(curie)}/terms/{_double_encode(_iri(curie))}"
-
-
-def get_ontology_label(curie):
-    """For a given curie like 'CL:1000413', get the label like 'endothelial cell of artery'"""
-
-    url = _ontology_info_url(curie)
-
-    if not url:
-        return ""
-
-    response = requests.get(url)
-
-    if not response.ok:
-        raise OntologyLookupError(
-            f"Curie {curie} lookup failed, got status code {response.status_code}: {response.text}"
-        )
-    return response.json()["label"]
-
-
-def lookup_candidate_term(label, ontology="cl", method="select"):
-    """Lookup candidate terms for a label. This is useful when there is an existing label in a
-    submitted dataset, and you want to find an appropriate ontology term.
-
-    Args:
-      label: the label to find ontology terms for
-      ontology: the ontology to search in, cl or uberon or efo for example
-      method: select or search. search provides much broader results
-
-    Returns:
-      list of (curie, label) tuples returned by OLS
-    """
-    # using OLS REST API [https://www.ebi.ac.uk/ols/docs/api]
-    url = f"{OLS_API_ROOT}/{method}?q={quote_plus(label)}&ontology={ontology.lower()}"
-    response = requests.get(url)
-
-    if not response.ok:
-        raise OntologyLookupError(
-            f"Label {label} lookup failed, got status code {response.status_code}: {response.text}"
-        )
-
-    return [(r["obo_id"], r["label"]) for r in response.json()["response"]["docs"]]

backend/czi_hosted/converters/schema/remix.py

@@ -1,264 +0,0 @@
-import argparse
-import collections
-import json
-import logging
-import math
-import string
-
-import anndata
-import numpy as np
-import pandas as pd
-import yaml
-
-from . import gene_symbol
-from . import ontology
-from . import validate
-
-REPLACE_SUFFIX = "_original"
-ONTOLOGY_SUFFIX = "_ontology_term_id"
-
-
-def is_curie(value):
-    """Return True iff the value is an OBO-id CURIE like EFO:000001"""
-    return (value.count(":")
-            and all(len(part) > 0 for part in value.split(":"))
-            and all(c in string.digits for c in value.split(":")[1]))
-
-
-def is_ontology_field(field_name):
-    """Return True iff the field_name is an ontology field like tissue_ontology_term_id"""
-    return field_name.endswith(ONTOLOGY_SUFFIX)
-
-
-def get_label_field_name(field_name):
-    """Get the associated label field from an ontology field, assay_ontology_term_id --> assay"""
-    return field_name[: -len(ONTOLOGY_SUFFIX)]
-
-
-def split_suffix(maybe_curie):
-    """Split off the (cell culture) or (organoid) suffix."""
-
-    suffixes = [" (cell culture)", " (organoid)"]
-    for suffix in suffixes:
-        if maybe_curie.endswith(suffix):
-            return maybe_curie[:-len(suffix)], suffix
-    return maybe_curie, ""
-
-
-def get_curie_and_label(maybe_curie):
-    """Given a string that might be a curie, return a (curie, label) pair"""
-
-    maybe_curie, suffix = split_suffix(maybe_curie)
-    if not is_curie(maybe_curie):
-        return ("", maybe_curie + suffix)
-    return (maybe_curie + suffix, ontology.get_ontology_label(maybe_curie) + suffix)
-
-
-def safe_add_field(adata_attr, field_name, field_value):
-    """Add a field and value to an AnnData, but don't clobber an exising value."""
-
-    if (
-        isinstance(field_value, list)
-        and field_value
-        and isinstance(field_value[0], dict)
-    ):
-        field_value = json.dumps(field_value)
-    if field_name in adata_attr:
-        adata_attr[field_name + REPLACE_SUFFIX] = adata_attr[field_name]
-    adata_attr[field_name] = field_value
-
-
-def remix_uns(adata, uns_config):
-    """Add fields from the config to adata.uns"""
-    for field_name, field_value in uns_config.items():
-
-        if is_ontology_field(field_name):
-            # If it's an ontology field, look it up
-            label_field_name = get_label_field_name(field_name)
-            ontology_term, ontology_label = get_curie_and_label(field_value)
-            safe_add_field(adata.uns, field_name, ontology_term)
-            safe_add_field(adata.uns, label_field_name, ontology_label)
-        else:
-            safe_add_field(adata.uns, field_name, field_value)
-
-
-def remix_obs(adata, obs_config):
-    """Add fields from the config to adata.obs"""
-
-    for field_name, field_value in obs_config.items():
-
-        if isinstance(field_value, dict):
-            # If the value is a dict, that means we are supposed to map from an
-            # existing column to the new one
-            source_column, column_map = next(iter(field_value.items()))
-            nan_value = None
-            for key in column_map:
-                if isinstance(key, float) and math.isnan(key):
-                    nan_value = column_map[key]
-            if nan_value is not None:
-                column_map["nan"] = nan_value
-
-            for key in column_map:
-                if key not in adata.obs[source_column].unique():
-                    logging.warning(f'Key {key} not in adata.obs["{source_column}"]')
-
-            for value in adata.obs[source_column].unique():
-                if value not in column_map:
-                    logging.warning(f'Value {value} in adata.obs["{source_column}"] not in translation dict')
-
-            if is_ontology_field(field_name):
-                ontology_term_map, ontology_label_map = {}, {}
-                logging.info(f"Looking up labels for {field_name}")
-                for original_value, maybe_curie in column_map.items():
-                    curie, label = get_curie_and_label(maybe_curie)
-                    ontology_term_map[original_value] = curie
-                    ontology_label_map[original_value] = label
-                    logging.info(f"Mapping {original_value} -> {curie} -> {label}")
-
-                ontology_column = adata.obs[source_column].replace(
-                    ontology_term_map, inplace=False
-                )
-                label_column = adata.obs[source_column].replace(
-                    ontology_label_map, inplace=False
-                )
-
-                safe_add_field(adata.obs, field_name, ontology_column)
-                safe_add_field(
-                    adata.obs, get_label_field_name(field_name), label_column
-                )
-            else:
-                label_column = adata.obs[source_column].replace(
-                    column_map, inplace=False
-                )
-                safe_add_field(adata.obs, field_name, label_column)
-
-        else:
-            if is_ontology_field(field_name):
-                # If it's an ontology field, look it up
-                label_field_name = get_label_field_name(field_name)
-                ontology_term, ontology_label = get_curie_and_label(field_value)
-                safe_add_field(adata.obs, field_name, ontology_term)
-                safe_add_field(adata.obs, label_field_name, ontology_label)
-            else:
-                safe_add_field(adata.obs, field_name, field_value)
-
-
-def merge_df(df, domain, index, columns):
-    """
-    Given a dataframe with duplicate column labels, merge and return a dataframe where
-    the duplicates have been merged together, resulting in a dataframe with unique column
-    labels.
-
-    "merge" depends on the value of domain. If the domain is "raw", then duplicate columns
-    can just be summed. If it's "log1p" or "sqrt", it needs to be exp1m'd or squared, then
-    summed, and then logged or sqrt'd again.
-    """
-
-    if not isinstance(df, np.ndarray):
-        to_merge = df.toarray()
-    else:
-        to_merge = df
-    if domain == "raw":
-        merged_df = pd.DataFrame(to_merge, index=index, columns=columns).sum(
-            axis=1, level=0, skipna=False
-        )
-    elif domain == "log1p":
-        merged_df = (
-            pd.DataFrame(np.expm1(to_merge, dtype=np.float128), index=index, columns=columns)
-            .sum(axis=1, level=0, skipna=False)
-        )
-        merged_df = pd.DataFrame(np.log1p(merged_df.to_numpy()), index=merged_df.index, columns=merged_df.columns)
-    elif domain == "sqrt":
-        merged_df = (
-            pd.DataFrame(np.square(to_merge), index=index, columns=columns)
-            .sum(axis=1, level=0, skipna=False)
-        )
-        merged_df = pd.DataFrame(np.sqrt(merged_df.to_numpy()), index=merged_df.index, columns=merged_df.columns)
-
-    return merged_df
-
-
-def fixup_gene_symbols(adata, fixup_config):
-    """Update the var index to hold a consistent set of HGNC gene symbols."""
-
-    upgraded_var_index = gene_symbol.get_upgraded_var_index(adata.var)
-
-    merged_X = merge_df(adata.X, fixup_config["X"], adata.obs.index, upgraded_var_index)
-    fixup_adata = anndata.AnnData(
-        X=merged_X,
-        obs=adata.obs,
-        var=merged_X.columns.to_frame(name="hgnc_gene_symbol"),
-        uns=adata.uns,
-        obsm=adata.obsm,
-    )
-
-    for layer, domain in fixup_config.items():
-        if layer == "X":
-            continue
-        if layer == "raw.X":
-            df = adata.raw.X
-        else:
-            df = adata.layers[layer]
-
-        merged_df = merge_df(df, domain, adata.obs.index, upgraded_var_index)
-        assert merged_df.index.equals(merged_X.index)
-        assert merged_df.columns.equals(merged_X.columns)
-
-        if domain == "raw":
-            fixup_raw = anndata.AnnData(
-                X=merged_df,
-                obs=adata.obs,
-                var=merged_X.columns.to_frame(name="hgnc_gene_symbol"),
-            )
-            fixup_adata.raw = fixup_raw
-        else:
-            fixup_adata.layers[layer] = merged_df
-
-    return fixup_adata
-
-def _strip_version(adata):
-    """Remove version information from the AnnData object."""
-
-    if "version" in adata.uns_keys():
-        del adata.uns["version"]
-
-def apply_schema(source_h5ad, remix_config, output_filename):
-
-    try:
-        import scanpy
-    except ImportError:
-        raise ImportError("scanpy must be installed for cellxgene schema")
-    adata = scanpy.read_h5ad(source_h5ad)
-    config = yaml.load(open(remix_config), Loader=yaml.FullLoader)
-    remix_uns(adata, config["uns"])
-    remix_obs(adata, config["obs"])
-
-    if config.get("fixup_gene_symbols"):
-        adata = fixup_gene_symbols(adata, config["fixup_gene_symbols"])
-
-    if ("version" in adata.uns_keys()
-            and isinstance(adata.uns["version"], collections.Mapping)
-            and "corpora_schema_version" in adata.uns["version"]):
-        schema_version = adata.uns["version"]["corpora_schema_version"]
-        try:
-            validate.get_schema_definition(schema_version)
-        except ValueError:
-            logging.warning(f"Stripping version information out of AnnData because schema "
-                            f"version {schema_version} is unknown.")
-            _strip_version(adata)
-
-        if not validate.validate_adata(adata, shallow=False):
-            logging.warning(f"Stripping version information out of AnnData because it does not "
-                            f"follow schema version {schema_version} .")
-            _strip_version(adata)
-
-    adata.write_h5ad(output_filename, compression="gzip")
-
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser()
-    parser.add_argument("--source-h5ad", required=True)
-    parser.add_argument("--remix-config", required=True)
-    parser.add_argument("--output-filename", required=True)
-    args = parser.parse_args()
-    apply_schema(args.source_h5ad, args.remix_config, args.output_filename)

backend/czi_hosted/converters/schema/schema_definitions/1_0_0.yaml

@@ -1,95 +0,0 @@
-title: Corpora schema version 1.0.0
-type: anndata
-components:
-    uns:
-        type: dict
-        keys:
-            version:
-                type: dict
-                keys:
-                    corpora_schema_version: null
-                    corpora_encoding_version: null
-            title:
-                type: string
-            contributors:
-                type: stringified list of dicts
-            layer_descriptions:
-                type: dict
-                keys:
-                    X: null
-            organism:
-                type: string
-                nullable: false
-            organism_ontology_term_id:
-                type: curie
-                prefixes:
-                    - NCBITaxon
-    var:
-        type: dataframe
-        index:
-            type: human-readable string
-            unique: true
-    obs:
-        type: dataframe
-        index:
-            unique: true
-        columns:
-            tissue:
-                type: human-readable string
-                nullable: false
-            tissue_ontology_term_id:
-                type: suffixed curie
-                nullable: true
-                prefixes:
-                    - UBERON
-            assay:
-                type: human-readable string
-                nullable: false
-            assay_ontology_term_id:
-                type: curie
-                nullable: true
-                prefixes:
-                    - EFO
-            disease:
-                type: human-readable string
-                nullable: false
-            disease_ontology_term_id:
-                type: curie
-                nullable: true
-                prefixes:
-                    - MONDO
-                    - PATO
-            cell_type:
-                type: human-readable string
-                nullable: false
-            cell_type_ontology_term_id:
-                type: curie
-                nullable: true
-                prefixes:
-                    - CL
-                    - UBERON
-            sex:
-                type: string
-                enum:
-                    - male
-                    - female
-                    - mixed
-                    - unknown
-                    - other
-            ethnicity:
-                type: human-readable string
-                nullable: false
-            ethnicity_ontology_term_id:
-                type: curie
-                nullable: true
-                prefixes:
-                    - HANCESTRO
-            development_stage:
-                type: human-readable string
-                nullable: false
-            development_stage_ontology_term_id:
-                type: curie
-                nullable: true
-                prefixes:
-                    - HsapDv
-                    - EFO

backend/czi_hosted/converters/schema/schema_definitions/1_1_0.yaml

@@ -1,93 +0,0 @@
-title: Corpora schema version 1.1.0
-type: anndata
-components:
-    uns:
-        type: dict
-        keys:
-            version:
-                type: dict
-                keys:
-                    corpora_schema_version: null
-                    corpora_encoding_version: null
-            title:
-                type: string
-            layer_descriptions:
-                type: dict
-                keys:
-                    X: null
-            organism:
-                type: string
-                nullable: false
-            organism_ontology_term_id:
-                type: curie
-                prefixes:
-                    - NCBITaxon
-    var:
-        type: dataframe
-        index:
-            type: human-readable string
-            unique: true
-    obs:
-        type: dataframe
-        index:
-            unique: true
-        columns:
-            tissue:
-                type: human-readable string
-                nullable: false
-            tissue_ontology_term_id:
-                type: suffixed curie
-                nullable: true
-                prefixes:
-                    - UBERON
-            assay:
-                type: human-readable string
-                nullable: false
-            assay_ontology_term_id:
-                type: curie
-                nullable: true
-                prefixes:
-                    - EFO
-            disease:
-                type: human-readable string
-                nullable: false
-            disease_ontology_term_id:
-                type: curie
-                nullable: true
-                prefixes:
-                    - MONDO
-                    - PATO
-            cell_type:
-                type: human-readable string
-                nullable: false
-            cell_type_ontology_term_id:
-                type: curie
-                nullable: true
-                prefixes:
-                    - CL
-                    - UBERON
-            sex:
-                type: string
-                enum:
-                    - male
-                    - female
-                    - mixed
-                    - unknown
-                    - other
-            ethnicity:
-                type: human-readable string
-                nullable: false
-            ethnicity_ontology_term_id:
-                type: curie
-                nullable: true
-                prefixes:
-                    - HANCESTRO
-            development_stage:
-                type: human-readable string
-                nullable: false
-            development_stage_ontology_term_id:
-                type: curie
-                nullable: true
-                prefixes:
-                    - HsapDv
-                    - EFO

backend/czi_hosted/converters/schema/validate.py

@@ -1,236 +0,0 @@
-import json
-import re
-import os
-import sys
-
-import pandas as pd
-import yaml
-
-
-def _is_null(v):
-    """Return True if v is null, for one of the multiple ways a "null" value shows up in an h5ad."""
-    return pd.isnull(v) or (hasattr(v, "__len__") and len(v) == 0)
-
-
-def _validate_stringified_list_of_dicts(s):
-    """Verify that a string can be parsed into a list.
-
-    We have some types that are lists of dicts. Those cannot be stored directly in an h5ad, so we have to
-    json.dumps them. This verifies that we can load them back.
-    """
-
-    try:
-        list_ = json.loads(s)
-        if not isinstance(list_, list):
-            return False
-        for el in list_:
-            if not isinstance(el, dict):
-                return False
-        return True
-    except (json.JSONDecodeError, TypeError):
-        pass
-    return False
-
-
-def _validate_human_readable_string(s):
-    """Verify that a string is human-readable.
-
-    There are parts of the schema where a "human-readable" string is required. "Human-readable" is kind
-    of vague and subjective. I feel like I can read many strings. So here we just check for the main ways
-    that fails: someone puts in an ontology term id or and ensembl gene/transcript id.
-
-    Returns False if s is not a string or is one of those bad string types.
-    """
-
-    return isinstance(s, str) and (not re.match(r"[A-Z]\w+:\d+", s)) and (not re.match(r"ENS[GT]\d+$", s))
-
-
-def _validate_curie(c, prefixes):
-    """Verify that a string is a valid compact URI, like EFO:000001. If prefixes is not empty, make sure the
-    prefix of the curies is in prefixes.
-    """
-
-    if not c:
-        return True
-
-    match = re.match(r"([A-Z]\w+):\d+$", c)
-
-    if prefixes:
-        return match and match.group(1) in prefixes
-    else:
-        return match
-
-
-def _validate_suffixed_curie(c, prefixes):
-    """Verify that a string is a compact URI with an optional suffix like 'EFO:00001 (cell culture)'"""
-
-    # Pull off the suffix
-    suffix = re.findall(r"\ \(.*\)$", c)
-    if suffix:
-        c = c[: -len(suffix[0])]
-    return _validate_curie(c, prefixes)
-
-
-def _validate_column(column, column_name, df_name, schema_def):
-    """Given a schema definition and the column of a dataframe, verify that the column satifies
-    the schema.
-    """
-
-    errors = []
-
-    if schema_def.get("unique"):
-        if column.nunique() != len(column):
-            errors.append(f"Column {column_name} in dataframe {df_name} is not unique.")
-
-    if "nullable" in schema_def and not schema_def["nullable"]:
-        if any(_is_null(v) for v in column):
-            errors.append(f"Column {column_name} in dataframe {df_name} contains empty values.")
-
-    if schema_def.get("type") == "human-readable string":
-        non_readables = [v for v in column if not _validate_human_readable_string(v)]
-        if non_readables:
-            errors.append(
-                f"Column {column_name} in dataframe {df_name} contains non-human-readable "
-                f"values like {non_readables[0]}"
-            )
-
-    if schema_def.get("type") in ("curie", "suffixed curie"):
-        validation_func = _validate_curie if schema_def.get("type") == "curie" else _validate_suffixed_curie
-        non_valid_curies = [v for v in column if not validation_func(v, schema_def.get("prefixes"))]
-        if non_valid_curies:
-            errors.append(
-                f"Column {column_name} in dataframe {df_name} contains invalid ontology values like "
-                f"{non_valid_curies[0]}."
-            )
-            if "prefixes" in schema_def:
-                errors[-1] += f" Values must be curies from one of these ontologies {schema_def['prefixes']}."
-
-    if "enum" in schema_def:
-        bad_enums = [v for v in column if v not in schema_def["enum"]]
-        if bad_enums:
-            errors.append(
-                f"Column {column_name} in dataframe {df_name} contains unpermitted values like "
-                f"{bad_enums[0]}. Values must be one of {schema_def['enum']}."
-            )
-
-    return errors
-
-
-def _validate_dict(dict_, dict_name, schema_def):
-    """Given a schema definition and dict, verify that the dict satifies the schema."""
-
-    errors = []
-
-    for key in schema_def.get("keys", []):
-        if key not in dict_:
-            errors.append(f"{dict_name} is missing key {key}.")
-        elif schema_def["keys"][key]:
-            if schema_def["keys"][key]["type"] == "stringified list of dicts":
-                if not _validate_stringified_list_of_dicts(dict_[key]):
-                    errors.append(
-                        f"Key {key} in {dict_name} should be a JSON-encoded list of dicts, but it is {dict_[key]}"
-                    )
-            elif schema_def["keys"][key]["type"] == "dict":
-                errors.extend(_validate_dict(dict_[key], key, schema_def["keys"][key]))
-            elif schema_def["keys"][key]["type"] == "curie":
-                if not _validate_curie(dict_[key], schema_def["keys"][key]["prefixes"]):
-                    errors.append(f"Key {key} in {dict_name} contains invalid ontology value.")
-            if "nullable" in schema_def["keys"][key] and not schema_def["keys"][key]["nullable"]:
-                if _is_null(dict_[key]):
-                    errors.append(f"Key {key} in dict {dict_name} is an empty value.")
-
-    return errors
-
-
-def _validate_dataframe(df, df_name, schema_def):
-    """Given a dataframe and schema definition, verify that the dataframe follows the schema."""
-
-    errors = []
-
-    if "index" in schema_def:
-        errors.extend(_validate_column(df.index, "index", df_name, schema_def["index"]))
-
-    for column in schema_def.get("columns", []):
-        if column not in df.columns:
-            errors.append(f"Dataframe {df_name} is missing column {column}.")
-        else:
-            errors.extend(_validate_column(df[column], column, df_name, schema_def["columns"][column]))
-
-    return errors
-
-
-def get_schema_definition(version):
-    """Look up and read a schema definition based on a version number like "1.0.0"."""
-
-    path = os.path.join(
-        os.path.dirname(os.path.realpath(__file__)), "schema_definitions", version.replace(".", "_") + ".yaml"
-    )
-
-    if not os.path.isfile(path):
-        raise ValueError(f"No definition for version {version} found.")
-
-    return yaml.load(open(path), Loader=yaml.FullLoader)
-
-
-def deep_check(adata, schema_def):
-    """Perform a "deep" check of the AnnData object using the schema definition.
-
-    This checks all the columns and unstructured metadata rather than just the version.
-
-    Returns a list of error messages. If that list is empty, the object passed validation.
-    """
-
-    errors = []
-
-    for component, component_def in schema_def["components"].items():
-        if component_def["type"] == "dataframe":
-            errors.extend(_validate_dataframe(getattr(adata, component), component, component_def))
-        elif component_def["type"] == "dict":
-            errors.extend(_validate_dict(getattr(adata, component), component, component_def))
-        else:
-            raise ValueError(f"Unexpected component type {component['type']}")
-
-    return errors
-
-
-def validate_adata(adata, shallow):
-    """Validate an AnnData object. If shallow, just check that the required version information is
-    present.
-    """
-
-    # Does it have the version information written into uns?
-    if "version" not in adata.uns_keys() or "corpora_schema_version" not in adata.uns["version"]:
-        print("AnnData file is missing corpora version information")
-        return False
-
-    # We can stop here if it's a "shallow" check, that is, if we're just
-    # checking that version is present.
-    if shallow:
-        return True
-
-    schema_def = get_schema_definition(adata.uns["version"]["corpora_schema_version"])
-
-    errors = deep_check(adata, schema_def)
-
-    for error in errors:
-        print(error)
-
-    return not errors
-
-
-def validate(h5ad_path, shallow=False):
-    """Entry point for validation."""
-
-    try:
-        import scanpy
-    except ImportError:
-        raise ImportError("scanpy must be installed for cellxgene schema")
-
-    try:
-        adata = scanpy.read_h5ad(h5ad_path, backed="r")
-    except (OSError, TypeError):
-        print(f"Unable to open {h5ad_path} with scanpy.")
-        sys.exit(1)
-
-    if not validate_adata(adata, shallow):
-        sys.exit(1)

backend/czi_hosted/eb/README.md

@@ -1,300 +0,0 @@
-# AWS Elastic Beanstalk
-
-This directory contains scripts to aid in creating and deploying cellxgene on
-AWS Elastic Beanstalk.
-
-This will result in a variant of cellxgene, running on AWS EC2 instances, serving data from S3.
-All datasets must be in the CXG (tiledb) format (see `cellxene convert --help`),
-and located under a single S3 prefix, which is accessible to the instance.
-In the current incarnation, no access control is available
-(outside of anything you configure yourself), so this is most appropriate for public datasets.
-
-This is early development work, and will change significantly in the near future.
-We would love feedback on it, but please assume it will change.
-
-## Prerequisites
-
-1. Some familiarity with AWS EB, S3, and IAM are needed.
-
-2. Install the awsebcli.
-   Instruction are here:
-   https://docs.aws.amazon.com/elasticbeanstalk/latest/dg/eb-cli3-install.html
-
-3. In the top level directory, run `make build-client` to create the client static assets.
-
-## Steps
-
-These steps are meant to serve as an example.
-There are many more options to these commands that may be important or necessary for your environment.
-
-### 1. Make your matrix files available to the EB servers.
-
-The following choices are known to work.
-
-- S3 Bucket.
-- POSIX filesystem (such as Lustre)
-- Lustre filesystem backed by S3
-
-S3 is convenient and the relatively inexpensive option.
-Lustre is higher performance, but more expensive, and slightly more complex to setup and manage.
-AWS supports a feature to back the Lustre filesystem with S3, which gives an easy to manage, high
-performance option.
-
-Once the storage is in place, the next step is to copy your data files to that location.
-Currently cellxgene supports a flat file organization. Each matrix file is located under
-the same s3 prefix or filesystem directory. This location is specified in the configuration
-as the dataroot.
-
-### 2. Create an elastic beanstalk application. For example:
-
-```
-EB_APP=cellxgene-app
-eb init -p python-3.6 $EB_APP
-```
-
-### 3. Configuring cellxgene
-
-All the cellxgene configuration options can be set from a configuration file.
-A yaml config file containing all of the default configuration options can be generated like this:
-
-`cellxgene launch --dump-default-config > myconfig.yaml`
-
-The config file may then be customized before the app is deployed.
-
-There are two ways to set the config file location, evaluated in this order:
-
-First, if your config file is named "config.yaml" and exists in `customize/config.yaml`,
-then it will be bundled with the application zip file and installed along
-side the app on the EB servers.
-
-Second, a potentially more flexible approach is to place your config file in a location accessible
-to the EB servers, such as in S3. For example: s3://my-bucket/my-datasets/config.yaml.
-Set the CXG_CONFIG_FILE environment variable to specify this location.
-
-Another option is to set the CXG_DATAROOT environment variable. The dataroot
-is the location where the matrix files are located.
-This environment variable will override the dataroot in the config file (if specified).
-
-### 4. Customization
-
-The deployment can be customized in several ways, by adding files to a directory called
-`customize` which is placed in this directory.
-
-#### config file
-
-This was described in the previous section.
-
-#### static files
-
-The cellxgene server can serve additional static webpages that will be associated with the app.
-These include the about_legal_tos (terms of service), and about_legal_privacy, for example.
-To use this feature, do the following:
-
-- In this directory, create a sub directory called "customize/deploy/".
-- Copy the files you want to serve into this directory
-- modify your configuration file to set the location to these file: /static/cellxgene/deploy/<filename>
-
-Example: you want to include an "about_legal_tos" and "about_legal_privacy" page to cellxgene.
-Assume files called "tos.html" and "privacy.html" exist.
-
-```
-$ mkdir -p customize/deploy
-$ cp <source_dir>/tos.html customize/deploy/tos.html
-$ cp <source_dir>/privacy.html customize/deploy/privacy.html
-
-# edit config.yaml
-$ grep "/static/cellxgene/deploy" config.yaml
-about_legal_tos: /static/cellxgene/deploy/tos.html
-about_legal_privacy: /static/cellxgene/deploy/privacy.html
-```
-
-#### Inline javascript scripts
-
-Additional scripts can be added using the server/inline_scripts config parameters.
-To include these scripts in the deployment, use the following steps:
-
-- In this directory, create a sub directory called "customize/inline_scripts".
-- Copy the script files into this directory
-- Modify your configuration file to set the location to these file (leaving off customize/inline_scripts)
-
-For example, to add an inline script called "myscript.js":
-
-```
-$ mkdir -p customize/inline_scripts
-$ cp <source_dir>/myscript.js customize/inline_scripts/myscript.js
-# edit the config.yaml
-$ grep inline_scripts config.yaml
-  inline_scripts : [ myscript.js ]
-```
-
-#### Plugins
-
-Optionally, you can add plugins to the server python code. To include a plugin in the deployment use the following steps:
-
-```
-$ mkdir -p customize/plugins
-$ cp <source_dir>/<my_plugin>.py customize/plugins/<my_plugin>.py
-```
-
-#### ebextensions
-
-Any additional config files intended for the `.ebextensions` directory of the artifact can be added
-to the `customize/ebextensions` directory. Any file found here will be copied over.
-
-#### requirements.txt
-
-A custom requirements.txt can be supplied in customize/requirements.txt.
-This file must fully specify the versions of all the python modules used by the server in the deployment.
-This is useful to ensure that the dependencies do not change from one deployment to the next.
-Therefore the custom/requirements.txt must all have exact versions specified (e.g. anndata==0.7.1).
-
-This file can be generated the first time using a process like this:
-
-```
-#  assume you are running in this directory
-$  virtualenv temp
-$  source temp/bin/activate
-$  pip install -r ../requirements.txt
-$  mkdir -p customize
-$  pip freeze > customize/requirements.txt
-$  deactivate
-$  rm -rf temp/
-```
-
-Keep the customize/requirememts.txt file, and reuse it for each deployment.
-If a future cellxgene version updates its requirements by modifying a module version
-or adding a new dependency, then the `make build` process will detect any
-incompatibilities and raise an error.
-
-#### File structure for customizations
-
-The following diagram shows the file structure for the customization directory.
-
-```
-customization
-+-- config.yaml
-+-- deploy/  
-+-- inline_scripts/
-+-- plugins/
-+-- ebextensions/ 
-+-- requirements.txt
-```
-
-### 5. Create the artifact.zip file for the application
-
-```
-$ make build
-```
-
-### 6. Flask secret key
-
-The application requires a secret key to be provided to flask, the web framework used by cellxgene.
-There are three ways to provide the secret key:
-
-- In the configuration file, update the server/flask_secret_key attribute.
-- In the configuration file, update the external/aws_secrets_manager section to set the
-  secret name and key that defines the flask secret key.
-- An environment variable: `CXG_SECRET_KEY`
-
-### 7. Create an environment
-
-```
-# name of the environment
-$ EB_ENV=cellxgene-env
-
-# type of ec2 instance to run the cellxgene server (for example)
-$ EB_INSTANCE=m5.large
-
-# One or both of the following environment variables needs to be set
-$ CXG_DATAROOT=<location to your S3 bucket>
-$ CXG_CONFIG_FILE=<location to your config file>
-
-# Potentially also set an environment variable for the flask secret key,
-# and other environemet variable described in the configuration file.
-
-$ eb create $EB_ENV --instance-type $EB_INSTANCE \
-   --envvars CXG_DATAROOT=$CXG_DATAROOT,CXG_CONFIG_FILE=$CXG_CONFIG_FILE
-```
-
-### 8. Give the elastic beanstalk environment access to the dataroot.
-
-If using S3, this link may provide some useful information:
-https://aws.amazon.com/premiumsupport/knowledge-center/elastic-beanstalk-s3-bucket-instance/
-If using Lustre, then this link may provide a place to start:
-https://aws.amazon.com/fsx/lustre/
-
-### 9. Deploy the application
-
-```
-$ eb deploy $EB_ENV
-```
-
-### 10. Open the application in a browser
-
-```
-$ eb open $EB_ENV
-```
-
-## Advanced Features
-
-### Authentication
-
-Authentication can be configured in the configuration file. Authentication is required
-for User Annotations (see below). User Annotations is a feature where annotations can be
-created by the user
-, and
-then associated with the user's id.
-When the user revisits the site, their annotations will be available.
-
-There are three main authentication modes: null, session, or oauth.  
-In the configuration file specify the authentication mode by setting
-`server / authentication / type`.
-
-#### null
-
-Authentication is disabled: user annotations cannot be enabled.
-
-#### session
-
-The user is associated with their client browser session. This approach is
-simple to setup, but not recommended for hosted cellxgene, since the user will not have access to
-their annotations when running from a different browser, or if their cookies get cleared.
-
-#### oauth
-
-A user logs into cellxgene using an identity provider (like Google), or logs in using
-an email/password. This is the best option, but requires making use of an oauth service and
-additional configuration of the cellxgene server.
-
-To see what this looks like, please look at https://cellxgene.cziscience.com/,
-and view one of the cellxgene datasets.
-For this server, Auth0 (auth0.com) is used for authentication, but there are other options.
-There are good sources of documentation online that describe how to use one of these
-services.
-
-The `params_oauth` section in the configuration file describes characteristics of the
-authentication service, like "client_id" and "client_secret".  
-For security, the client_secret needs to be protected. One option is to
-store it in the AWS Secrets Manager.
-
-### User Annotations
-
-User annotations can be configured in the configuration file both generally and for a specific data route. The annotations feature is only available when Authorization is enabled. 
-To enable Annotations, it is necessary to create a relational database and add the database uri (typically `postgresql://[user[:password]@][netloc][:port][/dbname]`) to the secrets manager under `DB_URI`. 
-The hosted version of cellxgene runs on AWS's [Aurora PostgreSQL](https://docs.aws.amazon.com/AmazonRDS/latest/AuroraUserGuide/Aurora.AuroraPostgreSQL.html) but any sqlalchemy compatible relational database should work. 
-Once the database is set up apply the cellxgene schema to your database by running the following inside the cellxgene repo
-`PROJECT_ROOT=$(git rev-parse --show-toplevel)`
-`python3`
-Inside the python console
-`from sqlalchemy import create_engine`
-`from server.db.cellxgene_orm import Base`
-`uri = "[DB_URI]”`
-`engine = create_engine(uri)`
-
- Base.metadata.create_all(engine)`
-
-To check the schema was properly applied (or just to check what is in the database at any point)
-ssh into your database. For a postgres database this entails running:  
-`psql [DB_URI]`
-
-You'll also need to update your IAM policies to allow the instance to write to the s3 bucket.

backend/czi_hosted/eb/check_config.py

@@ -1,38 +0,0 @@
-import sys
-import argparse
-import yaml
-
-from backend.czi_hosted.common.config.app_config import AppConfig
-
-def main():
-    parser = argparse.ArgumentParser("A script to check hosted configuration files")
-    parser.add_argument("config_file", help="the configuration file")
-    parser.add_argument(
-        "-s",
-        "--show",
-        default=False,
-        action="store_true",
-        help="print the configuration. NOTE: this may print secret values to stdout",
-    )
-
-    args = parser.parse_args()
-
-    app_config = AppConfig()
-    try:
-        app_config.update_from_config_file(args.config_file)
-        app_config.complete_config()
-    except Exception as e:
-        print(f"Error: {str(e)}")
-        print("FAIL:", args.config_file)
-        sys.exit(1)
-
-    if args.show:
-        yaml_config = app_config.config_to_dict()
-        yaml.dump(yaml_config, sys.stdout)
-
-    print("PASS:", args.config_file)
-    sys.exit(0)
-
-
-if __name__ == "__main__":
-    main()

backend/czi_hosted/requirements-dev.txt

@@ -1,12 +0,0 @@
-Authlib>=0.14.3
-black
-bumpversion>=0.5
-codecov>=2.0.15
-parameterized>=0.7.0
-psycopg2-binary>=2.8.5
-pytest>=3.6.3
-python-jose>=3.2.0
-twine>=1.12.1
--r requirements.txt
--r requirements-prepare.txt
-rsa>=4.7 # not directly required, pinned by Snyk to avoid a vulnerability

backend/czi_hosted/requirements-prepare.txt

@@ -1,4 +0,0 @@
-python-igraph
-louvain>=0.6
-scanpy
-umap-learn<0.5.0 # The pinned version scanpy is not compatible with latest umap-learn

backend/czi_hosted/requirements.txt

@@ -1,24 +0,0 @@
-anndata>=0.7.6 # we need to_memory(), added in 0.7.6
-boto3>=1.12.18
-click>=7.1.2
-Flask>=1.0.2,<2.0.0 # Flask 2.0 is not compatible with the latest version of Flask-RESTful (0.3.8)
-Flask-Compress>=1.4.0
-Flask-Cors>=3.0.9  # CVE-2020-25032
-Flask-RESTful>=0.3.6
-flask-server-timing>=0.1.2
-flask-talisman>=0.7.0
-flatbuffers>=1.11.0,<2.0.0 # cellxgene is not compatible with 2.0.0. Requires migration
-flatten-dict>=0.2.0
-fsspec>=0.4.4,<0.8.0
-gunicorn>=20.0.4
-h5py>=3.0.0
-numba>=0.51.2
-numpy>=1.17.5
-packaging>=20.0
-pandas>=1.0,!=1.1  # pandas 1.1 breaks tests, https://github.com/pandas-dev/pandas/issues/35446
-PyYAML>=5.4  # CVE-2020-14343
-scipy>=1.4
-requests>=2.22.0
-tiledb>=0.5.9,>=0.6.2,!=0.7.2, !=0.8.6
-s3fs==0.4.2
-sqlalchemy>=1.3.18

backend/server/Makefile

@@ -1,26 +0,0 @@
-include ../../common.mk
-
-.PHONY: clean
-clean:
-	rm -f common/web/templates/index.html
-	rm -rf common/web/static
-	rm -f common/web/csp-hashes.json
-
-.PHONY: unit-test
-unit-test:
-	PYTHONWARNINGS=ignore:ResourceWarning coverage run \
-		--source=app,auth,cli,common,compute,converters,data_anndata,data_common \
-		--omit=.coverage,venv \
-		-m unittest discover \
-		--start-directory ../test/test_server/unit \
-		--top-level-directory ../../ \
-		--verbose; test_result=$$?; \
-	exit $$test_result \
-
-.PHONY: test-annotations-performance
-test-annotations-performance:
-	python ../test/test_server/performance/performance_test_annotations_backend.py
-
-.PHONY: test-annotations-scale
-test-annotations-scale:
-	locust -f ../test/test_server/performance/scale_test_annotations.py --headless -u 30 -r 10 --host https://api.cellxgene.dev.single-cell.czi.technology/cellxgene/e/ --run-time 5m 2>&1 | tee locust_dev_stats.txt

backend/server/app/app.py

@@ -1,296 +0,0 @@
-import datetime
-import logging
-from functools import wraps
-from http import HTTPStatus
-
-from flask import (
-    Flask,
-    current_app,
-    make_response,
-    render_template,
-    Blueprint,
-    request,
-    send_from_directory,
-)
-from flask_restful import Api, Resource
-
-import backend.server.common.rest as common_rest
-from backend.common.errors import DatasetAccessError, RequestException
-from backend.server.common.health import health_check
-from backend.common.utils.utils import Float32JSONEncoder
-
-webbp = Blueprint("webapp", "backend.server.common.web", template_folder="templates")
-
-ONE_WEEK = 7 * 24 * 60 * 60
-
-
-def _cache_control(always, **cache_kwargs):
-    """
-    Used to easily manage cache control headers on responses.
-    See Werkzeug for attributes that can be set, eg, no_cache, private, max_age, etc.
-    https://werkzeug.palletsprojects.com/en/1.0.x/datastructures/#werkzeug.datastructures.ResponseCacheControl
-    """
-
-    def inner_cache_control(f):
-        @wraps(f)
-        def wrapper(*args, **kwargs):
-            response = make_response(f(*args, **kwargs))
-            if not always and not current_app.app_config.server_config.app__generate_cache_control_headers:
-                return response
-            if response.status_code >= 400:
-                return response
-            for k, v in cache_kwargs.items():
-                setattr(response.cache_control, k, v)
-            return response
-
-        return wrapper
-
-    return inner_cache_control
-
-
-def cache_control(**cache_kwargs):
-    """ config driven """
-    return _cache_control(False, **cache_kwargs)
-
-
-def cache_control_always(**cache_kwargs):
-    """ always generate headers, regardless of the config """
-    return _cache_control(True, **cache_kwargs)
-
-
-@webbp.route("/", methods=["GET"])
-def dataset_index():
-    app_config = current_app.app_config
-
-    dataset_config = app_config.get_dataset_config()
-    scripts = dataset_config.app__scripts
-    inline_scripts = dataset_config.app__inline_scripts
-
-    try:
-        args = {"SCRIPTS": scripts, "INLINE_SCRIPTS": inline_scripts}
-        return render_template("index.html", **args)
-
-    except DatasetAccessError as e:
-        return common_rest.abort_and_log(
-            e.status_code, f"Invalid dataset: {e.message}", loglevel=logging.INFO, include_exc_info=True
-        )
-
-
-@webbp.errorhandler(RequestException)
-def handle_request_exception(error):
-    return common_rest.abort_and_log(error.status_code, error.message, loglevel=logging.INFO, include_exc_info=True)
-
-
-def requires_authentication(func):
-    @wraps(func)
-    def wrapped_function(self, *args, **kwargs):
-        auth = current_app.auth
-        if auth.is_user_authenticated():
-            return func(self, *args, **kwargs)
-        else:
-            return make_response("not authenticated", HTTPStatus.UNAUTHORIZED)
-
-    return wrapped_function
-
-
-def rest_get_data_adaptor(func):
-    @wraps(func)
-    def wrapped_function(self):
-        try:
-            return func(self, current_app.data_adaptor)
-        except DatasetAccessError as e:
-            return common_rest.abort_and_log(
-                e.status_code, f"Invalid dataset: {e.message}", loglevel=logging.INFO, include_exc_info=True
-            )
-
-    return wrapped_function
-
-
-class HealthAPI(Resource):
-    @cache_control_always(no_store=True)
-    def get(self):
-        config = current_app.app_config
-        return health_check(config)
-
-
-class SchemaAPI(Resource):
-    # TODO @mdunitz separate dataset schema and user schema
-    @cache_control(public=True, max_age=ONE_WEEK)
-    @rest_get_data_adaptor
-    def get(self, data_adaptor):
-        return common_rest.schema_get(data_adaptor)
-
-
-class ConfigAPI(Resource):
-    @cache_control(public=True, max_age=ONE_WEEK)
-    @rest_get_data_adaptor
-    def get(self, data_adaptor):
-        return common_rest.config_get(current_app.app_config, data_adaptor)
-
-
-class UserInfoAPI(Resource):
-    @cache_control_always(no_store=True)
-    @rest_get_data_adaptor
-    def get(self, data_adaptor):
-        return common_rest.userinfo_get(current_app.app_config, data_adaptor)
-
-
-class AnnotationsObsAPI(Resource):
-    @cache_control(public=True, max_age=ONE_WEEK)
-    @rest_get_data_adaptor
-    def get(self, data_adaptor):
-        return common_rest.annotations_obs_get(request, data_adaptor)
-
-    @requires_authentication
-    @cache_control(no_store=True)
-    @rest_get_data_adaptor
-    def put(self, data_adaptor):
-        return common_rest.annotations_obs_put(request, data_adaptor)
-
-
-class AnnotationsVarAPI(Resource):
-    @cache_control(public=True, max_age=ONE_WEEK)
-    @rest_get_data_adaptor
-    def get(self, data_adaptor):
-        return common_rest.annotations_var_get(request, data_adaptor)
-
-
-class DataVarAPI(Resource):
-    @cache_control(no_store=True)
-    @rest_get_data_adaptor
-    def put(self, data_adaptor):
-        return common_rest.data_var_put(request, data_adaptor)
-
-    @cache_control(public=True, max_age=ONE_WEEK)
-    @rest_get_data_adaptor
-    def get(self, data_adaptor):
-        return common_rest.data_var_get(request, data_adaptor)
-
-
-class ColorsAPI(Resource):
-    @cache_control(public=True, max_age=ONE_WEEK)
-    @rest_get_data_adaptor
-    def get(self, data_adaptor):
-        return common_rest.colors_get(data_adaptor)
-
-
-class DiffExpObsAPI(Resource):
-    @cache_control(no_store=True)
-    @rest_get_data_adaptor
-    def post(self, data_adaptor):
-        return common_rest.diffexp_obs_post(request, data_adaptor)
-
-
-class LayoutObsAPI(Resource):
-    @cache_control(public=True, max_age=ONE_WEEK)
-    @rest_get_data_adaptor
-    def get(self, data_adaptor):
-        return common_rest.layout_obs_get(request, data_adaptor)
-
-
-class GenesetsAPI(Resource):
-    @cache_control(public=True, max_age=ONE_WEEK)
-    @rest_get_data_adaptor
-    def get(self, data_adaptor):
-        return common_rest.genesets_get(request, data_adaptor)
-
-    @requires_authentication
-    @cache_control(no_store=True)
-    @rest_get_data_adaptor
-    def put(self, data_adaptor):
-        return common_rest.genesets_put(request, data_adaptor)
-
-
-class SummarizeVarAPI(Resource):
-    @rest_get_data_adaptor
-    @cache_control(public=True, max_age=ONE_WEEK)
-    def get(self, data_adaptor):
-        return common_rest.summarize_var_get(request, data_adaptor)
-
-    @rest_get_data_adaptor
-    @cache_control(no_store=True)
-    def post(self, data_adaptor):
-        return common_rest.summarize_var_post(request, data_adaptor)
-
-
-def get_api_base_resources(bp_base):
-    """Add resources that are accessed from the api url"""
-    api = Api(bp_base)
-
-    # Diagnostics routes
-    api.add_resource(HealthAPI, "/health")
-    return api
-
-
-def get_api_dataroot_resources(bp_dataroot):
-    """Add resources that refer to a dataset"""
-    api = Api(bp_dataroot)
-
-    def add_resource(resource, url):
-        """convenience function to make the outer function less verbose"""
-        api.add_resource(resource, url)
-
-    # Initialization routes
-    add_resource(SchemaAPI, "/schema")
-    add_resource(ConfigAPI, "/config")
-    add_resource(UserInfoAPI, "/userinfo")
-    # Data routes
-    add_resource(AnnotationsObsAPI, "/annotations/obs")
-    add_resource(AnnotationsVarAPI, "/annotations/var")
-    add_resource(DataVarAPI, "/data/var")
-    add_resource(GenesetsAPI, "/genesets")
-    add_resource(SummarizeVarAPI, "/summarize/var")
-    # Display routes
-    add_resource(ColorsAPI, "/colors")
-    # Computation routes
-    add_resource(DiffExpObsAPI, "/diffexp/obs")
-    add_resource(LayoutObsAPI, "/layout/obs")
-    return api
-
-
-class Server:
-    @staticmethod
-    def _before_adding_routes(app, app_config):
-        """ will be called before routes are added, during __init__.  Subclass protocol """
-        pass
-
-    def __init__(self, app_config):
-        self.app = Flask(__name__, static_folder=None)
-        self._before_adding_routes(self.app, app_config)
-        self.app.json_encoder = Float32JSONEncoder
-        server_config = app_config.server_config
-
-        # enable session data
-        self.app.permanent_session_lifetime = datetime.timedelta(days=50 * 365)
-
-        # Config
-        secret_key = server_config.app__flask_secret_key
-        self.app.config.update(SECRET_KEY=secret_key)
-
-        self.app.register_blueprint(webbp)
-
-        api_version = "/api/v0.2"
-        api_path = "/"
-
-        bp_base = Blueprint("bp_base", __name__, url_prefix=api_path)
-        base_resources = get_api_base_resources(bp_base)
-        self.app.register_blueprint(base_resources.blueprint)
-
-        bp_api = Blueprint("api", __name__, url_prefix=f"{api_path}{api_version}")
-        resources = get_api_dataroot_resources(bp_api)
-        self.app.register_blueprint(resources.blueprint)
-        self.app.add_url_rule(
-            "/static/<path:filename>",
-            "static_assets",
-            view_func=lambda filename: send_from_directory("../common/web/static", filename),
-            methods=["GET"],
-        )
-
-        self.app.data_adaptor = server_config.data_adaptor
-        self.app.app_config = app_config
-
-        auth = server_config.auth
-        self.app.auth = auth
-        if auth.requires_client_login():
-            auth.add_url_rules(self.app)
-        auth.complete_setup(self.app)

backend/server/auth/__init__.py

@@ -1,5 +0,0 @@
-# import the built in auth types so they can be registered
-
-import backend.server.auth.auth_none  # noqa: F401
-import backend.server.auth.auth_test  # noqa: F401
-import backend.server.auth.auth_session  # noqa: F401

backend/server/auth/auth_test.py

@@ -1,73 +0,0 @@
-from backend.server.auth.auth import AuthTypeClientBase, AuthTypeFactory
-from flask import session, request, redirect
-
-
-class AuthTypeTest(AuthTypeClientBase):
-    """An authentication type for testing client based logins.  When the login route is accessed
-    the user is automatically logged in with a default or configured username"""
-
-    # key in session token with userid and username
-    CXGUID = "cxguid_test"
-    CXGUNAME = "cxguname_test"
-    CXGUEMAIL = "cxguemail_test"
-    CXGUPICTURE = "cxgupicture_test"
-
-    def __init__(self, app_config):
-        super().__init__()
-        self.user_name = "test_account"
-        self.user_id = "id0001"
-        self.user_email = "test_account@test.com"
-        self.user_picture = None
-
-    def is_valid_authentication_type(self):
-        return True
-
-    def requires_client_login(self):
-        return True
-
-    def add_url_rules(self, app):
-        app.add_url_rule("/login", "login", self.login, methods=["GET"])
-        app.add_url_rule("/logout", "logout", self.logout, methods=["GET"])
-
-    def complete_setup(self, app):
-        pass
-
-    def is_user_authenticated(self):
-        return self.CXGUID in session
-
-    def get_user_id(self):
-        return session.get(self.CXGUID)
-
-    def get_user_name(self):
-        return session.get(self.CXGUNAME)
-
-    def get_user_email(self):
-        return session.get(self.CXGUEMAIL)
-
-    def get_user_picture(self):
-        return session.get(self.CXGUPICTURE)
-
-    def login(self):
-        args = request.args
-        return_to = args.get("dataset", "/")
-        session[self.CXGUID] = args.get("userid", self.user_id)
-        session[self.CXGUNAME] = args.get("username", self.user_name)
-        session[self.CXGUEMAIL] = args.get("email", self.user_email)
-        session[self.CXGUPICTURE] = args.get("picture", self.user_picture)
-        return redirect(return_to)
-
-    def logout(self):
-        session.clear()
-        return_to = request.args.get("dataset", "/")
-        return redirect(return_to)
-
-    def get_login_url(self, data_adaptor):
-        """Return the url for the login route"""
-        return "/login"
-
-    def get_logout_url(self, data_adaptor):
-        """Return the url for the logout route"""
-        return "/logout"
-
-
-AuthTypeFactory.register("test", AuthTypeTest)

backend/server/cli/cli.py

@@ -1,33 +0,0 @@
-import click
-
-from .launch import launch
-from .prepare import prepare
-from .upgrade import log_upgrade_check
-from .schema import schema_cli
-from .. import __version__
-
-
-@click.group(
-    name="cellxgene",
-    subcommand_metavar="COMMAND <args>",
-    options_metavar="<options>",
-    context_settings=dict(max_content_width=85, help_option_names=["-h", "--help"]),
-)
-@click.help_option("--help", "-h", help="Show this message and exit.")
-@click.version_option(
-    version=__version__,
-    prog_name="cellxgene",
-    message="[%(prog)s] Version %(version)s",
-    help="Show the software version and exit.",
-)
-@click.option(
-    "--upgrade-check/--no-upgrade-check", default=True, show_default=True, help="Check for release upgrades on start.",
-)
-def cli(upgrade_check):
-    if upgrade_check:
-        log_upgrade_check()
-
-
-cli.add_command(launch)
-cli.add_command(prepare)
-cli.add_command(schema_cli)

backend/server/cli/launch.py

@@ -1,449 +0,0 @@
-import errno
-import functools
-import logging
-import sys
-import webbrowser
-import os
-import click
-from flask_compress import Compress
-from flask_cors import CORS
-
-from backend.server.default_config import default_config
-from backend.server.app.app import Server
-from backend.server.common.config.app_config import AppConfig
-from backend.common.errors import DatasetAccessError, ConfigurationError
-from backend.common.utils.utils import sort_options
-
-DEFAULT_CONFIG = AppConfig()
-
-
-def annotation_args(func):
-    @click.option(
-        "--disable-annotations",
-        is_flag=True,
-        default=not DEFAULT_CONFIG.dataset_config.user_annotations__enable,
-        show_default=True,
-        help="Disable user annotation of data.",
-    )
-    @click.option(
-        "--annotations-file",
-        default=DEFAULT_CONFIG.dataset_config.user_annotations__local_file_csv__file,
-        show_default=True,
-        multiple=False,
-        metavar="<path>",
-        help="CSV file to initialize editing of existing annotations; will be altered in-place. "
-        "Incompatible with --user-generated-data-dir.",
-    )
-    @click.option(
-        "--user-generated-data-dir",
-        "--annotations-dir",
-        default=DEFAULT_CONFIG.dataset_config.user_annotations__local_file_csv__directory,
-        show_default=False,
-        multiple=False,
-        metavar="<directory path>",
-        help="Directory of where to save output annotations; filename will be specified in the application. "
-        "Incompatible with --annotations-file and --gene-sets-file.",
-    )
-    @click.option(
-        "--disable-gene-sets-save",
-        is_flag=True,
-        default=DEFAULT_CONFIG.dataset_config.user_annotations__gene_sets__readonly,
-        show_default=False,
-        help="Disable saving gene sets. If disabled, users will be able to make changes to gene sets but all "
-        "changes will be lost on browser refresh.",
-    )
-    @click.option(
-        "--gene-sets-file",
-        default=DEFAULT_CONFIG.dataset_config.user_annotations__local_file_csv__gene_sets_file,
-        show_default=True,
-        multiple=False,
-        metavar="<path>",
-        help="CSV file to initialize editing of gene sets; will be altered in-place. Incompatible with "
-        "--user-generated-data-dir.",
-    )
-    @functools.wraps(func)
-    def wrapper(*args, **kwargs):
-        return func(*args, **kwargs)
-
-    return wrapper
-
-
-def config_args(func):
-    @click.option(
-        "--max-category-items",
-        default=DEFAULT_CONFIG.dataset_config.presentation__max_categories,
-        metavar="<integer>",
-        show_default=True,
-        help="Will not display categories with more distinct values than specified.",
-    )
-    @click.option(
-        "--disable-custom-colors",
-        is_flag=True,
-        default=False,
-        show_default=False,
-        help="Disable user-defined category-label colors drawn from source data file.",
-    )
-    @click.option(
-        "--diffexp-lfc-cutoff",
-        "-de",
-        default=DEFAULT_CONFIG.dataset_config.diffexp__lfc_cutoff,
-        show_default=True,
-        metavar="<float>",
-        help="Minimum log fold change threshold for differential expression.",
-    )
-    @click.option(
-        "--disable-diffexp",
-        is_flag=True,
-        default=not DEFAULT_CONFIG.dataset_config.diffexp__enable,
-        show_default=False,
-        help="Disable on-demand differential expression.",
-    )
-    @click.option(
-        "--embedding",
-        "-e",
-        default=DEFAULT_CONFIG.dataset_config.embeddings__names,
-        multiple=True,
-        show_default=False,
-        metavar="<text>",
-        help="Embedding name, eg, 'umap'. Repeat option for multiple embeddings. Defaults to all.",
-    )
-    @functools.wraps(func)
-    def wrapper(*args, **kwargs):
-        return func(*args, **kwargs)
-
-    return wrapper
-
-
-def dataset_args(func):
-    @click.option(
-        "--obs-names",
-        "-obs",
-        default=DEFAULT_CONFIG.server_config.single_dataset__obs_names,
-        metavar="<text>",
-        help="Name of annotation field to use for observations. If not specified cellxgene will use the the obs index.",
-    )
-    @click.option(
-        "--var-names",
-        "-var",
-        default=DEFAULT_CONFIG.server_config.single_dataset__var_names,
-        metavar="<text>",
-        help="Name of annotation to use for variables. If not specified cellxgene will use the the var index.",
-    )
-    @click.option(
-        "--backed",
-        "-b",
-        is_flag=True,
-        default=DEFAULT_CONFIG.server_config.adaptor__anndata_adaptor__backed,
-        show_default=False,
-        help="Load anndata in file-backed mode. " "This may save memory, but may result in slower overall performance.",
-    )
-    @click.option(
-        "--title",
-        "-t",
-        default=DEFAULT_CONFIG.server_config.single_dataset__title,
-        metavar="<text>",
-        help="Title to display. If omitted will use file name.",
-    )
-    @click.option(
-        "--about",
-        default=DEFAULT_CONFIG.server_config.single_dataset__about,
-        metavar="<URL>",
-        help="URL providing more information about the dataset (hint: must be a fully specified absolute URL).",
-    )
-    @click.option(
-        "--X-approximate-distribution",
-        default=DEFAULT_CONFIG.dataset_config.X_approximate_distribution,
-        show_default=True,
-        type=click.Choice(["auto", "normal", "count"], case_sensitive=False),
-        help="Specify the approximate distribution of X matrix values. 'auto' will use a heuristic "
-        "to determine the approximate distribution.  Mode 'auto' is incompatible with --backed.",
-    )
-    @functools.wraps(func)
-    def wrapper(*args, **kwargs):
-        return func(*args, **kwargs)
-
-    return wrapper
-
-
-def server_args(func):
-    @click.option(
-        "--debug",
-        "-d",
-        is_flag=True,
-        default=DEFAULT_CONFIG.server_config.app__debug,
-        show_default=True,
-        help="Run in debug mode. This is helpful for cellxgene developers, "
-        "or when you want more information about an error condition.",
-    )
-    @click.option(
-        "--verbose",
-        "-v",
-        is_flag=True,
-        default=DEFAULT_CONFIG.server_config.app__verbose,
-        show_default=True,
-        help="Provide verbose output, including warnings and all server requests.",
-    )
-    @click.option(
-        "--port",
-        "-p",
-        metavar="<port>",
-        default=DEFAULT_CONFIG.server_config.app__port,
-        type=int,
-        show_default=True,
-        help="Port to run server on. If not specified cellxgene will find an available port.",
-    )
-    @click.option(
-        "--host",
-        metavar="<IP address>",
-        default=DEFAULT_CONFIG.server_config.app__host,
-        show_default=False,
-        help="Host IP address. By default cellxgene will use localhost (e.g. 127.0.0.1).",
-    )
-    @click.option(
-        "--scripts",
-        "-s",
-        default=DEFAULT_CONFIG.dataset_config.app__scripts,
-        multiple=True,
-        metavar="<text>",
-        help="Additional script files to include in HTML page. If not specified, "
-        "no additional script files will be included.",
-        show_default=False,
-    )
-    @functools.wraps(func)
-    def wrapper(*args, **kwargs):
-        return func(*args, **kwargs)
-
-    return wrapper
-
-
-def launch_args(func):
-    @annotation_args
-    @config_args
-    @dataset_args
-    @server_args
-    @click.argument("datapath", required=False, metavar="<path to data file>")
-    @click.option(
-        "--open",
-        "-o",
-        "open_browser",
-        is_flag=True,
-        default=DEFAULT_CONFIG.server_config.app__open_browser,
-        show_default=True,
-        help="Open web browser after launch.",
-    )
-    @click.option(
-        "--config-file",
-        "-c",
-        "config_file",
-        default=None,
-        show_default=True,
-        help="Location to yaml file with configuration settings",
-    )
-    @click.option(
-        "--dump-default-config",
-        "dump_default_config",
-        is_flag=True,
-        default=False,
-        show_default=True,
-        help="Print default configuration settings and exit",
-    )
-    @click.help_option("--help", "-h", help="Show this message and exit.")
-    @functools.wraps(func)
-    def wrapper(*args, **kwargs):
-        return func(*args, **kwargs)
-
-    return wrapper
-
-
-def handle_scripts(scripts):
-    if scripts:
-        click.echo(
-            r"""
-    / / /\ \ \__ _ _ __ _ __ (_)_ __   __ _
-    \ \/  \/ / _` | '__| '_ \| | '_ \ / _` |
-     \  /\  / (_| | |  | | | | | | | | (_| |
-      \/  \/ \__,_|_|  |_| |_|_|_| |_|\__, |
-                                      |___/
-    The --scripts flag is intended for developers to include google analytics etc. You could be opening yourself to a
-    security risk by including the --scripts flag. Make sure you trust the scripts that you are including.
-            """
-        )
-        scripts_pretty = ", ".join(scripts)
-        click.confirm(f"Are you sure you want to inject these scripts: {scripts_pretty}?", abort=True)
-
-
-class CliLaunchServer(Server):
-    """
-    the CLI runs a local web server, and needs to enable a few more features.
-    """
-
-    def __init__(self, app_config):
-        super().__init__(app_config)
-
-    @staticmethod
-    def _before_adding_routes(app, app_config):
-        app.config["COMPRESS_MIMETYPES"] = [
-            "text/html",
-            "text/css",
-            "text/xml",
-            "application/json",
-            "application/javascript",
-            "application/octet-stream",
-        ]
-        Compress(app)
-        if app_config.server_config.app__debug:
-            CORS(app, supports_credentials=True)
-
-
-@sort_options
-@click.command(
-    short_help="Launch the cellxgene data viewer. " "Run `cellxgene launch --help` for more information.",
-    options_metavar="<options>",
-)
-@launch_args
-def launch(
-    datapath,
-    verbose,
-    debug,
-    open_browser,
-    port,
-    host,
-    embedding,
-    obs_names,
-    var_names,
-    max_category_items,
-    disable_custom_colors,
-    diffexp_lfc_cutoff,
-    title,
-    scripts,
-    about,
-    disable_annotations,
-    annotations_file,
-    user_generated_data_dir,
-    gene_sets_file,
-    disable_gene_sets_save,
-    backed,
-    disable_diffexp,
-    config_file,
-    dump_default_config,
-    x_approximate_distribution,
-):
-    """Launch the cellxgene data viewer.
-    This web app lets you explore single-cell expression data.
-    Data must be in a format that cellxgene expects.
-    Read the "getting started" guide to learn more:
-    https://chanzuckerberg.github.io/cellxgene/getting-started.html
-
-    Examples:
-
-    > cellxgene launch example-dataset/pbmc3k.h5ad --title pbmc3k
-
-    > cellxgene launch <your data file> --title <your title>
-
-    > cellxgene launch <url>"""
-
-    if dump_default_config:
-        print(default_config)
-        sys.exit(0)
-
-    # Startup message
-    click.echo("[cellxgene] Starting the CLI...")
-
-    # app config
-    app_config = AppConfig()
-    server_config = app_config.server_config
-
-    try:
-        if config_file:
-            app_config.update_from_config_file(config_file)
-
-        # Determine which config options were give on the command line.
-        # Those will override the ones provided in the config file (if provided).
-        cli_config = AppConfig()
-        cli_config.update_server_config(
-            app__verbose=verbose,
-            app__debug=debug,
-            app__host=host,
-            app__port=port,
-            app__open_browser=open_browser,
-            single_dataset__datapath=datapath,
-            single_dataset__title=title,
-            single_dataset__about=about,
-            single_dataset__obs_names=obs_names,
-            single_dataset__var_names=var_names,
-            adaptor__anndata_adaptor__backed=backed,
-        )
-        cli_config.update_dataset_config(
-            app__scripts=scripts,
-            user_annotations__enable=not disable_annotations,
-            user_annotations__local_file_csv__file=annotations_file,
-            user_annotations__local_file_csv__directory=user_generated_data_dir,
-            user_annotations__local_file_csv__gene_sets_file=gene_sets_file,
-            user_annotations__gene_sets__readonly=disable_gene_sets_save,
-            presentation__max_categories=max_category_items,
-            presentation__custom_colors=not disable_custom_colors,
-            embeddings__names=embedding,
-            diffexp__enable=not disable_diffexp,
-            diffexp__lfc_cutoff=diffexp_lfc_cutoff,
-            X_approximate_distribution=x_approximate_distribution,
-        )
-
-        diff = cli_config.server_config.changes_from_default()
-        changes = {key: val for key, val, _ in diff}
-        app_config.update_server_config(**changes)
-
-        diff = cli_config.dataset_config.changes_from_default()
-        changes = {key: val for key, val, _ in diff}
-        app_config.update_dataset_config(**changes)
-
-        # process the configuration
-        #  any errors will be thrown as an exception.
-        #  any info messages will be passed to the messagefn function.
-
-        def messagefn(message):
-            click.echo("[cellxgene] " + message)
-
-        # Use a default secret if one is not provided
-        if not server_config.app__flask_secret_key:
-            app_config.update_server_config(app__flask_secret_key="SparkleAndShine")
-
-        app_config.complete_config(messagefn)
-
-    except (ConfigurationError, DatasetAccessError) as e:
-        raise click.ClickException(e)
-
-    handle_scripts(scripts)
-
-    # create the server
-    server = CliLaunchServer(app_config)
-
-    if not server_config.app__verbose:
-        log = logging.getLogger("werkzeug")
-        log.setLevel(logging.ERROR)
-
-    cellxgene_url = f"http://{app_config.server_config.app__host}:{app_config.server_config.app__port}"
-    if server_config.app__open_browser:
-        click.echo(f"[cellxgene] Launching! Opening your browser to {cellxgene_url} now.")
-        webbrowser.open(cellxgene_url)
-    else:
-        click.echo(f"[cellxgene] Launching! Please go to {cellxgene_url} in your browser.")
-
-    click.echo("[cellxgene] Type CTRL-C at any time to exit.")
-
-    if not server_config.app__verbose:
-        f = open(os.devnull, "w")
-        sys.stdout = f
-
-    try:
-        server.app.run(
-            host=server_config.app__host,
-            debug=server_config.app__debug,
-            port=server_config.app__port,
-            threaded=not server_config.app__debug,
-            use_debugger=False,
-            use_reloader=False,
-        )
-    except OSError as e:
-        if e.errno == errno.EADDRINUSE:
-            raise click.ClickException("Port is in use, please specify an open port using the --port flag.") from e
-        raise

backend/server/cli/prepare.py

@@ -1,274 +0,0 @@
-from os.path import expanduser, isdir, isfile, sep, splitext
-
-import click
-import pandas as pd
-from numpy import ndarray, unique
-from scipy.sparse.csc import csc_matrix
-
-from backend.common.utils.utils import sort_options
-
-
-@sort_options
-@click.command(
-    short_help="Preprocess data for use with cellxgene. " "Run `cellxgene prepare --help` for more information.",
-    options_metavar="<options>",
-)
-@click.argument("data", nargs=1, metavar="<path to data file>", required=True)
-@click.option(
-    "--embedding",
-    "-e",
-    default=["umap", "tsne"],
-    multiple=True,
-    type=click.Choice(["umap", "tsne"]),
-    help="Embedding algorithm(s). Repeat option for multiple embeddings.",
-    show_default=True,
-)
-@click.option(
-    "--recipe", "-r", default="none", type=click.Choice(["none", "seurat", "zheng17"]), show_default=True,
-)
-@click.option("--output", "-o", default="", help="Save a new file to filename.", metavar="<filename>")
-@click.option("--plotting", "-p", default=False, is_flag=True, help="Generate plots.", show_default=True)
-@click.option("--sparse", default=False, is_flag=True, help="Force sparsity.", show_default=True)
-@click.option("--overwrite", default=False, is_flag=True, help="Allow file overwriting.", show_default=True)
-@click.option("--set-obs-names", default="", help="Named field to set as index for obs.", metavar="<name>")
-@click.option("--set-var-names", default="", help="Named field to set as index for var.", metavar="<name>")
-@click.option(
-    "--skip-qc",
-    default=False,
-    is_flag=True,
-    help="Do not run quality control metrics. By default cellxgene runs them "
-    "(saved to adata.obs and adata.var; see scanpy.pp.calculate_qc_metrics for details).",
-)
-@click.option(
-    "--make-obs-names-unique/--no-make-obs-names-unique",
-    default=True,
-    help="Ensure obs index is unique.",
-    show_default=True,
-)
-@click.option(
-    "--make-var-names-unique/--no-make-var-names-unique",
-    default=True,
-    help="Ensure var index is unique.",
-    show_default=True,
-)
-@click.help_option("--help", "-h", help="Show this message and exit.")
-def prepare(
-    data,
-    embedding,
-    recipe,
-    output,
-    plotting,
-    sparse,
-    overwrite,
-    set_obs_names,
-    set_var_names,
-    skip_qc,
-    make_obs_names_unique,
-    make_var_names_unique,
-):
-    """
-    Preprocess data for use with cellxgene.
-    This tool runs a series of scanpy routines for preparing a dataset for use
-    with cellxgene. It loads data from different formats
-    (h5ad, loom, or a 10x directory), runs dimensionality reduction,
-    computes nearest neighbors, computes an embedding, performs clustering,
-    and saves the results. Includes additional options for naming annotations,
-    ensuring sparsity, and plotting results.
-    """
-
-    # collect slow imports here to make CLI startup more responsive
-    click.echo("[cellxgene] Starting CLI...")
-    try:
-        import matplotlib
-
-        matplotlib.use("Agg")
-        import scanpy as sc
-    except ImportError:
-        raise click.ClickException(
-            "[cellxgene] cellxgene prepare has not been installed. Please run `pip install 'cellxgene[prepare]'` "
-            "to install the necessary requirements."
-        )
-
-    # scanpy settings
-    sc.settings.verbosity = 0
-    sc.settings.autosave = True
-
-    # check args
-    if sparse and not recipe == "none":
-        raise click.UsageError("Cannot use a recipe when forcing sparsity")
-
-    output = expanduser(output)
-
-    if not output:
-        click.echo(
-            "Warning: No file will be saved, to save the results of cellxgene prepare include "
-            "--output <filename> to save output to a new file"
-        )
-    if isfile(output) and not overwrite:
-        raise click.UsageError(f"Cannot overwrite existing file {output}, try using the flag --overwrite")
-
-    def load_data(data):
-        if isfile(data):
-            name, extension = splitext(data)
-            if extension == ".h5ad":
-                adata = sc.read_h5ad(data)
-            elif extension == ".loom":
-                adata = sc.read_loom(data)
-            else:
-                raise click.FileError(data, hint="does not have a valid extension [.h5ad | .loom]")
-        elif isdir(data):
-            if not data.endswith(sep):
-                data += sep
-            adata = sc.read_10x_mtx(data)
-        else:
-            raise click.FileError(data, hint="not a valid file or path")
-
-        if not set_obs_names == "":
-            if set_obs_names not in adata.obs_keys():
-                raise click.UsageError(f"obs {set_obs_names} not found, options are: {adata.obs_keys()}")
-            adata.obs_names = adata.obs[set_obs_names]
-        if not set_var_names == "":
-            if set_var_names not in adata.var_keys():
-                raise click.UsageError(f"var {set_var_names} not found, options are: {adata.var_keys()}")
-            adata.var_names = adata.var[set_var_names]
-        if make_obs_names_unique:
-            adata.obs.index = make_index_unique(adata.obs.index)
-        if make_var_names_unique:
-            adata.var.index = make_index_unique(adata.var.index)
-        if not adata._obs.index.is_unique:
-            click.echo("Warning: obs index is not unique")
-        if not adata._var.index.is_unique:
-            click.echo("Warning: var index is not unique")
-        return adata
-
-    def calculate_qc_metrics(adata):
-        if not skip_qc:
-            sc.pp.calculate_qc_metrics(adata, inplace=True)
-        return adata
-
-    def make_sparse(adata):
-        if (type(adata.X) is ndarray) and sparse:
-            adata.X = csc_matrix(adata.X)
-
-    def run_recipe(adata):
-        if recipe == "seurat":
-            sc.pp.recipe_seurat(adata)
-        elif recipe == "zheng17":
-            sc.pp.recipe_zheng17(adata)
-        else:
-            sc.pp.filter_cells(adata, min_genes=5)
-            sc.pp.filter_genes(adata, min_cells=25)
-            if sparse:
-                sc.pp.scale(adata, zero_center=False)
-            else:
-                sc.pp.scale(adata)
-
-    def run_pca(adata):
-        if sparse:
-            sc.pp.pca(adata, svd_solver="arpack", zero_center=False)
-        else:
-            sc.pp.pca(adata, svd_solver="arpack")
-
-    def run_neighbors(adata):
-        sc.pp.neighbors(adata)
-
-    def run_louvain(adata):
-        sc.tl.louvain(adata)
-
-    def run_embedding(adata):
-        if len(unique(adata.obs["louvain"].values)) < 10:
-            palette = "tab10"
-        else:
-            palette = "tab20"
-
-        if "umap" in embedding:
-            sc.tl.umap(adata)
-            if plotting:
-                sc.pl.umap(adata, color="louvain", palette=palette, save="_louvain")
-
-        if "tsne" in embedding:
-            sc.tl.tsne(adata)
-            if plotting:
-                sc.pl.tsne(adata, color="louvain", palette=palette, save="_louvain")
-
-    def show_step(item):
-        if not skip_qc:
-            qc_name = "Calculating QC metrics"
-        else:
-            qc_name = "Skipping QC"
-        names = {
-            "calculate_qc_metrics": qc_name,
-            "make_sparse": "Ensuring sparsity",
-            "run_recipe": f'Running preprocessing recipe "{recipe}"',
-            "run_pca": "Running PCA",
-            "run_neighbors": "Calculating neighbors",
-            "run_louvain": "Calculating clusters",
-            "run_embedding": "Computing embedding",
-        }
-        if item is not None:
-            return names[item.__name__]
-
-    steps = [calculate_qc_metrics, make_sparse, run_recipe, run_pca, run_neighbors, run_louvain, run_embedding]
-
-    click.echo(f"[cellxgene] Loading data from {data}, please wait...")
-    adata = load_data(data)
-
-    click.echo("[cellxgene] Beginning preprocessing...")
-    with click.progressbar(steps, label="[cellxgene] Progress", show_eta=False, item_show_func=show_step) as bar:
-        for step in bar:
-            step(adata)
-
-    # saving
-    if not output == "":
-        click.echo(f"[cellxgene] Saving results to {output}...")
-        adata.write(output)
-
-    click.echo("[cellxgene] Success!")
-
-
-# TODO (mweiden): remove this once this issue is resolved https://github.com/theislab/anndata/issues/344
-# Note: tentative solution here https://github.com/theislab/anndata/pull/345
-def make_index_unique(index: pd.Index, join: str = "-"):
-    """
-    Makes the index unique by appending a number string to each duplicate index element: '1', '2', etc.
-
-    If a tentative name created by the algorithm already exists in the index, it tries the next integer in the sequence.
-
-    The first occurrence of a non-unique value is ignored.
-    Parameters
-    ----------
-    join
-         The connecting string between name and integer.
-    Examples
-    --------
-    >>> from anndata import AnnData
-    >>> adata1 = AnnData(np.ones((3, 2)), dict(obs_names=['a', 'b', 'c']))
-    >>> adata2 = AnnData(np.zeros((3, 2)), dict(obs_names=['d', 'b', 'b']))
-    >>> adata = adata1.concatenate(adata2)
-    >>> adata.obs_names
-    Index(['a', 'b', 'c', 'd', 'b', 'b'], dtype='object')
-    >>> adata.obs_names_make_unique()
-    >>> adata.obs_names
-    Index(['a', 'b', 'c', 'd', 'b-1', 'b-2'], dtype='object')
-    """
-    if index.is_unique:
-        return index
-    from collections import defaultdict
-
-    values = index.values
-    values_set = set(values)
-    indices_dup = index.duplicated(keep="first")
-    values_dup = values[indices_dup]
-    counter = defaultdict(lambda: 0)
-    for i, v in enumerate(values_dup):
-        while True:
-            counter[v] += 1
-            tentative_new_name = v + join + str(counter[v])
-            if tentative_new_name not in values_set:
-                values_set.add(tentative_new_name)
-                values_dup[i] = tentative_new_name
-                break
-
-    values[indices_dup] = values_dup
-    index = pd.Index(values)
-    return index

backend/server/cli/schema.py

@@ -1,72 +0,0 @@
-import click
-
-from backend.server.converters.schema import remix, validate
-
-
-@click.group(
-    name="schema",
-    subcommand_metavar="COMMAND <args>",
-    short_help="Apply and validate the cellxgene data integration schema to an h5ad file.",
-    context_settings=dict(max_content_width=85, help_option_names=["-h", "--help"]),
-)
-def schema_cli():
-    try:
-        import scanpy  # noqa: F401
-    except ImportError:
-        raise click.ClickException(
-            "[cellxgene] cellxgene schema requires scanpy"
-        )
-
-
-@click.command(
-    name="apply",
-    short_help="(experimental) Apply the cellxgene data integration schema to an h5ad.",
-    help="(experimental) Using a yaml file that describes schema values to insert or convert and in input "
-    "h5ad file, apply the schema changes and create a new, conforming h5ad.",
-)
-@click.option(
-    "--source-h5ad",
-    help="Input h5ad file.",
-    nargs=1,
-    required=True,
-    type=click.Path(exists=True, dir_okay=False),
-)
-@click.option(
-    "--remix-config",
-    help="Config yaml with information on how to apply the schema.",
-    nargs=1,
-    required=True,
-    type=click.Path(exists=True, dir_okay=False),
-)
-@click.option(
-    "--output-filename",
-    help="Filename for the new, schema-conforming h5ad file.",
-    required=True,
-    nargs=1
-)
-def schema_apply(source_h5ad, remix_config, output_filename):
-    remix.apply_schema(source_h5ad, remix_config, output_filename)
-
-
-@click.command(
-    name="validate",
-    short_help="(experimental) Check that an h5ad follows the cellxgene data integration schema.",
-)
-@click.argument(
-    "h5ad",
-    nargs=1,
-    type=click.Path(exists=True, dir_okay=False),
-)
-@click.option(
-    "--shallow",
-    help="When true, just check that the correct version information is present.",
-    default=False,
-    show_default=True,
-    is_flag=True,
-)
-def schema_validate(h5ad, shallow):
-    validate.validate(h5ad, shallow)
-
-
-schema_cli.add_command(schema_apply)
-schema_cli.add_command(schema_validate)

backend/server/common/annotations/annotations.py

@@ -1,90 +0,0 @@
-from abc import ABCMeta, abstractmethod
-
-from backend.common.errors import DisabledFeatureError
-from backend.common.utils.type_conversion_utils import get_schema_type_hint_of_array
-from backend.common.genesets import write_gene_sets_tidycsv
-
-
-class Annotations(metaclass=ABCMeta):
-    """baseclass for annotations and gene sets"""
-
-    def __init__(self, config={}):
-        self.config = config
-
-    def user_annotations_enabled(self):
-        return self.config.get("user-annotations", False)
-
-    def gene_sets_save_enabled(self):
-        return self.config.get("genesets-save", False)
-
-    def check_user_annotations_enabled(self):
-        if not self.user_annotations_enabled():
-            raise DisabledFeatureError("User annotations are disabled.")
-
-    def check_gene_sets_save_enabled(self):
-        if not self.gene_sets_save_enabled():
-            raise DisabledFeatureError("User gene sets save is disabled.")
-
-    def get_schema(self, data_adaptor):
-        schema = []
-        labels = self.read_labels(data_adaptor)
-        if labels is not None and not labels.empty:
-            for col in labels.columns:
-                col_schema = dict(name=col, writable=True)
-                col_schema.update(get_schema_type_hint_of_array(labels[col]))
-                schema.append(col_schema)
-
-        return schema
-
-    @abstractmethod
-    def set_collection(self, name):
-        """set or create a new annotation collection"""
-        pass
-
-    @abstractmethod
-    def read_labels(self, data_adaptor):
-        """Return the labels as a pandas.DataFrame"""
-        pass
-
-    @abstractmethod
-    def write_labels(self, df, data_adaptor):
-        """Write the labels (df) to a persistent storage such that it can later be read"""
-        pass
-
-    @abstractmethod
-    def read_gene_sets(self, data_adaptor):
-        """Return the gene sets from persistent storage"""
-        pass
-
-    @abstractmethod
-    def write_gene_sets(self, gs, data_adaptor):
-        """Write the gene sets (gs) to a persistent storage such that it can later be read"""
-        pass
-
-    @abstractmethod
-    def update_parameters(self, parameters, data_adaptor):
-        """Update configuration parameters that describe information about the annotations feature"""
-        pass
-
-    @staticmethod
-    def gene_sets_to_csv(genesets):
-        """
-        Convert the internal gene sets format (returned by read_gene_set) into
-        the simple Tidy CSV.
-        """
-        from io import StringIO
-
-        if isinstance(genesets, dict):
-            genesets = genesets.values()
-
-        with StringIO() as sio:
-            write_gene_sets_tidycsv(sio, genesets)
-            return sio.getvalue()
-
-    @staticmethod
-    def gene_sets_to_response(genesets):
-        """
-        Convert the internal gene sets format (returned by read_gene_set) into
-        the dict expected by the JSON REST API
-        """
-        return list(genesets.values())

backend/server/common/annotations/local_file_csv.py

@@ -1,281 +0,0 @@
-import base64
-import os
-import re
-import threading
-from datetime import datetime
-from hashlib import blake2b
-
-import pandas as pd
-from flask import session, has_request_context, current_app
-
-from backend.server import __version__ as cellxgene_version
-from backend.server.common.annotations.annotations import Annotations
-from backend.common.genesets import read_gene_sets_tidycsv
-from backend.common.errors import AnnotationsError, ObsoleteRequest
-from backend.common.utils.data_locator import DataLocator
-
-
-class AnnotationsLocalFile(Annotations):
-    CXG_ANNO_COLLECTION = "cxg_anno_collection"
-
-    def __init__(self, config, output_dir, label_output_file, gene_sets_output_file):
-        super().__init__(config)
-        self.output_dir = output_dir
-        self.label_output_file = label_output_file
-        self.gene_sets_output_file = gene_sets_output_file
-        # lock used to protect label file write ops
-        self.label_lock = threading.RLock()
-        self.gene_sets_lock = threading.RLock()
-
-        # cache the most recent cell labels/annotations.
-        self.last_label_fname = None
-        self.last_labels = None
-
-        # cache the most recent gene sets.
-        self.last_geneset_fname = None
-        self.last_geneset = None
-
-        # txn ID - used to de-dup geneset writes
-        self.last_geneset_tid = 0
-
-    def is_safe_collection_name(self, name):
-        """
-        return true if this is a safe collection name
-        this is ultra conservative. If we want to allow full legal file name syntax,
-        we could look at modules like `pathvalidate`
-        """
-        if name is None:
-            return False
-        return re.match(r"^[\w\-]+$", name) is not None
-
-    def set_collection(self, name):
-        session[self.CXG_ANNO_COLLECTION] = name
-        session.permanent = True
-
-    def get_collection(self):
-        if session is None:
-            return None
-        return session.get(self.CXG_ANNO_COLLECTION)
-
-    def read_labels(self, data_adaptor):
-        self.check_user_annotations_enabled()  # raises
-
-        if has_request_context():
-            if not current_app.auth.is_user_authenticated():
-                return pd.DataFrame()
-
-        fname = self._get_celllabels_filename(data_adaptor)
-        with self.label_lock:
-            if fname is not None and os.path.exists(fname) and os.path.getsize(fname) > 0:
-                # returned the cached labels if possible, otherwise read them from the file
-                if fname == self.last_label_fname:
-                    return self.last_labels
-                else:
-                    labels = pd.read_csv(
-                        fname, dtype="category", index_col=0, header=0, comment="#", keep_default_na=False
-                    )
-                    # update the cache
-                    self.last_label_fname = fname
-                    self.last_labels = labels
-                    return labels
-            else:
-                return pd.DataFrame()
-
-    def write_labels(self, df, data_adaptor):
-        self.check_user_annotations_enabled()  # raises
-
-        # update our internal state and save it.  Multi-threading often enabled,
-        # so treat this as a critical section.
-        with self.label_lock:
-            lastmod = data_adaptor.get_last_mod_time()
-            lastmodstr = "'unknown'" if lastmod is None else lastmod.isoformat(timespec="seconds")
-            header = (
-                f"# Annotations generated on {datetime.now().isoformat(timespec='seconds')} "
-                f"using cellxgene version {cellxgene_version}\n"
-                f"# Input data file was {data_adaptor.get_location()}, "
-                f"which was last modified on {lastmodstr}\n"
-            )
-
-            fname = self._get_celllabels_filename(data_adaptor)
-            self._backup(fname)
-            if not df.empty:
-                with open(fname, "w", newline="") as f:
-                    if header is not None:
-                        f.write(header)
-                    df.to_csv(f)
-            else:
-                open(fname, "w").close()
-
-            # update the cache
-            self.last_label_fname = fname
-            self.last_labels = df
-
-    def read_gene_sets(self, data_adaptor, context=None):
-        if has_request_context():
-            if not current_app.auth.is_user_authenticated():
-                return ({}, self.last_geneset_tid)
-
-        fname = self._get_genesets_filename(data_adaptor)
-        gene_sets = {}
-        tid = None
-        with self.gene_sets_lock:
-            tid = self.last_geneset_tid  # inside the critical section
-            if fname is not None and os.path.exists(fname) and os.path.getsize(fname) > 0:
-                # return the cached genesets if possible, otherwise read from file and validate them
-                if fname == self.last_geneset_fname:
-                    gene_sets = self.last_geneset
-                else:
-                    # read
-                    gene_sets = read_gene_sets_tidycsv(DataLocator(fname), context)
-
-                    # validate
-                    gene_sets = data_adaptor.check_new_gene_sets(gene_sets, context)
-
-                    # update cache
-                    self.last_geneset_fname = fname
-                    self.last_geneset = gene_sets
-
-        return (gene_sets, tid)
-
-    def write_gene_sets(self, gene_sets, tid, data_adaptor):
-        self.check_gene_sets_save_enabled()  # raises
-
-        if type(tid) != int or tid < 0:
-            raise ValueError("tid must be a positive integer")
-
-        # may raise
-        gene_sets = data_adaptor.check_new_gene_sets(gene_sets)
-
-        with self.gene_sets_lock:
-            # skip if the request is stale
-            if tid is not None:
-                if tid <= self.last_geneset_tid:
-                    raise ObsoleteRequest("TID is stale.")
-                self.last_geneset_tid = tid
-
-            lastmod = data_adaptor.get_last_mod_time()
-            lastmodstr = "'unknown'" if lastmod is None else lastmod.isoformat(timespec="seconds")
-            header = (
-                f"# Gene set generated on {datetime.now().isoformat(timespec='seconds')} "
-                f"using cellxgene version {cellxgene_version}\n"
-                f"# Input data file was {data_adaptor.get_location()}, "
-                f"which was last modified on {lastmodstr}\n"
-            )
-
-            fname = self._get_genesets_filename(data_adaptor)
-            self._backup(fname)
-            with open(fname, "w", newline="") as f:
-                f.write(header)
-                f.write(self.gene_sets_to_csv(gene_sets))
-
-            # update the cache
-            self.last_geneset_fname = fname
-            self.last_geneset = gene_sets if type(gene_sets) == dict else {g["geneset_name"]: g for g in gene_sets}
-
-    def _get_userdata_idhash(self, data_adaptor):
-        """
-        Return a short hash that weakly identifies the user and dataset.
-        Used to create safe annotations output file names.
-        """
-        uid = current_app.auth.get_user_id() or ""
-        id = (uid + data_adaptor.get_location()).encode()
-        idhash = base64.b32encode(blake2b(id, digest_size=5).digest()).decode("utf-8")
-        return idhash
-
-    def _get_output_dir(self):
-        if self.output_dir:
-            return self.output_dir
-
-        output_file = self.label_output_file or self.gene_sets_output_file
-        if output_file:
-            return os.path.dirname(os.path.abspath(output_file))
-
-        return os.getcwd()
-
-    def _get_celllabels_filename(self, data_adaptor):
-        """return the current annotation file name"""
-        if self.label_output_file:
-            return self.label_output_file
-
-        return self._get_filename(data_adaptor, "cell-labels")
-
-    def _get_genesets_filename(self, data_adaptor):
-        """return the current gene sets file name"""
-        if self.gene_sets_output_file:
-            return self.gene_sets_output_file
-
-        return self._get_filename(data_adaptor, "gene-sets")
-
-    def _get_filename(self, data_adaptor, anno_name):
-        # we need to generate a file name, which we can only do if we have a UID and collection name
-        if session is None:
-            raise AnnotationsError("unable to determine file name for annotations")
-
-        collection = self.get_collection()
-        if collection is None:
-            return None
-
-        if data_adaptor is None:
-            raise AnnotationsError("unable to determine file name for annotations")
-
-        idhash = self._get_userdata_idhash(data_adaptor)
-        return os.path.join(self._get_output_dir(), f"{collection}-{anno_name}-{idhash}.csv")
-
-    def _backup(self, fname, max_backups=9):
-        """
-        save N backups of file to backup_dir.
-            1. fname -> backup_dir/fname-TIME
-            2. delete excess files in backup_dir
-        """
-        root, ext = os.path.splitext(fname)
-        backup_dir = f"{root}-backups"
-
-        # Make sure there is work to do
-        if not os.path.exists(fname):
-            return
-
-        # Ensure backup_dir exists
-        if not os.path.exists(backup_dir):
-            os.mkdir(backup_dir)
-
-        # Save current file to backup_dir
-        fname_base = os.path.basename(fname)
-        fname_base_root, fname_base_ext = os.path.splitext(fname_base)
-        # don't use ISO standard time format, as it contains characters illegal on some filesytems.
-        nowish = datetime.now().strftime("%Y-%m-%dT%H-%M-%S")
-        backup_fname = os.path.join(backup_dir, f"{fname_base_root}-{nowish}{fname_base_ext}")
-        if os.path.exists(backup_fname):
-            os.remove(backup_fname)
-        os.rename(fname, backup_fname)
-
-        # prune the backup_dir to max number of backup files, keeping the most recent backups
-        backups = list(filter(lambda s: s.startswith(fname_base_root), os.listdir(backup_dir)))
-        excess_count = len(backups) - max_backups
-        if excess_count > 0:
-            backups.sort()
-            for bu in backups[0:excess_count]:
-                os.remove(os.path.join(backup_dir, bu))
-
-    def update_parameters(self, parameters, data_adaptor):
-        params = {}
-        params["annotations"] = self.user_annotations_enabled()
-        params["annotations_genesets_readonly"] = not self.gene_sets_save_enabled()
-        params["annotations_genesets_name_is_read_only"] = self.gene_sets_output_file is not None
-        params["user_annotation_collection_name_enabled"] = True
-
-        if self.label_output_file is not None:
-            # user has hard-wired the name of the annotation cell label data collection
-            fname = os.path.basename(self.label_output_file)
-            collection_fname = os.path.splitext(fname)[0]
-            params["annotations-data-collection-is-read-only"] = True
-            params["annotations-data-collection-name"] = collection_fname
-
-        elif session is not None:
-            collection = self.get_collection()
-            params["annotations-data-collection-is-read-only"] = not self.user_annotations_enabled()
-            params["annotations-data-collection-name"] = collection
-
-        if current_app.auth.is_user_authenticated():
-            params["annotations-user-data-idhash"] = self._get_userdata_idhash(data_adaptor)
-
-        parameters.update(params)

backend/server/common/config/__init__.py

@@ -1,4 +0,0 @@
-from backend.common.utils.aws_secret_utils import get_secret_key  # noqa F504
-
-DEFAULT_SERVER_PORT = 5005
-BIG_FILE_SIZE_THRESHOLD = 100 * 2 ** 20  # 100MB

backend/server/common/config/app_config.py

@@ -1,171 +0,0 @@
-import yaml
-from flatten_dict import unflatten
-
-from backend.server.default_config import get_default_config
-from backend.server.common.config.dataset_config import DatasetConfig
-from backend.server.common.config.server_config import ServerConfig
-from backend.server.common.config.external_config import ExternalConfig
-from backend.common.errors import ConfigurationError
-
-
-class AppConfig(object):
-    """
-    AppConfig stores all the configuration for cellxgene.
-    AppConfig contains one or more DatasetConfig(s) and one ServerConfig.
-    The server_config contains attributes that refer to the server process as a whole.
-    The dataset_config refers to attributes that are associated with the features and
-    presentations of a dataset.
-    AppConfig has methods to initialize, modify, and access the configuration.
-    """
-
-    def __init__(self):
-
-        # the default configuration (see default_config.py)
-        # TODO @madison -- if we always read from the default config (hard coded path) can we set those values as
-        #  defaults within the config class?
-        self.default_config = get_default_config()
-        # the server configuration
-        self.server_config = ServerConfig(self, self.default_config["server"])
-        # the dataset config
-        self.dataset_config = DatasetConfig(None, self, self.default_config["dataset"])
-        #  external config
-        self.external_config = ExternalConfig(self, self.default_config["external"])
-
-        # Set to true when config_completed is called
-        self.is_completed = False
-
-    def get_dataset_config(self):
-        return self.dataset_config
-
-    def check_config(self):
-        """Verify all the attributes in the config have been type checked"""
-        if not self.is_completed:
-            raise ConfigurationError("The configuration has not been completed")
-        self.server_config.check_config()
-        self.dataset_config.check_config()
-        self.external_config.check_config()
-
-    def update_server_config(self, **kw):
-        self.server_config.update(**kw)
-        self.is_complete = False
-
-    def update_dataset_config(self, **kw):
-        self.dataset_config.update(**kw)
-        self.is_complete = False
-
-    def update_single_config_from_path_and_value(self, path, value):
-        """Update a single config parameter with the value.
-        Path is a list of string, that gives a path to the config parameter to be updated.
-        For example, path may be ["server","app","port"].
-        """
-        self.is_complete = False
-        if not isinstance(path, list):
-            raise ConfigurationError(f"path must be a list of strings, got '{str(path)}'")
-        for part in path:
-            if not isinstance(part, str):
-                raise ConfigurationError(f"path must be a list of strings, got '{str(path)}'")
-
-        if len(path) < 1 or path[0] not in ("server", "dataset"):
-            raise ConfigurationError("path must start with 'server', or 'dataset'")
-
-        if path[0] == "server":
-            attr = "__".join(path[1:])
-            try:
-                self.update_server_config(**{attr: value})
-            except ConfigurationError:
-                raise ConfigurationError(f"unknown config parameter at path: '{str(path)}'")
-        elif path[0] == "dataset":
-            attr = "__".join(path[1:])
-            try:
-                self.update_dataset_config(**{attr: value})
-            except ConfigurationError:
-                raise ConfigurationError(f"unknown config parameter at path: '{str(path)}'")
-
-    def update_from_config_file(self, config_file):
-        try:
-            with open(config_file) as yml_file:
-                config = yaml.safe_load(yml_file)
-        except yaml.YAMLError as e:
-            raise ConfigurationError(f"The specified config file contained an error: {e}")
-        except OSError as e:
-            raise ConfigurationError(f"Issue retrieving the specified config file: {e}")
-
-        if config.get("server"):
-            self.server_config.update_from_config(config["server"], "server")
-        if config.get("dataset"):
-            self.dataset_config.update_from_config(config["dataset"], "dataset")
-
-        if config.get("external"):
-            self.external_config.update_from_config(config["external"], "external")
-
-        self.is_complete = False
-
-    def config_to_dict(self):
-        """return the configuration as an unflattened dict"""
-        server = self.server_config.create_mapping(self.server_config.default_config)
-        dataset = self.dataset_config.create_mapping(self.dataset_config.default_config)
-        external = self.external_config.create_mapping(self.external_config.default_config)
-        config = dict(server={}, dataset={})
-        for attrname in server.keys():
-            config["server__" + attrname] = getattr(self.server_config, attrname)
-        for attrname in dataset.keys():
-            config["dataset__" + attrname] = getattr(self.dataset_config, attrname)
-        for attrname in external.keys():
-            config["external__" + attrname] = getattr(self.external_config, attrname)
-
-        config = unflatten(config, splitter=lambda key: key.split("__"))
-        return config
-
-    def write_config(self, config_file):
-        """output the config to a yaml file"""
-        config = self.config_to_dict()
-        yaml.dump(config, open(config_file, "w"))
-
-    def changes_from_default(self):
-        """Return all the attribute that are different from the default"""
-        diff_server = self.server_config.changes_from_default()
-        diff_dataset = self.dataset_config.changes_from_default()
-        diff_external = self.external.changes_from_default()
-        diff = dict(server=diff_server, dataset=diff_dataset, external=diff_external)
-        return diff
-
-    def complete_config(self, messagefn=None):
-        """The configure options are checked, and any additional setup based on the config
-        parameters is done"""
-
-        if messagefn is None:
-
-            def noop(message):
-                pass
-
-            messagefn = noop
-
-        # TODO: to give better error messages we can add a mapping between where each config
-        # attribute originated (e.g. command line argument or config file), then in the error
-        # messages we can give correct context for attributes with bad value.
-        context = dict(messagefn=messagefn)
-
-        # complete config for external_config first, since this may update values in the other sections
-        self.external_config.complete_config(context)
-        self.server_config.complete_config(context)
-        self.dataset_config.complete_config(context)
-
-        self.is_completed = True
-        self.check_config()
-
-    def get_matrix_data_cache_manager(self):
-        return self.server_config.matrix_data_cache_manager
-
-    def get_title(self, data_adaptor):
-        return (
-            self.server_config.single_dataset__title
-            if self.server_config.single_dataset__title
-            else data_adaptor.get_title()
-        )
-
-    def get_about(self, data_adaptor):
-        return (
-            self.server_config.single_dataset__about
-            if self.server_config.single_dataset__about
-            else data_adaptor.get_about()
-        )

backend/server/common/config/base_config.py

@@ -1,99 +0,0 @@
-import copy
-
-from flatten_dict import flatten
-from backend.common.errors import ConfigurationError
-
-
-class BaseConfig(object):
-    """
-    This class handles the mechanics of updating and checking attributes.
-    Derived classes are expected to store the actual attributes
-    Currently DatasetConfig and ServerConfig both inherit from BaseConfig.
-    """
-
-    def __init__(self, app_config, default_config):
-        # reference back to the app_config
-        self.app_config = app_config
-        # the complete set of attributes and their default values (unflattened)
-        self.default_config = default_config
-        # used to make sure every attribute value is checked
-        self.attr_checked = {key_name: False for key_name in self.create_mapping(default_config).keys()}
-
-    def create_mapping(self, config):
-        """
-        Create a dictionary where the keys are the name of attributes (using double underscore convention)
-        For example: authentication__type
-
-        The values are a tuple,
-        - the first item of the tuple is a tuple of path elements (location in config 'tree')
-        - the second item is the value of the config parameter
-
-        For example: (('authentication', 'type'), 'session'))
-        """
-        config_copy = copy.deepcopy(config)
-        mapping = {}
-
-        flat_config = flatten(config_copy)
-        for key, value in flat_config.items():
-            # name of the attribute
-            attr = "__".join(key)
-            mapping[attr] = (key, value)
-
-        return mapping
-
-    def validate_correct_type_of_configuration_attribute(self, attrname, vtype):
-        val = getattr(self, attrname)
-        if type(vtype) in (list, tuple):
-            if type(val) not in vtype:
-                tnames = ",".join([x.__name__ for x in vtype])
-                raise ConfigurationError(
-                    f"Invalid type for attribute: {attrname}, expected types ({tnames}), got {type(val).__name__}"
-                )
-        else:
-            if type(val) != vtype:
-                raise ConfigurationError(
-                    f"Invalid type for attribute: {attrname}, "
-                    f"expected type {vtype.__name__}, got {type(val).__name__}"
-                )
-
-        self.attr_checked[attrname] = True
-
-    def check_config(self):
-        mapping = self.create_mapping(self.default_config)
-        for key in mapping.keys():
-            if not self.attr_checked[key]:
-                raise ConfigurationError(f"The attr '{key}' has not been checked")
-
-    def update(self, **kw):
-        """Update the attributes defined in kw with their new values."""
-        for key, value in kw.items():
-            if not hasattr(self, key):
-                raise ConfigurationError(f"unknown config parameter {key}.")
-            try:
-                if type(value) == tuple:
-                    # convert tuple values to list values
-                    value = list(value)
-                setattr(self, key, value)
-            except KeyError:
-                raise ConfigurationError(f"Unable to set config parameter {key}.")
-
-            self.attr_checked[key] = False
-
-    def update_from_config(self, config, prefix):
-        mapping = self.create_mapping(config)
-        for attr, (key, value) in mapping.items():
-            if not hasattr(self, attr):
-                raise ConfigurationError(f"Unknown key from config file: {prefix}__{attr}")
-            setattr(self, attr, value)
-
-            self.attr_checked[attr] = False
-
-    def changes_from_default(self):
-        """Return all the attribute that are different from the default"""
-        mapping = self.create_mapping(self.default_config)
-        diff = []
-        for attrname, (key, defval) in mapping.items():
-            curval = getattr(self, attrname)
-            if curval != defval:
-                diff.append((attrname, curval, defval))
-        return diff

backend/server/common/config/client_config.py

@@ -1,119 +0,0 @@
-from backend.server import display_version as cellxgene_display_version
-
-
-def get_client_config(app_config, data_adaptor):
-    """
-    Return the configuration as required by the /config REST route
-    """
-
-    server_config = app_config.server_config
-    dataset_config = data_adaptor.dataset_config
-    annotation = dataset_config.user_annotations
-    auth = server_config.auth
-
-    # FIXME The current set of config is not consistently presented:
-    # we have camalCase, hyphen-text, and underscore_text
-
-    # make sure the configuration has been checked.
-    app_config.check_config()
-
-    # display_names
-    title = app_config.get_title(data_adaptor)
-    about = app_config.get_about(data_adaptor)
-
-    display_names = dict(engine=data_adaptor.get_name(), dataset=title)
-
-    # library_versions
-    library_versions = {}
-    library_versions.update(data_adaptor.get_library_versions())
-    library_versions["cellxgene"] = cellxgene_display_version
-
-    # links
-    links = {"about-dataset": about}
-
-    # parameters
-    parameters = {
-        "layout": dataset_config.embeddings__names,
-        "max-category-items": dataset_config.presentation__max_categories,
-        "obs_names": server_config.single_dataset__obs_names,
-        "var_names": server_config.single_dataset__var_names,
-        "diffexp_lfc_cutoff": dataset_config.diffexp__lfc_cutoff,
-        "backed": server_config.adaptor__anndata_adaptor__backed,
-        "disable-diffexp": not dataset_config.diffexp__enable,
-        "annotations": False,
-        "annotations_file": None,
-        "annotations_dir": None,
-        "annotations_genesets": True,  # feature flag
-        "annotations_genesets_readonly": dataset_config.user_annotations__gene_sets__readonly,
-        "annotations_genesets_summary_methods": ["mean"],
-        "custom_colors": dataset_config.presentation__custom_colors,
-        "diffexp-may-be-slow": False,
-    }
-
-    # corpora dataset_props
-    # TODO/Note: putting info from the dataset into the /config is not ideal.
-    # However, it is definitely not part of /schema, and we do not have a top-level
-    # route for data properties.  Consider creating one at some point.
-    corpora_props = data_adaptor.get_corpora_props()
-    if corpora_props and "default_embedding" in corpora_props:
-        default_embedding = corpora_props["default_embedding"]
-        if isinstance(default_embedding, str) and default_embedding.startswith("X_"):
-            default_embedding = default_embedding[2:]  # drop X_ prefix
-        if default_embedding in data_adaptor.get_embedding_names():
-            parameters["default_embedding"] = default_embedding
-
-    data_adaptor.update_parameters(parameters)
-    if annotation:
-        annotation.update_parameters(parameters, data_adaptor)
-
-    # gather it all together
-    client_config = {}
-    config = client_config["config"] = {}
-    config["displayNames"] = display_names
-    config["library_versions"] = library_versions
-    config["links"] = links
-    config["parameters"] = parameters
-    config["corpora_props"] = corpora_props
-    config["limits"] = {
-        "column_request_max": server_config.limits__column_request_max,
-        "diffexp_cellcount_max": server_config.limits__diffexp_cellcount_max,
-    }
-
-    if dataset_config.app__authentication_enable and auth.is_valid_authentication_type():
-        config["authentication"] = {
-            "requires_client_login": auth.requires_client_login(),
-        }
-        if auth.requires_client_login():
-            config["authentication"].update(
-                {
-                    # Todo why are these stored on the data_adaptor?
-                    "login": auth.get_login_url(data_adaptor),
-                    "logout": auth.get_logout_url(data_adaptor),
-                }
-            )
-
-    return client_config
-
-
-def get_client_userinfo(app_config, data_adaptor):
-    """
-    Return the userinfo as required by the /userinfo REST route
-    """
-
-    server_config = app_config.server_config
-    dataset_config = data_adaptor.dataset_config
-    auth = server_config.auth
-
-    # make sure the configuration has been checked.
-    app_config.check_config()
-
-    if dataset_config.app__authentication_enable and auth.is_valid_authentication_type():
-        userinfo = {}
-        userinfo["userinfo"] = {
-            "is_authenticated": auth.is_user_authenticated(),
-            "username": auth.get_user_name(),
-            "user_id": auth.get_user_id(),
-            "email": auth.get_user_email(),
-            "picture": auth.get_user_picture(),
-        }
-        return userinfo

backend/server/common/config/dataset_config.py

@@ -1,194 +0,0 @@
-import os
-from os.path import splitext, isdir
-
-from backend.server.common.annotations.local_file_csv import AnnotationsLocalFile
-from backend.server.common.config.base_config import BaseConfig
-from backend.common.errors import ConfigurationError, AnnotationsError
-from backend.server.data_common.matrix_loader import MatrixDataLoader
-
-
-class DatasetConfig(BaseConfig):
-    """Manages the config attribute associated with a dataset."""
-
-    def __init__(self, tag, app_config, default_config):
-        super().__init__(app_config, default_config)
-        self.tag = tag
-        try:
-            self.app__scripts = default_config["app"]["scripts"]
-            self.app__inline_scripts = default_config["app"]["inline_scripts"]
-            self.app__authentication_enable = default_config["app"]["authentication_enable"]
-
-            self.presentation__max_categories = default_config["presentation"]["max_categories"]
-            self.presentation__custom_colors = default_config["presentation"]["custom_colors"]
-
-            self.user_annotations__enable = default_config["user_annotations"]["enable"]
-            self.user_annotations__type = default_config["user_annotations"]["type"]
-            self.user_annotations__local_file_csv__directory = default_config["user_annotations"]["local_file_csv"][
-                "directory"
-            ]
-            self.user_annotations__local_file_csv__file = default_config["user_annotations"]["local_file_csv"]["file"]
-            self.user_annotations__gene_sets__readonly = default_config["user_annotations"]["gene_sets"]["readonly"]
-            self.user_annotations__local_file_csv__gene_sets_file = default_config["user_annotations"][
-                "local_file_csv"
-            ]["gene_sets_file"]
-
-            self.embeddings__names = default_config["embeddings"]["names"]
-
-            self.diffexp__enable = default_config["diffexp"]["enable"]
-            self.diffexp__lfc_cutoff = default_config["diffexp"]["lfc_cutoff"]
-            self.diffexp__top_n = default_config["diffexp"]["top_n"]
-
-            self.X_approximate_distribution = default_config["X_approximate_distribution"]
-
-        except KeyError as e:
-            raise ConfigurationError(f"Unexpected config: {str(e)}")
-
-        # The annotation object is created during complete_config and stored here.
-        self.user_annotations = None
-
-    def complete_config(self, context):
-        self.handle_app()
-        self.handle_presentation()
-        self.handle_user_annotations(context)
-        self.handle_embeddings()
-        self.handle_diffexp(context)
-        self.handle_X_approximate_distribution()
-
-    def get_data_adaptor(self):
-        server_config = self.app_config.server_config
-        if not server_config.data_adaptor:
-            matrix_data_loader = MatrixDataLoader(server_config.single_dataset__datapath, app_config=self.app_config)
-            server_config.data_adaptor = matrix_data_loader.open(self.app_config)
-
-        return server_config.data_adaptor
-
-    def handle_app(self):
-        self.validate_correct_type_of_configuration_attribute("app__scripts", list)
-        self.validate_correct_type_of_configuration_attribute("app__inline_scripts", list)
-        self.validate_correct_type_of_configuration_attribute("app__authentication_enable", bool)
-
-        # scripts can be string (filename) or dict (attributes). Convert string to dict.
-        scripts = []
-        for script in self.app__scripts:
-            try:
-                if isinstance(script, str):
-                    scripts.append({"src": script})
-                elif isinstance(script, dict) and isinstance(script["src"], str):
-                    scripts.append(script)
-                else:
-                    raise Exception
-            except Exception as e:
-                raise ConfigurationError(f"Scripts must be string or a dict containing an src key: {e}")
-
-        self.app__scripts = scripts
-
-    def handle_presentation(self):
-        self.validate_correct_type_of_configuration_attribute("presentation__max_categories", int)
-        self.validate_correct_type_of_configuration_attribute("presentation__custom_colors", bool)
-
-    def handle_user_annotations(self, context):
-        self.validate_correct_type_of_configuration_attribute("user_annotations__enable", bool)
-        self.validate_correct_type_of_configuration_attribute("user_annotations__type", str)
-        self.validate_correct_type_of_configuration_attribute(
-            "user_annotations__local_file_csv__directory", (type(None), str)
-        )
-        self.validate_correct_type_of_configuration_attribute(
-            "user_annotations__local_file_csv__file", (type(None), str)
-        )
-        self.validate_correct_type_of_configuration_attribute(
-            "user_annotations__local_file_csv__gene_sets_file", (type(None), str)
-        )
-        self.validate_correct_type_of_configuration_attribute("user_annotations__gene_sets__readonly", bool)
-
-        if self.user_annotations__enable or not self.user_annotations__gene_sets__readonly:
-            server_config = self.app_config.server_config
-            if not self.app__authentication_enable:
-                raise ConfigurationError("user annotations requires authentication to be enabled")
-            if not server_config.auth.is_valid_authentication_type():
-                auth_type = server_config.authentication__type
-                raise ConfigurationError(f"authentication method {auth_type} is not compatible with user annotations")
-
-        # Must always have an annotations instance to support genesets. User annotation (cell labels) are optional
-        # as are writable gene sets
-        if self.user_annotations__type == "local_file_csv":
-            self.handle_local_file_csv_annotations(context)
-        else:
-            raise ConfigurationError('The only annotation type support is "local_file_csv"')
-
-        self.check_annotation_config_vars_not_set(context)
-
-    def handle_local_file_csv_annotations(self, context):
-        dirname = self.user_annotations__local_file_csv__directory
-        filename = self.user_annotations__local_file_csv__file
-        genesets_filename = self.user_annotations__local_file_csv__gene_sets_file
-
-        if dirname is not None and (filename is not None or genesets_filename is not None):
-            raise ConfigurationError(
-                "'user-generated-data-dir' may not be used with 'annotations-file' or 'gene-sets-file'."
-            )
-
-        if filename is not None:
-            lf_name, lf_ext = splitext(filename)
-            if lf_ext and lf_ext != ".csv":
-                raise ConfigurationError(f"annotation file type must be .csv: {filename}")
-
-        if genesets_filename is not None:
-            lf_name, lf_ext = splitext(genesets_filename)
-            if lf_ext and lf_ext != ".csv":
-                raise ConfigurationError(f"genesets file type must be .csv: {genesets_filename}")
-
-        if dirname is not None and not isdir(dirname):
-            try:
-                os.mkdir(dirname)
-            except OSError:
-                raise ConfigurationError("Unable to create directory specified by --user-generated-data-dir")
-
-        anno_config = {
-            "user-annotations": self.user_annotations__enable,
-            "genesets-save": not self.user_annotations__gene_sets__readonly,
-        }
-        self.user_annotations = AnnotationsLocalFile(anno_config, dirname, filename, genesets_filename)
-
-        # if the user has specified a fixed label file, go ahead and validate it
-        # so that we can remove errors early in the process.
-        server_config = self.app_config.server_config
-        if server_config.single_dataset__datapath:
-            data_adaptor = self.get_data_adaptor()
-            if self.user_annotations__local_file_csv__file:
-                self.user_annotations.read_labels(data_adaptor)
-            if self.user_annotations__local_file_csv__gene_sets_file:
-                try:
-                    self.user_annotations.read_gene_sets(data_adaptor, context)
-                except (ValueError, AnnotationsError, KeyError) as e:
-                    raise ConfigurationError(f"Unable to read genesets CSV file: {str(e)}") from e
-
-    def check_annotation_config_vars_not_set(self, context):
-        if self.user_annotations__type is not None:
-            dirname = self.user_annotations__local_file_csv__directory
-            filename = self.user_annotations__local_file_csv__file
-            if not self.user_annotations__enable:
-                if filename is not None:
-                    context["messagefn"]("Warning: --annotations-file ignored as annotations are disabled.")
-                if dirname is not None:
-                    context["messagefn"]("Warning: --user-generated-data-dir ignored as annotations are disabled.")
-
-    def handle_embeddings(self):
-        self.validate_correct_type_of_configuration_attribute("embeddings__names", list)
-
-    def handle_diffexp(self, context):
-        self.validate_correct_type_of_configuration_attribute("diffexp__enable", bool)
-        self.validate_correct_type_of_configuration_attribute("diffexp__lfc_cutoff", float)
-        self.validate_correct_type_of_configuration_attribute("diffexp__top_n", int)
-
-        data_adaptor = self.get_data_adaptor()
-        if self.diffexp__enable and data_adaptor.parameters.get("diffexp_may_be_slow", False):
-            context["messagefn"](
-                "CAUTION: due to the size of your dataset, " "running differential expression may take longer or fail."
-            )
-
-    def handle_X_approximate_distribution(self):
-        self.validate_correct_type_of_configuration_attribute("X_approximate_distribution", str)
-        if self.X_approximate_distribution not in ["auto", "normal", "count"]:
-            raise ConfigurationError(
-                "X_approximate_distribution has unknown value -- must be 'auto', 'normal' or 'count'."
-            )

backend/server/common/config/external_config.py

@@ -1,96 +0,0 @@
-import os
-
-from backend.server.common.config.base_config import BaseConfig
-from backend.common.errors import ConfigurationError
-from backend.server.common.config import get_secret_key
-from backend.common.errors import SecretKeyRetrievalError
-from backend.common.utils.type_conversion_utils import convert_string_to_value
-
-
-class ExternalConfig(BaseConfig):
-    """Manages the config attribute associated with external configuration sources, such as
-    environment variables or the AWS Secrets Manager."""
-
-    def __init__(self, app_config, default_config):
-        super().__init__(app_config, default_config)
-        try:
-            self.environment = default_config["environment"]
-            self.aws_secrets_manager__region = default_config["aws_secrets_manager"]["region"]
-            self.aws_secrets_manager__secrets = default_config["aws_secrets_manager"]["secrets"]
-
-        except KeyError as e:
-            raise ConfigurationError(f"Unexpected config: {str(e)}")
-
-    def complete_config(self, context):
-        self.handle_environment(context)
-        self.handle_aws_secrets_manager(context)
-
-    def handle_environment(self, context):
-        """For each environment variable defined, get the value (if it is set),
-        and set the specified config parameter"""
-        self.validate_correct_type_of_configuration_attribute("environment", list)
-        for envdict in self.environment:
-            name = envdict.get("name")
-            if name is None:
-                raise ConfigurationError("environment: 'name' is missing")
-            required = envdict.get("required", False)
-            if type(required) != bool:
-                raise ConfigurationError("environment: 'required' must be a bool")
-            path = envdict.get("path")
-            if path is None:
-                raise ConfigurationError("environment: 'path' is missing")
-
-            value = os.environ.get(name)
-            if value is None:
-                if required:
-                    raise ConfigurationError(f"required environment variable '{name}' not set")
-            else:
-                value = convert_string_to_value(value)
-                self.app_config.update_single_config_from_path_and_value(path, value)
-
-    def handle_aws_secrets_manager(self, context):
-        """For each aws secret defined, get the key/values, and set the specified config parameter"""
-        self.validate_correct_type_of_configuration_attribute("aws_secrets_manager__region", (type(None), str))
-        self.validate_correct_type_of_configuration_attribute("aws_secrets_manager__secrets", list)
-
-        if not self.aws_secrets_manager__secrets:
-            return
-
-        self.validate_correct_type_of_configuration_attribute("aws_secrets_manager__region", str)
-
-        for secret in self.aws_secrets_manager__secrets:
-            secret_name = secret.get("name")
-            if secret_name is None:
-                raise ConfigurationError("aws_secrets_manager: 'name' is missing")
-            if not isinstance(secret_name, str):
-                raise ConfigurationError("aws_secrets_manager: 'name' must be a string")
-
-            try:
-                secret_dict = get_secret_key(self.aws_secrets_manager__region, secret_name)
-            except SecretKeyRetrievalError as e:
-                raise ConfigurationError(f"Unable to retrieve secret {secret_name}: {str(e)}")
-
-            values = secret.get("values")
-            if values is None:
-                raise ConfigurationError("aws_secrets_manager: 'values' is missing")
-            if not isinstance(values, list):
-                raise ConfigurationError("aws_secrets_manager: 'values' must be a list")
-
-            for value in values:
-                key = value.get("key")
-                if key is None:
-                    raise ConfigurationError(f"missing 'key' in secret values: {secret_name}")
-                path = value.get("path")
-                if path is None:
-                    raise ConfigurationError(f"missing 'path' in secret values: {secret_name}")
-                required = value.get("required", False)
-                if type(required) != bool:
-                    raise ConfigurationError(f"wrong type for 'required' in secret values: {secret_name}")
-
-                secret_value = secret_dict.get(key)
-                if secret_value is None:
-                    if required:
-                        raise ConfigurationError(f"required secret '{secret_name}:{key}' not set")
-                else:
-                    secret_value = convert_string_to_value(secret_value)
-                    self.app_config.update_single_config_from_path_and_value(path, secret_value)

backend/server/common/config/server_config.py

@@ -1,185 +0,0 @@
-import os
-import sys
-import warnings
-from os.path import basename
-from urllib.parse import urlparse
-
-from backend.server.auth.auth import AuthTypeFactory
-from backend.server.common.config.base_config import BaseConfig
-from backend.server.common.config import DEFAULT_SERVER_PORT, BIG_FILE_SIZE_THRESHOLD
-from backend.common.utils.data_locator import discover_s3_region_name
-from backend.common.errors import ConfigurationError, DatasetAccessError
-from backend.common.utils.utils import is_port_available, find_available_port, custom_format_warning
-from backend.server.data_common.matrix_loader import MatrixDataLoader
-
-
-class ServerConfig(BaseConfig):
-    """Manages the config attribute associated with the server."""
-
-    def __init__(self, app_config, default_config):
-        super().__init__(app_config, default_config)
-
-        try:
-            self.app__verbose = default_config["app"]["verbose"]
-            self.app__debug = default_config["app"]["debug"]
-            self.app__host = default_config["app"]["host"]
-            self.app__port = default_config["app"]["port"]
-            self.app__open_browser = default_config["app"]["open_browser"]
-            self.app__force_https = default_config["app"]["force_https"]
-            self.app__flask_secret_key = default_config["app"]["flask_secret_key"]
-            self.app__generate_cache_control_headers = default_config["app"]["generate_cache_control_headers"]
-
-            self.authentication__type = default_config["authentication"]["type"]
-            self.authentication__insecure_test_environment = default_config["authentication"][
-                "insecure_test_environment"
-            ]
-
-            self.single_dataset__datapath = default_config["single_dataset"]["datapath"]
-            self.single_dataset__obs_names = default_config["single_dataset"]["obs_names"]
-            self.single_dataset__var_names = default_config["single_dataset"]["var_names"]
-            self.single_dataset__about = default_config["single_dataset"]["about"]
-            self.single_dataset__title = default_config["single_dataset"]["title"]
-
-            self.data_locator__s3__region_name = default_config["data_locator"]["s3"]["region_name"]
-
-            self.adaptor__anndata_adaptor__backed = default_config["adaptor"]["anndata_adaptor"]["backed"]
-
-            self.limits__diffexp_cellcount_max = default_config["limits"]["diffexp_cellcount_max"]
-            self.limits__column_request_max = default_config["limits"]["column_request_max"]
-
-        except KeyError as e:
-            raise ConfigurationError(f"Unexpected config: {str(e)}")
-
-        self.data_adaptor = None
-
-        # The authentication object
-        self.auth = None
-
-    def complete_config(self, context):
-        self.handle_app(context)
-        self.handle_data_source()
-        self.handle_authentication()
-        self.handle_data_locator()
-        self.handle_adaptor()  # may depend on data_locator
-        self.handle_single_dataset(context)  # may depend on adaptor
-        self.handle_limits()
-
-        self.check_config()
-
-    def handle_app(self, context):
-        self.validate_correct_type_of_configuration_attribute("app__verbose", bool)
-        self.validate_correct_type_of_configuration_attribute("app__debug", bool)
-        self.validate_correct_type_of_configuration_attribute("app__host", str)
-        self.validate_correct_type_of_configuration_attribute("app__port", (type(None), int))
-        self.validate_correct_type_of_configuration_attribute("app__open_browser", bool)
-        self.validate_correct_type_of_configuration_attribute("app__force_https", bool)
-        self.validate_correct_type_of_configuration_attribute("app__flask_secret_key", str)
-        self.validate_correct_type_of_configuration_attribute("app__generate_cache_control_headers", bool)
-
-        if self.app__port:
-            try:
-                if not is_port_available(self.app__host, self.app__port):
-                    raise ConfigurationError(
-                        f"The port selected {self.app__port} is in use, please configure an open port."
-                    )
-            except OverflowError:
-                raise ConfigurationError(f"Invalid port: {self.app__port}")
-        else:
-            try:
-                default_server_port = int(os.environ.get("CXG_SERVER_PORT", DEFAULT_SERVER_PORT))
-            except ValueError:
-                raise ConfigurationError(
-                    "Invalid port from environment variable CXG_SERVER_PORT: " + os.environ.get("CXG_SERVER_PORT")
-                )
-            try:
-                self.app__port = find_available_port(self.app__host, default_server_port)
-            except OverflowError:
-                raise ConfigurationError(f"Invalid port: {default_server_port}")
-
-        if self.app__debug:
-            context["messagefn"]("in debug mode, setting verbose=True and open_browser=False")
-            self.app__verbose = True
-            self.app__open_browser = False
-        else:
-            warnings.formatwarning = custom_format_warning
-
-        if not self.app__verbose:
-            sys.tracebacklimit = 0
-
-    def handle_authentication(self):
-        self.validate_correct_type_of_configuration_attribute("authentication__type", (type(None), str))
-        self.validate_correct_type_of_configuration_attribute("authentication__insecure_test_environment", bool)
-
-        if self.authentication__type == "test" and not self.authentication__insecure_test_environment:
-            raise ConfigurationError("Test auth can only be used in an insecure test environment")
-
-        self.auth = AuthTypeFactory.create(self.authentication__type, self)
-        if self.auth is None:
-            raise ConfigurationError(f"Unknown authentication type: {self.authentication__type}")
-
-    def handle_data_locator(self):
-        self.validate_correct_type_of_configuration_attribute("data_locator__s3__region_name", (type(None), bool, str))
-        if self.data_locator__s3__region_name is True:
-            path = self.single_dataset__datapath
-
-            if path.startswith("s3://"):
-                region_name = discover_s3_region_name(path)
-                if region_name is None:
-                    raise ConfigurationError(f"Unable to discover s3 region name from {path}")
-            else:
-                region_name = None
-            self.data_locator__s3__region_name = region_name
-
-    def handle_data_source(self):
-        self.validate_correct_type_of_configuration_attribute("single_dataset__datapath", str)
-
-    def handle_single_dataset(self, context):
-        self.validate_correct_type_of_configuration_attribute("single_dataset__datapath", (str, type(None)))
-        self.validate_correct_type_of_configuration_attribute("single_dataset__title", (str, type(None)))
-        self.validate_correct_type_of_configuration_attribute("single_dataset__about", (str, type(None)))
-        self.validate_correct_type_of_configuration_attribute("single_dataset__obs_names", (str, type(None)))
-        self.validate_correct_type_of_configuration_attribute("single_dataset__var_names", (str, type(None)))
-
-        # preload this data set
-        matrix_data_loader = MatrixDataLoader(self.single_dataset__datapath, app_config=self.app_config)
-        try:
-            matrix_data_loader.pre_load_validation()
-        except DatasetAccessError as e:
-            raise ConfigurationError(str(e))
-
-        file_size = matrix_data_loader.file_size()
-        file_basename = basename(self.single_dataset__datapath)
-        if file_size > BIG_FILE_SIZE_THRESHOLD:
-            context["messagefn"](f"Loading data from {file_basename}, this may take a while...")
-        else:
-            context["messagefn"](f"Loading data from {file_basename}.")
-
-        if self.single_dataset__about:
-
-            def url_check(url):
-                try:
-                    result = urlparse(url)
-                    if all([result.scheme, result.netloc]):
-                        return True
-                    else:
-                        return False
-                except ValueError:
-                    return False
-
-            if not url_check(self.single_dataset__about):
-                raise ConfigurationError(
-                    "Must provide an absolute URL for --about. (Example format: http://example.com)"
-                )
-
-    def handle_adaptor(self):
-        self.validate_correct_type_of_configuration_attribute("adaptor__anndata_adaptor__backed", bool)
-
-    def handle_limits(self):
-        self.validate_correct_type_of_configuration_attribute("limits__diffexp_cellcount_max", (type(None), int))
-        self.validate_correct_type_of_configuration_attribute("limits__column_request_max", (type(None), int))
-
-    def exceeds_limit(self, limit_name, value):
-        limit_value = getattr(self, "limits__" + limit_name, None)
-        if limit_value is None:  # disabled
-            return False
-        return value > limit_value

backend/server/common/corpora.py

@@ -1,78 +0,0 @@
-"""
-Corpora schema conventions support.  Helper functions for reading.
-
-https://github.com/chanzuckerberg/corpora-data-portal/blob/main/backend/schema/corpora_schema.md
-
-https://github.com/chanzuckerberg/corpora-data-portal/blob/main/backend/schema/corpora_schema_h5ad_implementation.md
-"""
-import collections
-import json
-
-from backend.server.cli.upgrade import validate_version_str
-from backend.server.common.utils.corpora_constants import CorporaConstants
-
-
-def corpora_get_versions_from_anndata(adata):
-    """
-    Given an AnnData object, return:
-        * None - if not a Corpora object
-        * [ corpora_schema_version, corpora_encoding_version ] - if a Corpora object
-
-    Implements the identification protocol defined in the specification.
-    """
-
-    # per Corpora AnnData spec, this is a corpora file if the following is true
-    if "version" not in adata.uns_keys():
-        return None
-    version = adata.uns["version"]
-    if not isinstance(version, collections.abc.Mapping) or "corpora_schema_version" not in version:
-        return None
-
-    corpora_schema_version = version.get("corpora_schema_version")
-    corpora_encoding_version = version.get("corpora_encoding_version")
-
-    # TODO: spec says these must be SEMVER values, so check.
-    if validate_version_str(corpora_schema_version) and validate_version_str(corpora_encoding_version):
-        return [corpora_schema_version, corpora_encoding_version]
-
-
-def corpora_is_version_supported(corpora_schema_version, corpora_encoding_version):
-    return (
-        corpora_schema_version
-        and corpora_encoding_version
-        and corpora_schema_version.startswith("1.")
-        and corpora_encoding_version.startswith("0.1.")
-    )
-
-
-def corpora_get_props_from_anndata(adata):
-    """
-    Get Corpora dataset properties from an AnnData
-    """
-    versions = corpora_get_versions_from_anndata(adata)
-    if versions is None:
-        return None
-    [corpora_schema_version, corpora_encoding_version] = versions
-    version_is_supported = corpora_is_version_supported(corpora_schema_version, corpora_encoding_version)
-    if not version_is_supported:
-        raise ValueError("Unsupported Corpora schema version")
-
-    corpora_props = {}
-    for key in CorporaConstants.REQUIRED_SIMPLE_METADATA_FIELDS:
-        if key not in adata.uns:
-            raise KeyError(f"missing Corpora schema field {key}")
-        corpora_props[key] = adata.uns[key]
-
-    for key in CorporaConstants.OPTIONAL_JSON_ENCODED_METADATA_FIELD:
-        if key not in adata.uns:
-            continue
-        try:
-            corpora_props[key] = json.loads(adata.uns[key])
-        except json.JSONDecodeError:
-            raise json.JSONDecodeError(f"Corpora schema field {key} is expected to be a valid JSON string")
-
-    for key in CorporaConstants.OPTIONAL_SIMPLE_METADATA_FIELDS:
-        if key in adata.uns:
-            corpora_props[key] = adata.uns[key]
-
-    return corpora_props

backend/server/common/health.py

@@ -1,33 +0,0 @@
-from http import HTTPStatus
-from flask import make_response, jsonify
-
-from backend.server import __version__ as cellxgene_version
-from backend.common.utils.data_locator import DataLocator
-
-
-def _is_accessible(path, config):
-    if path is None:
-        return True
-
-    try:
-        dl = DataLocator(path, region_name=config.data_locator__s3__region_name)
-        return dl.exists()
-    except RuntimeError:
-        return False
-
-
-def health_check(config):
-    """
-    simple health check - return HTTP response.
-    See https://tools.ietf.org/id/draft-inadarei-api-health-check-01.html
-    """
-    health = {"status": None, "version": "1", "releaseID": cellxgene_version}
-
-    server_config = config.server_config
-    check = _is_accessible(server_config.single_dataset__datapath, server_config)
-
-    health["status"] = "pass" if check else "fail"
-    code = HTTPStatus.OK if health["status"] == "pass" else HTTPStatus.BAD_REQUEST
-    response = make_response(jsonify(health), code)
-    response.headers["Content-Type"] = "application/health+json"
-    return response

backend/server/common/rest.py

@@ -1,404 +0,0 @@
-import copy
-import logging
-import sys
-from http import HTTPStatus
-import zlib
-import json
-
-from flask import make_response, jsonify, current_app, abort
-from werkzeug.urls import url_unquote
-
-from backend.server.common.config.client_config import get_client_config, get_client_userinfo
-from backend.common.constants import Axis, DiffExpMode, JSON_NaN_to_num_warning_msg
-from backend.common.errors import (
-    FilterError,
-    JSONEncodingValueError,
-    PrepareError,
-    DisabledFeatureError,
-    ExceedsLimitError,
-    DatasetAccessError,
-    ColorFormatException,
-    AnnotationsError,
-    ObsoleteRequest,
-    UnsupportedSummaryMethod,
-)
-from backend.common.genesets import summarizeQueryHash
-from backend.common.fbs.matrix import decode_matrix_fbs
-
-
-def abort_and_log(code, logmsg, loglevel=logging.DEBUG, include_exc_info=False):
-    """
-    Log the message, then abort with HTTP code. If include_exc_info is true,
-    also include current exception via sys.exc_info().
-    """
-    if include_exc_info:
-        exc_info = sys.exc_info()
-    else:
-        exc_info = False
-    current_app.logger.log(loglevel, logmsg, exc_info=exc_info)
-    # Do NOT send log message to HTTP response.
-    return abort(code)
-
-
-def _query_parameter_to_filter(args):
-    """
-    Convert an annotation value filter, if present in the query args,
-    into the standard dict filter format used by internal code.
-
-    Query param filters look like:  <axis>:name=value, where value
-    may be one of:
-        - a range, min,max, where either may be an open range by using an asterisk, eg, 10,*
-        - a value
-    Eg,
-        ...?tissue=lung&obs:tissue=heart&obs:num_reads=1000,*
-    """
-    filters = {
-        "obs": {},
-        "var": {},
-    }
-
-    # args has already been url-unquoted once.  We assume double escaping
-    # on name and value.
-    try:
-        for key, value in args.items(multi=True):
-            axis, name = key.split(":")
-            if axis not in ("obs", "var"):
-                raise FilterError("unknown filter axis")
-            name = url_unquote(name)
-            current = filters[axis].setdefault(name, {"name": name})
-
-            val_split = value.split(",")
-            if len(val_split) == 1:
-                if "min" in current or "max" in current:
-                    raise FilterError("do not mix range and value filters")
-                value = url_unquote(value)
-                values = current.setdefault("values", [])
-                values.append(value)
-
-            elif len(val_split) == 2:
-                if len(current) > 1:
-                    raise FilterError("duplicate range specification")
-                min = url_unquote(val_split[0])
-                max = url_unquote(val_split[1])
-                if min != "*":
-                    current["min"] = float(min)
-                if max != "*":
-                    current["max"] = float(max)
-                if len(current) < 2:
-                    raise FilterError("must specify at least min or max in range filter")
-
-            else:
-                raise FilterError("badly formated filter value")
-
-    except ValueError as e:
-        raise FilterError(str(e))
-
-    result = {}
-    for axis in ("obs", "var"):
-        axis_filter = filters[axis]
-        if len(axis_filter) > 0:
-            result[axis] = {"annotation_value": [val for val in axis_filter.values()]}
-
-    return result
-
-
-def schema_get_helper(data_adaptor):
-    """helper function to gather the schema from the data source and annotations"""
-    schema = data_adaptor.get_schema()
-    schema = copy.deepcopy(schema)
-
-    # add label obs annotations as needed
-    annotations = data_adaptor.dataset_config.user_annotations
-    if annotations.user_annotations_enabled():
-        label_schema = annotations.get_schema(data_adaptor)
-        schema["annotations"]["obs"]["columns"].extend(label_schema)
-
-    return schema
-
-
-def schema_get(data_adaptor):
-    schema = schema_get_helper(data_adaptor)
-    return make_response(jsonify({"schema": schema}), HTTPStatus.OK)
-
-
-def config_get(app_config, data_adaptor):
-    config = get_client_config(app_config, data_adaptor)
-    return make_response(jsonify(config), HTTPStatus.OK)
-
-
-def userinfo_get(app_config, data_adaptor):
-    config = get_client_userinfo(app_config, data_adaptor)
-    return make_response(jsonify(config), HTTPStatus.OK)
-
-
-def annotations_obs_get(request, data_adaptor):
-    fields = request.args.getlist("annotation-name", None)
-    num_columns_requested = len(data_adaptor.get_obs_keys()) if len(fields) == 0 else len(fields)
-    if data_adaptor.server_config.exceeds_limit("column_request_max", num_columns_requested):
-        return abort(HTTPStatus.BAD_REQUEST)
-    preferred_mimetype = request.accept_mimetypes.best_match(["application/octet-stream"])
-    if preferred_mimetype != "application/octet-stream":
-        return abort(HTTPStatus.NOT_ACCEPTABLE)
-
-    try:
-        labels = None
-        annotations = data_adaptor.dataset_config.user_annotations
-        if annotations.user_annotations_enabled():
-            labels = annotations.read_labels(data_adaptor)
-        fbs = data_adaptor.annotation_to_fbs_matrix(Axis.OBS, fields, labels)
-        return make_response(fbs, HTTPStatus.OK, {"Content-Type": "application/octet-stream"})
-    except KeyError as e:
-        return abort_and_log(HTTPStatus.BAD_REQUEST, str(e), include_exc_info=True)
-
-
-def annotations_put_fbs_helper(data_adaptor, fbs):
-    """helper function to write annotations from fbs"""
-    annotations = data_adaptor.dataset_config.user_annotations
-    if not annotations.user_annotations_enabled():
-        raise DisabledFeatureError("Writable annotations are not enabled")
-
-    new_label_df = decode_matrix_fbs(fbs)
-    if not new_label_df.empty:
-        new_label_df = data_adaptor.check_new_labels(new_label_df)
-    annotations.write_labels(new_label_df, data_adaptor)
-
-
-def inflate(data):
-    return zlib.decompress(data)
-
-
-def annotations_obs_put(request, data_adaptor):
-    annotations = data_adaptor.dataset_config.user_annotations
-    if not annotations.user_annotations_enabled():
-        return abort(HTTPStatus.NOT_IMPLEMENTED)
-
-    anno_collection = request.args.get("annotation-collection-name", default=None)
-    fbs = inflate(request.get_data())
-
-    if anno_collection is not None:
-        if not annotations.is_safe_collection_name(anno_collection):
-            return abort(HTTPStatus.BAD_REQUEST, "Bad annotation collection name")
-        annotations.set_collection(anno_collection)
-
-    try:
-        annotations_put_fbs_helper(data_adaptor, fbs)
-        res = json.dumps({"status": "OK"})
-        return make_response(res, HTTPStatus.OK, {"Content-Type": "application/json"})
-    except (ValueError, DisabledFeatureError, KeyError) as e:
-        return abort_and_log(HTTPStatus.BAD_REQUEST, str(e), include_exc_info=True)
-
-
-def annotations_var_get(request, data_adaptor):
-    fields = request.args.getlist("annotation-name", None)
-    num_columns_requested = len(data_adaptor.get_var_keys()) if len(fields) == 0 else len(fields)
-    if data_adaptor.server_config.exceeds_limit("column_request_max", num_columns_requested):
-        return abort(HTTPStatus.BAD_REQUEST)
-    preferred_mimetype = request.accept_mimetypes.best_match(["application/octet-stream"])
-    if preferred_mimetype != "application/octet-stream":
-        return abort(HTTPStatus.NOT_ACCEPTABLE)
-
-    try:
-        labels = None
-        return make_response(
-            data_adaptor.annotation_to_fbs_matrix(Axis.VAR, fields, labels),
-            HTTPStatus.OK,
-            {"Content-Type": "application/octet-stream"},
-        )
-    except KeyError as e:
-        return abort_and_log(HTTPStatus.BAD_REQUEST, str(e), include_exc_info=True)
-
-
-def data_var_put(request, data_adaptor):
-    preferred_mimetype = request.accept_mimetypes.best_match(["application/octet-stream"])
-    if preferred_mimetype != "application/octet-stream":
-        return abort(HTTPStatus.NOT_ACCEPTABLE)
-
-    filter_json = request.get_json()
-    filter = filter_json["filter"] if filter_json else None
-    try:
-        return make_response(
-            data_adaptor.data_frame_to_fbs_matrix(filter, axis=Axis.VAR),
-            HTTPStatus.OK,
-            {"Content-Type": "application/octet-stream"},
-        )
-    except (FilterError, ValueError, ExceedsLimitError) as e:
-        return abort_and_log(HTTPStatus.BAD_REQUEST, str(e), include_exc_info=True)
-
-
-def data_var_get(request, data_adaptor):
-    preferred_mimetype = request.accept_mimetypes.best_match(["application/octet-stream"])
-    if preferred_mimetype != "application/octet-stream":
-        return abort(HTTPStatus.NOT_ACCEPTABLE)
-
-    try:
-        filter = _query_parameter_to_filter(request.args)
-        return make_response(
-            data_adaptor.data_frame_to_fbs_matrix(filter, axis=Axis.VAR),
-            HTTPStatus.OK,
-            {"Content-Type": "application/octet-stream"},
-        )
-    except (FilterError, ValueError, ExceedsLimitError) as e:
-        return abort_and_log(HTTPStatus.BAD_REQUEST, str(e), include_exc_info=True)
-
-
-def colors_get(data_adaptor):
-    if not data_adaptor.dataset_config.presentation__custom_colors:
-        return make_response(jsonify({}), HTTPStatus.OK)
-    try:
-        return make_response(jsonify(data_adaptor.get_colors()), HTTPStatus.OK)
-    except ColorFormatException as e:
-        return abort_and_log(HTTPStatus.NOT_FOUND, str(e), include_exc_info=True)
-
-
-def diffexp_obs_post(request, data_adaptor):
-    if not data_adaptor.dataset_config.diffexp__enable:
-        return abort(HTTPStatus.NOT_IMPLEMENTED)
-
-    args = request.get_json()
-    try:
-        # TODO: implement varfilter mode
-        mode = DiffExpMode(args["mode"])
-
-        if mode == DiffExpMode.VAR_FILTER or "varFilter" in args:
-            return abort_and_log(HTTPStatus.NOT_IMPLEMENTED, "varFilter not enabled")
-
-        set1_filter = args.get("set1", {"filter": {}})["filter"]
-        set2_filter = args.get("set2", {"filter": {}})["filter"]
-        count = args.get("count", None)
-
-        if set1_filter is None or set2_filter is None or count is None:
-            return abort_and_log(HTTPStatus.BAD_REQUEST, "missing required parameter")
-        if Axis.VAR in set1_filter or Axis.VAR in set2_filter:
-            return abort_and_log(HTTPStatus.BAD_REQUEST, "var axis filter not enabled")
-
-    except (KeyError, TypeError) as e:
-        return abort_and_log(HTTPStatus.BAD_REQUEST, str(e), include_exc_info=True)
-
-    try:
-        diffexp = data_adaptor.diffexp_topN(set1_filter, set2_filter, count)
-        return make_response(diffexp, HTTPStatus.OK, {"Content-Type": "application/json"})
-    except (ValueError, DisabledFeatureError, FilterError, ExceedsLimitError) as e:
-        return abort_and_log(HTTPStatus.BAD_REQUEST, str(e), include_exc_info=True)
-    except JSONEncodingValueError:
-        # JSON encoding failure, usually due to bad data. Just let it ripple up
-        # to default exception handler.
-        current_app.logger.warning(JSON_NaN_to_num_warning_msg)
-        raise
-
-
-def layout_obs_get(request, data_adaptor):
-    fields = request.args.getlist("layout-name", None)
-    num_columns_requested = len(data_adaptor.get_embedding_names()) if len(fields) == 0 else len(fields)
-    if data_adaptor.server_config.exceeds_limit("column_request_max", num_columns_requested):
-        return abort(HTTPStatus.BAD_REQUEST)
-
-    preferred_mimetype = request.accept_mimetypes.best_match(["application/octet-stream"])
-    if preferred_mimetype != "application/octet-stream":
-        return abort(HTTPStatus.NOT_ACCEPTABLE)
-
-    try:
-        return make_response(
-            data_adaptor.layout_to_fbs_matrix(fields), HTTPStatus.OK, {"Content-Type": "application/octet-stream"}
-        )
-    except (KeyError, DatasetAccessError) as e:
-        return abort_and_log(HTTPStatus.BAD_REQUEST, str(e), include_exc_info=True)
-    except PrepareError:
-        return abort_and_log(
-            HTTPStatus.NOT_IMPLEMENTED,
-            f"No embedding available {request.path}",
-            loglevel=logging.ERROR,
-            include_exc_info=True,
-        )
-
-
-def genesets_get(request, data_adaptor):
-    preferred_mimetype = request.accept_mimetypes.best_match(["application/json", "text/csv"])
-    if preferred_mimetype not in ("application/json", "text/csv"):
-        return abort(HTTPStatus.NOT_ACCEPTABLE)
-
-    try:
-        annotations = data_adaptor.dataset_config.user_annotations
-        (genesets, tid) = annotations.read_gene_sets(data_adaptor)
-
-        if preferred_mimetype == "text/csv":
-            return make_response(
-                annotations.gene_sets_to_csv(genesets),
-                HTTPStatus.OK,
-                {
-                    "Content-Type": "text/csv",
-                    "Content-Disposition": "attachment; filename=genesets.csv",
-                },
-            )
-        else:
-            return make_response(
-                jsonify({"genesets": annotations.gene_sets_to_response(genesets), "tid": tid}), HTTPStatus.OK
-            )
-    except (ValueError, KeyError, AnnotationsError) as e:
-        return abort_and_log(HTTPStatus.BAD_REQUEST, str(e))
-
-
-def genesets_put(request, data_adaptor):
-    annotations = data_adaptor.dataset_config.user_annotations
-    if not annotations.gene_sets_save_enabled():
-        return abort(HTTPStatus.NOT_IMPLEMENTED)
-
-    anno_collection = request.args.get("annotation-collection-name", default=None)
-    if anno_collection is not None:
-        if not annotations.is_safe_collection_name(anno_collection):
-            return abort(HTTPStatus.BAD_REQUEST, "Bad annotation collection name")
-        annotations.set_collection(anno_collection)
-
-    args = request.get_json()
-    try:
-        genesets = args.get("genesets", None)
-        tid = args.get("tid", None)
-        if genesets is None:
-            abort(HTTPStatus.BAD_REQUEST)
-
-        annotations.write_gene_sets(genesets, tid, data_adaptor)
-        return make_response(jsonify({"status": "OK"}), HTTPStatus.OK)
-    except (ValueError, DisabledFeatureError, KeyError) as e:
-        return abort_and_log(HTTPStatus.BAD_REQUEST, str(e), include_exc_info=True)
-    except (ObsoleteRequest, TypeError) as e:
-        return abort(HTTPStatus.NOT_FOUND, description=str(e))
-
-
-def summarize_var_helper(request, data_adaptor, key, raw_query):
-    preferred_mimetype = request.accept_mimetypes.best_match(["application/octet-stream"])
-    if preferred_mimetype != "application/octet-stream":
-        return abort(HTTPStatus.NOT_ACCEPTABLE)
-
-    summary_method = request.values.get("method", default="mean")
-    query_hash = summarizeQueryHash(raw_query)
-    if key and query_hash != key:
-        return abort(HTTPStatus.BAD_REQUEST, description="query key did not match")
-
-    args_filter_only = request.values.copy()
-    args_filter_only.poplist("method")
-    args_filter_only.poplist("key")
-
-    try:
-        filter = _query_parameter_to_filter(args_filter_only)
-        return make_response(
-            data_adaptor.summarize_var(summary_method, filter, query_hash),
-            HTTPStatus.OK,
-            {"Content-Type": "application/octet-stream"},
-        )
-    except (ValueError) as e:
-        return abort(HTTPStatus.NOT_FOUND, description=str(e))
-    except (UnsupportedSummaryMethod, FilterError) as e:
-        return abort(HTTPStatus.BAD_REQUEST, description=str(e))
-
-
-def summarize_var_get(request, data_adaptor):
-    return summarize_var_helper(request, data_adaptor, None, request.query_string)
-
-
-def summarize_var_post(request, data_adaptor):
-    if not request.content_type or "application/x-www-form-urlencoded" not in request.content_type:
-        return abort(HTTPStatus.UNSUPPORTED_MEDIA_TYPE)
-    if request.content_length > 1_000_000:  # just a sanity check to avoid memory exhaustion
-        return abort(HTTPStatus.BAD_REQUEST)
-
-    key = request.args.get("key", default=None)
-    return summarize_var_helper(request, data_adaptor, key, request.get_data())

backend/server/common/utils/corpora_constants.py

@@ -1,22 +0,0 @@
-class CorporaConstants(object):
-    REQUIRED_SIMPLE_METADATA_FIELDS = [
-        "version",
-        "title",
-        "layer_descriptions",
-        "organism",
-        "organism_ontology_term_id",
-    ]
-
-    # The Corpora specification requires some values encoded as JSON due to the inability of AnnData to store complex
-    # types.
-    OPTIONAL_JSON_ENCODED_METADATA_FIELD = ["contributors", "project_links"]
-
-    OPTIONAL_SIMPLE_METADATA_FIELDS = [
-        "preprint_doi",
-        "publication_doi",
-        "default_embedding",
-        "default_field",
-        "tags",
-        "project_name",
-        "project_description",
-    ]

backend/server/converters/schema/gene_symbol.py

@@ -1,211 +0,0 @@
-"""Helpers for converting and checking HGNC gene symbols."""
-
-import argparse
-import enum
-import logging
-import os
-import re
-import numpy as np
-import pandas as pd
-
-
-def get_upgraded_var_index(var, hgnc_path=None):
-    """Given an anndata var dataframe, return a new index for the dataframe
-    where human gene symbols have been upgraded to the current HGNC set.
-    """
-
-    if not hgnc_path:
-        hgnc_path = os.path.join(os.path.dirname(os.path.realpath(__file__)), "hgnc_complete_set.txt.gz")
-
-    hgnc_symbol_checker = HGNCSymbolChecker.from_hgnc_records(hgnc_path)
-
-    return pd.Index([hgnc_symbol_checker.upgrade_symbol(s) for s in var.index])
-
-
-class SymbolStatus(enum.Enum):
-    """The status of a symbol in the HGNC database.
-
-    APPROVED: Currently a valid symbol
-    WITHDRAWN: A previously approved HGNC symbol for a gene that has since been shown
-               not to exist _unless_ that symbol is also approved
-    AMBIGUOUS: A symbol that is not approved but is an alias or previous symbol for
-               multiple approved symbols
-    UPGRADABLE: A symbol that is not approved but unambiguously maps to an approved
-                symbol
-    UNKNOWN: A symbol that does not appear in HGNC
-    """
-
-    APPROVED = 1
-    WITHDRAWN = 2
-    AMBIGUOUS = 3
-    UPGRADABLE = 4
-    UNKNOWN = 5
-
-
-class HGNCSymbolChecker:
-    """Handle checking and correcting HGNC symbols."""
-
-    def __init__(self, approved_symbols, withdrawn_symbols, ambiguous_symbols, symbol_map):
-        self.approved_symbols = approved_symbols
-        self.withdrawn_symbols = withdrawn_symbols
-        self.ambiguous_symbols = ambiguous_symbols
-        self.symbol_map = symbol_map
-
-    def print_symbol_map(self):
-        """Print out a map from old symbol to new symbol."""
-
-        for symbol_pair in self.symbol_map.items():
-            print("\t".join(symbol_pair))
-
-    def check_symbol(self, symbol):
-        """See if a symbol if approved or something else."""
-        if symbol in self.approved_symbols:
-            return SymbolStatus.APPROVED
-
-        if symbol in self.withdrawn_symbols:
-            return SymbolStatus.WITHDRAWN
-
-        if symbol in self.ambiguous_symbols:
-            return SymbolStatus.AMBIGUOUS
-
-        if symbol in self.symbol_map:
-            return SymbolStatus.UPGRADABLE
-
-        return SymbolStatus.UNKNOWN
-
-    def upgrade_symbol(self, symbol):
-        """Return the approved symbol for the given symbol.
-
-        If the symbol cannot be upgraded, just return the original symbol.
-        """
-
-        fixed_symbol, stripped_symbol = format_symbol(symbol)
-
-        if fixed_symbol in self.approved_symbols:
-            return fixed_symbol
-        elif fixed_symbol in self.symbol_map:
-            return self.symbol_map[fixed_symbol]
-        elif stripped_symbol in self.approved_symbols:
-            return stripped_symbol
-        elif stripped_symbol in self.symbol_map:
-            return self.symbol_map[stripped_symbol]
-
-        return symbol
-
-    @classmethod
-    def from_hgnc_records(cls, hgnc_dataset_path):
-        """Parse a hgnc database download into a HGNCSymbolChecker object."""
-
-        def all_symbols(record):
-            """Get all the symbols associated with an HGNC record including previous, alias,
-            and approved."""
-            yield format_symbol(record["symbol"])[0]
-            for symbol in alias_and_previous_symbols(record):
-                yield symbol
-
-        def alias_and_previous_symbols(record):
-            """Get alias and previous symbols from an HGNC record."""
-            for field in ("alias_symbol", "prev_symbol"):
-                if record[field] is not np.nan:
-                    for symbol in record[field].split("|"):
-                        yield format_symbol(symbol)[0]
-            # Sometimes something like HGNC:1234 appears in datasets, which we
-            # want to fix as well.
-            yield record["hgnc_id"]
-
-        hgnc_records = pd.read_csv(hgnc_dataset_path, sep="\t", header=0, low_memory=False).to_dict("records")
-
-        # Get all symbols that are currently approved.
-        approved_symbols = set()
-        for record in hgnc_records:
-            if record["status"] == "Approved":
-                approved_symbols.add(format_symbol(record["symbol"])[0])
-
-        # Get all symbols that have been withdrawn
-        withdrawn_symbols = set()
-        for record in hgnc_records:
-            if record["status"] == "Entry Withdrawn":
-                for symbol in all_symbols(record):
-                    withdrawn_symbols.add(symbol)
-
-        # If a symbol is both approved and withdrawn, be optimistic and call it approved
-        logging.warning(
-            f"Some symbols are simulaneously withdrawn and approved\n"
-            f"We will treat them at approved:\n"
-            f"{withdrawn_symbols.intersection(approved_symbols)}"
-        )
-        withdrawn_symbols = withdrawn_symbols.difference(approved_symbols)
-
-        # Now try to map from symbols that are not approved but are an alias or previous symbol for an approved symbol
-        alias_previous_to_approved = {}
-        ambiguous_symbols = set()
-
-        for record in hgnc_records:
-            if record["status"] == "Approved":
-
-                # The approved symbol is what we'll map to
-                approved_symbol = format_symbol(record["symbol"])[0]
-
-                for symbol in alias_and_previous_symbols(record):
-
-                    # If the alias or previous symbol is also an approved symbol,
-                    # we'll just leave it alone
-                    if symbol in approved_symbols:
-                        continue
-
-                    # If the alias or previous symbol maps to a different approved symbol, mark it as ambiguous
-                    if symbol in alias_previous_to_approved and alias_previous_to_approved[symbol] != approved_symbol:
-                        ambiguous_symbols.add(symbol)
-                    else:
-                        alias_previous_to_approved[symbol] = approved_symbol
-
-        # Remove all the ambiguous symbols from the map
-        for ambiguous_symbol in ambiguous_symbols:
-            alias_previous_to_approved.pop(ambiguous_symbol)
-
-        return HGNCSymbolChecker(approved_symbols, withdrawn_symbols, ambiguous_symbols, alias_previous_to_approved)
-
-
-def format_symbol(symbol):
-    """HGNC rules say symbols should all be upper case except for C#orf#. However, case is
-    variable in both alias and previous symbols as well as in the symbols we get in
-    submissions. So, upper case everything except for the one situation where mixed-case
-    is allowed, which are the genes like C2orf157.
-
-    Also, seurat and scanpy append ".1" or "-1" to duplicated gene names, and these altered
-    names persist throughout the life of the object. They won't match against the HGNC database
-    and we want to merge them, so we need to strip off the suffix and try matching again.
-
-    This function takes a symbol and returns the symbol with the fixed case and also with the
-    seurat/scanpy suffix stripped off.
-    """
-
-    match = re.match(r"^(C)(\d+)(orf)(\d+)$", symbol, re.IGNORECASE)
-
-    if match:
-        fixed_case = f"C{match.group(2)}orf{match.group(4)}"
-    else:
-        fixed_case = symbol.upper()
-
-    suffix_stripped = re.sub(r"[\.\-]\d+$", "", fixed_case)
-
-    return fixed_case, suffix_stripped
-
-
-def main():
-    """When called as main, parse a given hgnc download and print out a map from old to new
-    symbol.
-    """
-    parser = argparse.ArgumentParser()
-    parser.add_argument(
-        "hgnc_dataset", help="HGNC dataset tsv, available from www.genenames.org/download/statistics-and-files/"
-    )
-    args = parser.parse_args()
-
-    hgnc_symbol_checker = HGNCSymbolChecker.from_hgnc_records(args.hgnc_dataset)
-
-    hgnc_symbol_checker.print_symbol_map()
-
-
-if __name__ == "__main__":
-    main()

backend/server/converters/schema/ontology.py

@@ -1,86 +0,0 @@
-"""Methods for working with ontologies and the OLS."""
-from urllib.parse import quote_plus
-
-import requests
-
-OLS_API_ROOT = "http://www.ebi.ac.uk/ols/api"
-
-# Curie means something like CL:0000001
-
-
-def _ontology_name(curie):
-    """Get the name of the ontology from the curie, CL or UBERON for example."""
-    return curie.split(":")[0]
-
-
-def _ontology_value(curie):
-    """Get the id component of the curie, 0000001 from CL:0000001 for example."""
-    return curie.split(":")[1]
-
-
-def _double_encode(url):
-    """Double url encode a url. This is required by the OLS API."""
-    return quote_plus(quote_plus(url))
-
-
-def _iri(curie):
-    """Get the iri from a curie. This is a bit hopeful that they all map to purl.obolibrary.org"""
-    if _ontology_name(curie) == "EFO":
-        return f"http://www.ebi.ac.uk/efo/EFO_{_ontology_value(curie)}"
-    return f"http://purl.obolibrary.org/obo/{_ontology_name(curie)}_{_ontology_value(curie)}"
-
-
-class OntologyLookupError(Exception):
-    """Exception for some problem with looking up ontology information."""
-
-
-def _ontology_info_url(curie):
-    """Get the to make a GET to to get information about an ontology term."""
-
-    # If the curie is empty, just return an empty string. This happens when there is no
-    # valid ontology value.
-    if not curie:
-        return ""
-    else:
-        return f"{OLS_API_ROOT}/ontologies/{_ontology_name(curie)}/terms/{_double_encode(_iri(curie))}"
-
-
-def get_ontology_label(curie):
-    """For a given curie like 'CL:1000413', get the label like 'endothelial cell of artery'"""
-
-    url = _ontology_info_url(curie)
-
-    if not url:
-        return ""
-
-    response = requests.get(url)
-
-    if not response.ok:
-        raise OntologyLookupError(
-            f"Curie {curie} lookup failed, got status code {response.status_code}: {response.text}"
-        )
-    return response.json()["label"]
-
-
-def lookup_candidate_term(label, ontology="cl", method="select"):
-    """Lookup candidate terms for a label. This is useful when there is an existing label in a
-    submitted dataset, and you want to find an appropriate ontology term.
-
-    Args:
-      label: the label to find ontology terms for
-      ontology: the ontology to search in, cl or uberon or efo for example
-      method: select or search. search provides much broader results
-
-    Returns:
-      list of (curie, label) tuples returned by OLS
-    """
-    # using OLS REST API [https://www.ebi.ac.uk/ols/docs/api]
-    url = f"{OLS_API_ROOT}/{method}?q={quote_plus(label)}&ontology={ontology.lower()}"
-    response = requests.get(url)
-
-    if not response.ok:
-        raise OntologyLookupError(
-            f"Label {label} lookup failed, got status code {response.status_code}: {response.text}"
-        )
-
-    return [(r["obo_id"], r["label"]) for r in response.json()["response"]["docs"]]

backend/server/converters/schema/remix.py

@@ -1,264 +0,0 @@
-import argparse
-import collections
-import json
-import logging
-import math
-import string
-
-import anndata
-import numpy as np
-import pandas as pd
-import yaml
-
-from . import gene_symbol
-from . import ontology
-from . import validate
-
-REPLACE_SUFFIX = "_original"
-ONTOLOGY_SUFFIX = "_ontology_term_id"
-
-
-def is_curie(value):
-    """Return True iff the value is an OBO-id CURIE like EFO:000001"""
-    return (value.count(":")
-            and all(len(part) > 0 for part in value.split(":"))
-            and all(c in string.digits for c in value.split(":")[1]))
-
-
-def is_ontology_field(field_name):
-    """Return True iff the field_name is an ontology field like tissue_ontology_term_id"""
-    return field_name.endswith(ONTOLOGY_SUFFIX)
-
-
-def get_label_field_name(field_name):
-    """Get the associated label field from an ontology field, assay_ontology_term_id --> assay"""
-    return field_name[: -len(ONTOLOGY_SUFFIX)]
-
-
-def split_suffix(maybe_curie):
-    """Split off the (cell culture) or (organoid) suffix."""
-
-    suffixes = [" (cell culture)", " (organoid)"]
-    for suffix in suffixes:
-        if maybe_curie.endswith(suffix):
-            return maybe_curie[:-len(suffix)], suffix
-    return maybe_curie, ""
-
-
-def get_curie_and_label(maybe_curie):
-    """Given a string that might be a curie, return a (curie, label) pair"""
-
-    maybe_curie, suffix = split_suffix(maybe_curie)
-    if not is_curie(maybe_curie):
-        return ("", maybe_curie + suffix)
-    return (maybe_curie + suffix, ontology.get_ontology_label(maybe_curie) + suffix)
-
-
-def safe_add_field(adata_attr, field_name, field_value):
-    """Add a field and value to an AnnData, but don't clobber an exising value."""
-
-    if (
-        isinstance(field_value, list)
-        and field_value
-        and isinstance(field_value[0], dict)
-    ):
-        field_value = json.dumps(field_value)
-    if field_name in adata_attr:
-        adata_attr[field_name + REPLACE_SUFFIX] = adata_attr[field_name]
-    adata_attr[field_name] = field_value
-
-
-def remix_uns(adata, uns_config):
-    """Add fields from the config to adata.uns"""
-    for field_name, field_value in uns_config.items():
-
-        if is_ontology_field(field_name):
-            # If it's an ontology field, look it up
-            label_field_name = get_label_field_name(field_name)
-            ontology_term, ontology_label = get_curie_and_label(field_value)
-            safe_add_field(adata.uns, field_name, ontology_term)
-            safe_add_field(adata.uns, label_field_name, ontology_label)
-        else:
-            safe_add_field(adata.uns, field_name, field_value)
-
-
-def remix_obs(adata, obs_config):
-    """Add fields from the config to adata.obs"""
-
-    for field_name, field_value in obs_config.items():
-
-        if isinstance(field_value, dict):
-            # If the value is a dict, that means we are supposed to map from an
-            # existing column to the new one
-            source_column, column_map = next(iter(field_value.items()))
-            nan_value = None
-            for key in column_map:
-                if isinstance(key, float) and math.isnan(key):
-                    nan_value = column_map[key]
-            if nan_value is not None:
-                column_map["nan"] = nan_value
-
-            for key in column_map:
-                if key not in adata.obs[source_column].unique():
-                    logging.warning(f'Key {key} not in adata.obs["{source_column}"]')
-
-            for value in adata.obs[source_column].unique():
-                if value not in column_map:
-                    logging.warning(f'Value {value} in adata.obs["{source_column}"] not in translation dict')
-
-            if is_ontology_field(field_name):
-                ontology_term_map, ontology_label_map = {}, {}
-                logging.info(f"Looking up labels for {field_name}")
-                for original_value, maybe_curie in column_map.items():
-                    curie, label = get_curie_and_label(maybe_curie)
-                    ontology_term_map[original_value] = curie
-                    ontology_label_map[original_value] = label
-                    logging.info(f"Mapping {original_value} -> {curie} -> {label}")
-
-                ontology_column = adata.obs[source_column].replace(
-                    ontology_term_map, inplace=False
-                )
-                label_column = adata.obs[source_column].replace(
-                    ontology_label_map, inplace=False
-                )
-
-                safe_add_field(adata.obs, field_name, ontology_column)
-                safe_add_field(
-                    adata.obs, get_label_field_name(field_name), label_column
-                )
-            else:
-                label_column = adata.obs[source_column].replace(
-                    column_map, inplace=False
-                )
-                safe_add_field(adata.obs, field_name, label_column)
-
-        else:
-            if is_ontology_field(field_name):
-                # If it's an ontology field, look it up
-                label_field_name = get_label_field_name(field_name)
-                ontology_term, ontology_label = get_curie_and_label(field_value)
-                safe_add_field(adata.obs, field_name, ontology_term)
-                safe_add_field(adata.obs, label_field_name, ontology_label)
-            else:
-                safe_add_field(adata.obs, field_name, field_value)
-
-
-def merge_df(df, domain, index, columns):
-    """
-    Given a dataframe with duplicate column labels, merge and return a dataframe where
-    the duplicates have been merged together, resulting in a dataframe with unique column
-    labels.
-
-    "merge" depends on the value of domain. If the domain is "raw", then duplicate columns
-    can just be summed. If it's "log1p" or "sqrt", it needs to be exp1m'd or squared, then
-    summed, and then logged or sqrt'd again.
-    """
-
-    if not isinstance(df, np.ndarray):
-        to_merge = df.toarray()
-    else:
-        to_merge = df
-    if domain == "raw":
-        merged_df = pd.DataFrame(to_merge, index=index, columns=columns).sum(
-            axis=1, level=0, skipna=False
-        )
-    elif domain == "log1p":
-        merged_df = (
-            pd.DataFrame(np.expm1(to_merge, dtype=np.float128), index=index, columns=columns)
-            .sum(axis=1, level=0, skipna=False)
-        )
-        merged_df = pd.DataFrame(np.log1p(merged_df.to_numpy()), index=merged_df.index, columns=merged_df.columns)
-    elif domain == "sqrt":
-        merged_df = (
-            pd.DataFrame(np.square(to_merge), index=index, columns=columns)
-            .sum(axis=1, level=0, skipna=False)
-        )
-        merged_df = pd.DataFrame(np.sqrt(merged_df.to_numpy()), index=merged_df.index, columns=merged_df.columns)
-
-    return merged_df
-
-
-def fixup_gene_symbols(adata, fixup_config):
-    """Update the var index to hold a consistent set of HGNC gene symbols."""
-
-    upgraded_var_index = gene_symbol.get_upgraded_var_index(adata.var)
-
-    merged_X = merge_df(adata.X, fixup_config["X"], adata.obs.index, upgraded_var_index)
-    fixup_adata = anndata.AnnData(
-        X=merged_X,
-        obs=adata.obs,
-        var=merged_X.columns.to_frame(name="hgnc_gene_symbol"),
-        uns=adata.uns,
-        obsm=adata.obsm,
-    )
-
-    for layer, domain in fixup_config.items():
-        if layer == "X":
-            continue
-        if layer == "raw.X":
-            df = adata.raw.X
-        else:
-            df = adata.layers[layer]
-
-        merged_df = merge_df(df, domain, adata.obs.index, upgraded_var_index)
-        assert merged_df.index.equals(merged_X.index)
-        assert merged_df.columns.equals(merged_X.columns)
-
-        if domain == "raw":
-            fixup_raw = anndata.AnnData(
-                X=merged_df,
-                obs=adata.obs,
-                var=merged_X.columns.to_frame(name="hgnc_gene_symbol"),
-            )
-            fixup_adata.raw = fixup_raw
-        else:
-            fixup_adata.layers[layer] = merged_df
-
-    return fixup_adata
-
-def _strip_version(adata):
-    """Remove version information from the AnnData object."""
-
-    if "version" in adata.uns_keys():
-        del adata.uns["version"]
-
-def apply_schema(source_h5ad, remix_config, output_filename):
-
-    try:
-        import scanpy
-    except ImportError:
-        raise ImportError("scanpy must be installed for cellxgene schema")
-    adata = scanpy.read_h5ad(source_h5ad)
-    config = yaml.load(open(remix_config), Loader=yaml.FullLoader)
-    remix_uns(adata, config["uns"])
-    remix_obs(adata, config["obs"])
-
-    if config.get("fixup_gene_symbols"):
-        adata = fixup_gene_symbols(adata, config["fixup_gene_symbols"])
-
-    if ("version" in adata.uns_keys()
-            and isinstance(adata.uns["version"], collections.Mapping)
-            and "corpora_schema_version" in adata.uns["version"]):
-        schema_version = adata.uns["version"]["corpora_schema_version"]
-        try:
-            validate.get_schema_definition(schema_version)
-        except ValueError:
-            logging.warning(f"Stripping version information out of AnnData because schema "
-                            f"version {schema_version} is unknown.")
-            _strip_version(adata)
-
-        if not validate.validate_adata(adata, shallow=False):
-            logging.warning(f"Stripping version information out of AnnData because it does not "
-                            f"follow schema version {schema_version} .")
-            _strip_version(adata)
-
-    adata.write_h5ad(output_filename, compression="gzip")
-
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser()
-    parser.add_argument("--source-h5ad", required=True)
-    parser.add_argument("--remix-config", required=True)
-    parser.add_argument("--output-filename", required=True)
-    args = parser.parse_args()
-    apply_schema(args.source_h5ad, args.remix_config, args.output_filename)

backend/server/converters/schema/schema_definitions/1_0_0.yaml

@@ -1,95 +0,0 @@
-title: Corpora schema version 1.0.0
-type: anndata
-components:
-    uns:
-        type: dict
-        keys:
-            version:
-                type: dict
-                keys:
-                    corpora_schema_version: null
-                    corpora_encoding_version: null
-            title:
-                type: string
-            contributors:
-                type: stringified list of dicts
-            layer_descriptions:
-                type: dict
-                keys:
-                    X: null
-            organism:
-                type: string
-                nullable: false
-            organism_ontology_term_id:
-                type: curie
-                prefixes:
-                    - NCBITaxon
-    var:
-        type: dataframe
-        index:
-            type: human-readable string
-            unique: true
-    obs:
-        type: dataframe
-        index:
-            unique: true
-        columns:
-            tissue:
-                type: human-readable string
-                nullable: false
-            tissue_ontology_term_id:
-                type: suffixed curie
-                nullable: true
-                prefixes:
-                    - UBERON
-            assay:
-                type: human-readable string
-                nullable: false
-            assay_ontology_term_id:
-                type: curie
-                nullable: true
-                prefixes:
-                    - EFO
-            disease:
-                type: human-readable string
-                nullable: false
-            disease_ontology_term_id:
-                type: curie
-                nullable: true
-                prefixes:
-                    - MONDO
-                    - PATO
-            cell_type:
-                type: human-readable string
-                nullable: false
-            cell_type_ontology_term_id:
-                type: curie
-                nullable: true
-                prefixes:
-                    - CL
-                    - UBERON
-            sex:
-                type: string
-                enum:
-                    - male
-                    - female
-                    - mixed
-                    - unknown
-                    - other
-            ethnicity:
-                type: human-readable string
-                nullable: false
-            ethnicity_ontology_term_id:
-                type: curie
-                nullable: true
-                prefixes:
-                    - HANCESTRO
-            development_stage:
-                type: human-readable string
-                nullable: false
-            development_stage_ontology_term_id:
-                type: curie
-                nullable: true
-                prefixes:
-                    - HsapDv
-                    - EFO

backend/server/converters/schema/schema_definitions/1_1_0.yaml

@@ -1,93 +0,0 @@
-title: Corpora schema version 1.1.0
-type: anndata
-components:
-    uns:
-        type: dict
-        keys:
-            version:
-                type: dict
-                keys:
-                    corpora_schema_version: null
-                    corpora_encoding_version: null
-            title:
-                type: string
-            layer_descriptions:
-                type: dict
-                keys:
-                    X: null
-            organism:
-                type: string
-                nullable: false
-            organism_ontology_term_id:
-                type: curie
-                prefixes:
-                    - NCBITaxon
-    var:
-        type: dataframe
-        index:
-            type: human-readable string
-            unique: true
-    obs:
-        type: dataframe
-        index:
-            unique: true
-        columns:
-            tissue:
-                type: human-readable string
-                nullable: false
-            tissue_ontology_term_id:
-                type: suffixed curie
-                nullable: true
-                prefixes:
-                    - UBERON
-            assay:
-                type: human-readable string
-                nullable: false
-            assay_ontology_term_id:
-                type: curie
-                nullable: true
-                prefixes:
-                    - EFO
-            disease:
-                type: human-readable string
-                nullable: false
-            disease_ontology_term_id:
-                type: curie
-                nullable: true
-                prefixes:
-                    - MONDO
-                    - PATO
-            cell_type:
-                type: human-readable string
-                nullable: false
-            cell_type_ontology_term_id:
-                type: curie
-                nullable: true
-                prefixes:
-                    - CL
-                    - UBERON
-            sex:
-                type: string
-                enum:
-                    - male
-                    - female
-                    - mixed
-                    - unknown
-                    - other
-            ethnicity:
-                type: human-readable string
-                nullable: false
-            ethnicity_ontology_term_id:
-                type: curie
-                nullable: true
-                prefixes:
-                    - HANCESTRO
-            development_stage:
-                type: human-readable string
-                nullable: false
-            development_stage_ontology_term_id:
-                type: curie
-                nullable: true
-                prefixes:
-                    - HsapDv
-                    - EFO

backend/server/converters/schema/validate.py

@@ -1,236 +0,0 @@
-import json
-import re
-import os
-import sys
-
-import pandas as pd
-import yaml
-
-
-def _is_null(v):
-    """Return True if v is null, for one of the multiple ways a "null" value shows up in an h5ad."""
-    return pd.isnull(v) or (hasattr(v, "__len__") and len(v) == 0)
-
-
-def _validate_stringified_list_of_dicts(s):
-    """Verify that a string can be parsed into a list.
-
-    We have some types that are lists of dicts. Those cannot be stored directly in an h5ad, so we have to
-    json.dumps them. This verifies that we can load them back.
-    """
-
-    try:
-        list_ = json.loads(s)
-        if not isinstance(list_, list):
-            return False
-        for el in list_:
-            if not isinstance(el, dict):
-                return False
-        return True
-    except (json.JSONDecodeError, TypeError):
-        pass
-    return False
-
-
-def _validate_human_readable_string(s):
-    """Verify that a string is human-readable.
-
-    There are parts of the schema where a "human-readable" string is required. "Human-readable" is kind
-    of vague and subjective. I feel like I can read many strings. So here we just check for the main ways
-    that fails: someone puts in an ontology term id or and ensembl gene/transcript id.
-
-    Returns False if s is not a string or is one of those bad string types.
-    """
-
-    return isinstance(s, str) and (not re.match(r"[A-Z]\w+:\d+", s)) and (not re.match(r"ENS[GT]\d+$", s))
-
-
-def _validate_curie(c, prefixes):
-    """Verify that a string is a valid compact URI, like EFO:000001. If prefixes is not empty, make sure the
-    prefix of the curies is in prefixes.
-    """
-
-    if not c:
-        return True
-
-    match = re.match(r"([A-Z]\w+):\d+$", c)
-
-    if prefixes:
-        return match and match.group(1) in prefixes
-    else:
-        return match
-
-
-def _validate_suffixed_curie(c, prefixes):
-    """Verify that a string is a compact URI with an optional suffix like 'EFO:00001 (cell culture)'"""
-
-    # Pull off the suffix
-    suffix = re.findall(r"\ \(.*\)$", c)
-    if suffix:
-        c = c[: -len(suffix[0])]
-    return _validate_curie(c, prefixes)
-
-
-def _validate_column(column, column_name, df_name, schema_def):
-    """Given a schema definition and the column of a dataframe, verify that the column satifies
-    the schema.
-    """
-
-    errors = []
-
-    if schema_def.get("unique"):
-        if column.nunique() != len(column):
-            errors.append(f"Column {column_name} in dataframe {df_name} is not unique.")
-
-    if "nullable" in schema_def and not schema_def["nullable"]:
-        if any(_is_null(v) for v in column):
-            errors.append(f"Column {column_name} in dataframe {df_name} contains empty values.")
-
-    if schema_def.get("type") == "human-readable string":
-        non_readables = [v for v in column if not _validate_human_readable_string(v)]
-        if non_readables:
-            errors.append(
-                f"Column {column_name} in dataframe {df_name} contains non-human-readable "
-                f"values like {non_readables[0]}"
-            )
-
-    if schema_def.get("type") in ("curie", "suffixed curie"):
-        validation_func = _validate_curie if schema_def.get("type") == "curie" else _validate_suffixed_curie
-        non_valid_curies = [v for v in column if not validation_func(v, schema_def.get("prefixes"))]
-        if non_valid_curies:
-            errors.append(
-                f"Column {column_name} in dataframe {df_name} contains invalid ontology values like "
-                f"{non_valid_curies[0]}."
-            )
-            if "prefixes" in schema_def:
-                errors[-1] += f" Values must be curies from one of these ontologies {schema_def['prefixes']}."
-
-    if "enum" in schema_def:
-        bad_enums = [v for v in column if v not in schema_def["enum"]]
-        if bad_enums:
-            errors.append(
-                f"Column {column_name} in dataframe {df_name} contains unpermitted values like "
-                f"{bad_enums[0]}. Values must be one of {schema_def['enum']}."
-            )
-
-    return errors
-
-
-def _validate_dict(dict_, dict_name, schema_def):
-    """Given a schema definition and dict, verify that the dict satifies the schema."""
-
-    errors = []
-
-    for key in schema_def.get("keys", []):
-        if key not in dict_:
-            errors.append(f"{dict_name} is missing key {key}.")
-        elif schema_def["keys"][key]:
-            if schema_def["keys"][key]["type"] == "stringified list of dicts":
-                if not _validate_stringified_list_of_dicts(dict_[key]):
-                    errors.append(
-                        f"Key {key} in {dict_name} should be a JSON-encoded list of dicts, but it is {dict_[key]}"
-                    )
-            elif schema_def["keys"][key]["type"] == "dict":
-                errors.extend(_validate_dict(dict_[key], key, schema_def["keys"][key]))
-            elif schema_def["keys"][key]["type"] == "curie":
-                if not _validate_curie(dict_[key], schema_def["keys"][key]["prefixes"]):
-                    errors.append(f"Key {key} in {dict_name} contains invalid ontology value.")
-            if "nullable" in schema_def["keys"][key] and not schema_def["keys"][key]["nullable"]:
-                if _is_null(dict_[key]):
-                    errors.append(f"Key {key} in dict {dict_name} is an empty value.")
-
-    return errors
-
-
-def _validate_dataframe(df, df_name, schema_def):
-    """Given a dataframe and schema definition, verify that the dataframe follows the schema."""
-
-    errors = []
-
-    if "index" in schema_def:
-        errors.extend(_validate_column(df.index, "index", df_name, schema_def["index"]))
-
-    for column in schema_def.get("columns", []):
-        if column not in df.columns:
-            errors.append(f"Dataframe {df_name} is missing column {column}.")
-        else:
-            errors.extend(_validate_column(df[column], column, df_name, schema_def["columns"][column]))
-
-    return errors
-
-
-def get_schema_definition(version):
-    """Look up and read a schema definition based on a version number like "1.0.0"."""
-
-    path = os.path.join(
-        os.path.dirname(os.path.realpath(__file__)), "schema_definitions", version.replace(".", "_") + ".yaml"
-    )
-
-    if not os.path.isfile(path):
-        raise ValueError(f"No definition for version {version} found.")
-
-    return yaml.load(open(path), Loader=yaml.FullLoader)
-
-
-def deep_check(adata, schema_def):
-    """Perform a "deep" check of the AnnData object using the schema definition.
-
-    This checks all the columns and unstructured metadata rather than just the version.
-
-    Returns a list of error messages. If that list is empty, the object passed validation.
-    """
-
-    errors = []
-
-    for component, component_def in schema_def["components"].items():
-        if component_def["type"] == "dataframe":
-            errors.extend(_validate_dataframe(getattr(adata, component), component, component_def))
-        elif component_def["type"] == "dict":
-            errors.extend(_validate_dict(getattr(adata, component), component, component_def))
-        else:
-            raise ValueError(f"Unexpected component type {component['type']}")
-
-    return errors
-
-
-def validate_adata(adata, shallow):
-    """Validate an AnnData object. If shallow, just check that the required version information is
-    present.
-    """
-
-    # Does it have the version information written into uns?
-    if "version" not in adata.uns_keys() or "corpora_schema_version" not in adata.uns["version"]:
-        print("AnnData file is missing corpora version information")
-        return False
-
-    # We can stop here if it's a "shallow" check, that is, if we're just
-    # checking that version is present.
-    if shallow:
-        return True
-
-    schema_def = get_schema_definition(adata.uns["version"]["corpora_schema_version"])
-
-    errors = deep_check(adata, schema_def)
-
-    for error in errors:
-        print(error)
-
-    return not errors
-
-
-def validate(h5ad_path, shallow=False):
-    """Entry point for validation."""
-
-    try:
-        import scanpy
-    except ImportError:
-        raise ImportError("scanpy must be installed for cellxgene schema")
-
-    try:
-        adata = scanpy.read_h5ad(h5ad_path, backed="r")
-    except (OSError, TypeError):
-        print(f"Unable to open {h5ad_path} with scanpy.")
-        sys.exit(1)
-
-    if not validate_adata(adata, shallow):
-        sys.exit(1)

backend/server/data_anndata/anndata_adaptor.py

@@ -1,373 +0,0 @@
-import warnings
-
-import anndata
-import numpy as np
-from packaging import version
-from pandas.core.dtypes.dtypes import CategoricalDtype
-from scipy import sparse
-
-import backend.common.compute.diffexp_generic as diffexp_generic
-import backend.common.compute.estimate_distribution as estimate_distribution
-from backend.common.colors import convert_anndata_category_colors_to_cxg_category_colors
-from backend.common.constants import Axis, MAX_LAYOUTS, XApproximateDistribution
-from backend.server.common.corpora import corpora_get_props_from_anndata
-from backend.common.errors import PrepareError, DatasetAccessError
-from backend.common.utils.type_conversion_utils import get_schema_type_hint_of_array
-from backend.server.data_common.data_adaptor import DataAdaptor
-from backend.common.fbs.matrix import encode_matrix_fbs
-
-anndata_version = version.parse(str(anndata.__version__)).release
-
-
-def anndata_version_is_pre_070():
-    major = anndata_version[0]
-    minor = anndata_version[1] if len(anndata_version) > 1 else 0
-    return major == 0 and minor < 7
-
-
-class AnndataAdaptor(DataAdaptor):
-    def __init__(self, data_locator, app_config=None, dataset_config=None):
-        super().__init__(data_locator, app_config, dataset_config)
-        self.data = None
-        self.X_approximate_distribution = None
-        self._load_data(data_locator)
-        self._validate_and_initialize()
-
-    def cleanup(self):
-        pass
-
-    @staticmethod
-    def pre_load_validation(data_locator):
-        if data_locator.islocal():
-            # if data locator is local, apply file system conventions and other "cheap"
-            # validation checks.  If a URI, defer until we actually fetch the data and
-            # try to read it.  Many of these tests don't make sense for URIs (eg, extension-
-            # based typing).
-            if not data_locator.exists():
-                raise DatasetAccessError("does not exist")
-            if not data_locator.isfile():
-                raise DatasetAccessError("is not a file")
-
-    @staticmethod
-    def file_size(data_locator):
-        return data_locator.size() if data_locator.islocal() else 0
-
-    @staticmethod
-    def open(data_locator, app_config, dataset_config=None):
-        return AnndataAdaptor(data_locator, app_config, dataset_config)
-
-    def get_corpora_props(self):
-        return corpora_get_props_from_anndata(self.data)
-
-    def get_name(self):
-        return "cellxgene anndata adaptor version"
-
-    def get_library_versions(self):
-        return dict(anndata=str(anndata.__version__))
-
-    @staticmethod
-    def _create_unique_column_name(df, col_name_prefix):
-        """given the columns of a dataframe, and a name prefix, return a column name which
-        does not exist in the dataframe, AND which is prefixed by `prefix`
-
-        The approach is to append a numeric suffix, starting at zero and increasing by
-        one, until an unused name is found (eg, prefix_0, prefix_1, ...).
-        """
-        suffix = 0
-        while f"{col_name_prefix}{suffix}" in df:
-            suffix += 1
-        return f"{col_name_prefix}{suffix}"
-
-    def _alias_annotation_names(self):
-        """
-        The front-end relies on the existance of a unique, human-readable
-        index for obs & var (eg, var is typically gene name, obs the cell name).
-        The user can specify these via the --obs-names and --var-names config.
-        If they are not specified, use the existing index to create them, giving
-        the resulting column a unique name (eg, "name").
-
-        In both cases, enforce that the result is unique, and communicate the
-        index column name to the front-end via the obs_names and var_names config
-        (which is incorporated into the schema).
-        """
-        self.original_obs_index = self.data.obs.index
-
-        for (ax_name, var_name) in ((Axis.OBS, "obs"), (Axis.VAR, "var")):
-            config_name = f"single_dataset__{var_name}_names"
-            parameter_name = f"{var_name}_names"
-            name = getattr(self.server_config, config_name)
-            df_axis = getattr(self.data, str(ax_name))
-            if name is None:
-                # Default: create unique names from index
-                if not df_axis.index.is_unique:
-                    raise KeyError(
-                        f"Values in {ax_name}.index must be unique. "
-                        "Please prepare data to contain unique index values, or specify an "
-                        "alternative with --{ax_name}-name."
-                    )
-                name = self._create_unique_column_name(df_axis.columns, "name_")
-                self.parameters[parameter_name] = name
-                # reset index to simple range; alias name to point at the
-                # previously specified index.
-                df_axis.rename_axis(name, inplace=True)
-                df_axis.reset_index(inplace=True)
-            elif name in df_axis.columns:
-                # User has specified alternative column for unique names, and it exists
-                if not df_axis[name].is_unique:
-                    raise KeyError(
-                        f"Values in {ax_name}.{name} must be unique. " "Please prepare data to contain unique values."
-                    )
-                df_axis.reset_index(drop=True, inplace=True)
-                self.parameters[parameter_name] = name
-            else:
-                # user specified a non-existent column name
-                raise KeyError(f"Annotation name {name}, specified in --{ax_name}-name does not exist.")
-
-    def _create_schema(self):
-        self.schema = {
-            "dataframe": {
-                "nObs": self.cell_count,
-                "nVar": self.gene_count,
-                **get_schema_type_hint_of_array(self.data.X),
-            },
-            "annotations": {
-                "obs": {"index": self.parameters.get("obs_names"), "columns": []},
-                "var": {"index": self.parameters.get("var_names"), "columns": []},
-            },
-            "layout": {"obs": []},
-        }
-        for ax in Axis:
-            curr_axis = getattr(self.data, str(ax))
-            for ann in curr_axis:
-                ann_schema = {"name": ann, "writable": False}
-                ann_schema.update(get_schema_type_hint_of_array(curr_axis[ann]))
-                self.schema["annotations"][ax]["columns"].append(ann_schema)
-
-        for layout in self.get_embedding_names():
-            layout_schema = {"name": layout, "type": "float32", "dims": [f"{layout}_0", f"{layout}_1"]}
-            self.schema["layout"]["obs"].append(layout_schema)
-
-    def get_schema(self):
-        return self.schema
-
-    def _load_data(self, data_locator):
-        # as of AnnData 0.6.19, backed mode performs initial load fast, but at the
-        # cost of significantly slower access to X data.
-        try:
-            # there is no guarantee data_locator indicates a local file.  The AnnData
-            # API will only consume local file objects.  If we get a non-local object,
-            # make a copy in tmp, and delete it after we load into memory.
-            with data_locator.local_handle() as lh:
-                # as of AnnData 0.6.19, backed mode performs initial load fast, but at the
-                # cost of significantly slower access to X data.
-                backed = "r" if self.server_config.adaptor__anndata_adaptor__backed else None
-                self.data = anndata.read_h5ad(lh, backed=backed)
-
-        except ValueError:
-            raise DatasetAccessError(
-                "File must be in the .h5ad format. Please read "
-                "https://github.com/theislab/scanpy_usage/blob/master/170505_seurat/info_h5ad.md to "
-                "learn more about this format. You may be able to convert your file into this format "
-                "using `cellxgene prepare`, please run `cellxgene prepare --help` for more "
-                "information."
-            )
-        except MemoryError:
-            raise DatasetAccessError("Out of memory - file is too large for available memory.")
-        except Exception:
-            raise DatasetAccessError(
-                "File not found or is inaccessible. File must be an .h5ad object. "
-                "Please check your input and try again."
-            )
-
-    def _validate_and_initialize(self):
-        if anndata_version_is_pre_070():
-            warnings.warn(
-                "Use of anndata versions older than 0.7 will have serious issues. Please update to at "
-                "least anndata 0.7 or later."
-            )
-
-        # var and obs column names must be unique
-        if not self.data.obs.columns.is_unique or not self.data.var.columns.is_unique:
-            raise KeyError("All annotation column names must be unique.")
-
-        self._alias_annotation_names()
-        self._validate_data_types()
-        self.cell_count = self.data.shape[0]
-        self.gene_count = self.data.shape[1]
-        self._create_schema()
-
-        if self.dataset_config.X_approximate_distribution == "auto":
-            """Lazy evaluate the heuristic if we are backed."""
-            if not self.data.isbacked:
-                self.X_approximate_distribution = estimate_distribution.estimate_approximate_distribution(self.data.X)
-        else:
-            self.X_approximate_distribution = self.dataset_config.X_approximate_distribution
-
-        # heuristic
-        n_values = self.data.shape[0] * self.data.shape[1]
-        if (n_values > 1e8 and self.server_config.adaptor__anndata_adaptor__backed is True) or (n_values > 5e8):
-            self.parameters.update({"diffexp_may_be_slow": True})
-
-    def _is_valid_layout(self, arr):
-        """return True if this layout data is a valid array for front-end presentation:
-        * ndarray, dtype float/int/uint
-        * with shape (n_obs, >= 2)
-        * with all values finite or NaN (no +Inf or -Inf)
-        """
-        is_valid = type(arr) == np.ndarray and arr.dtype.kind in "fiu"
-        is_valid = is_valid and arr.shape[0] == self.data.n_obs and arr.shape[1] >= 2
-        is_valid = is_valid and not np.any(np.isinf(arr)) and not np.all(np.isnan(arr))
-        return is_valid
-
-    def _validate_data_types(self):
-        # The backed API does not support interrogation of the underlying sparsity or sparse matrix type
-        # Fake it by asking for a small subarray and testing it.   NOTE: if the user has ignored our
-        # anndata <= 0.7 warning, opted for the --backed option, and specified a large, sparse dataset,
-        # this "small" indexing request will load the entire X array. This is due to a bug in anndata<=0.7
-        # which will load the entire X matrix to fullfill any slicing request if X is sparse.  See
-        # user warning in _load_data().
-        X0 = self.data.X[0, 0:1]
-        if sparse.isspmatrix(X0) and not sparse.isspmatrix_csc(X0):
-            warnings.warn(
-                "Anndata data matrix is sparse, but not a CSC (columnar) matrix.  "
-                "Performance may be improved by using CSC."
-            )
-        if self.data.X.dtype != "float32":
-            warnings.warn(
-                f"Anndata data matrix is in {self.data.X.dtype} format not float32. " f"Precision may be truncated."
-            )
-        for ax in Axis:
-            curr_axis = getattr(self.data, str(ax))
-            for ann in curr_axis:
-                datatype = curr_axis[ann].dtype
-                downcast_map = {
-                    "int64": "int32",
-                    "uint32": "int32",
-                    "uint64": "int32",
-                    "float64": "float32",
-                }
-                if datatype in downcast_map:
-                    warnings.warn(
-                        f"Anndata annotation {ax}:{ann} is in unsupported format: {datatype}. "
-                        f"Data will be downcast to {downcast_map[datatype]}."
-                    )
-                if isinstance(datatype, CategoricalDtype):
-                    category_num = len(curr_axis[ann].dtype.categories)
-                    if category_num > 500 and category_num > self.dataset_config.presentation__max_categories:
-                        warnings.warn(
-                            f"{str(ax).title()} annotation '{ann}' has {category_num} categories, this may be "
-                            f"cumbersome or slow to display. We recommend setting the "
-                            f"--max-category-items option to 500, this will hide categorical "
-                            f"annotations with more than 500 categories in the UI"
-                        )
-
-    def annotation_to_fbs_matrix(self, axis, fields=None, labels=None):
-        if axis == Axis.OBS:
-            if labels is not None and not labels.empty:
-                df = self.data.obs.join(labels, self.parameters.get("obs_names"))
-            else:
-                df = self.data.obs
-        else:
-            df = self.data.var
-
-        if fields is not None and len(fields) > 0:
-            df = df[fields]
-        return encode_matrix_fbs(df, col_idx=df.columns)
-
-    def get_embedding_names(self):
-        """
-        Return pre-computed embeddings.
-
-        function:
-            a) generate list of default layouts
-            b) validate layouts are legal.  remove/warn on any that are not
-            c) cap total list of layouts at global const MAX_LAYOUTS
-        """
-        # load default layouts from the data.
-        layouts = self.dataset_config.embeddings__names
-
-        if layouts is None or len(layouts) == 0:
-            layouts = [key[2:] for key in self.data.obsm_keys() if type(key) == str and key.startswith("X_")]
-
-        # remove invalid layouts
-        valid_layouts = []
-        obsm_keys = self.data.obsm_keys()
-        for layout in layouts:
-            layout_name = f"X_{layout}"
-            if layout_name not in obsm_keys:
-                warnings.warn(f"Ignoring unknown layout name: {layout}.")
-            elif not self._is_valid_layout(self.data.obsm[layout_name]):
-                warnings.warn(f"Ignoring layout due to malformed shape or data type: {layout}")
-            else:
-                valid_layouts.append(layout)
-
-        if len(valid_layouts) == 0:
-            raise PrepareError("No valid layout data.")
-
-        # cap layouts to MAX_LAYOUTS
-        return valid_layouts[0:MAX_LAYOUTS]
-
-    def get_embedding_array(self, ename, dims=2):
-        full_embedding = self.data.obsm[f"X_{ename}"]
-        return full_embedding[:, 0:dims]
-
-    def compute_diffexp_ttest(self, maskA, maskB, top_n=None, lfc_cutoff=None):
-        if top_n is None:
-            top_n = self.dataset_config.diffexp__top_n
-        if lfc_cutoff is None:
-            lfc_cutoff = self.dataset_config.diffexp__lfc_cutoff
-        return diffexp_generic.diffexp_ttest(self, maskA, maskB, top_n, lfc_cutoff)
-
-    def get_colors(self):
-        return convert_anndata_category_colors_to_cxg_category_colors(self.data)
-
-    def get_X_array(self, obs_mask=None, var_mask=None):
-        # H5Py does not support boolean indexing (masks), so convert to integer indexing
-        # when backed (ie, when AnnData is using H5Py indexing)
-        if obs_mask is None:
-            obs_mask = slice(None)
-        elif self.data.isbacked and obs_mask.dtype == bool:
-            obs_mask = obs_mask.nonzero()[0]
-        if var_mask is None:
-            var_mask = slice(None)
-        elif self.data.isbacked and var_mask.dtype == bool:
-            var_mask = var_mask.nonzero()[0]
-        X = self.data.X[obs_mask, var_mask]
-        return X
-
-    def get_X_approximate_distribution(self) -> XApproximateDistribution:
-        """return the approximate distribution of the X matrix."""
-        if self.X_approximate_distribution is None:
-            """Not yet evaluated."""
-            assert self.dataset_config.X_approximate_distribution == "auto"
-            self.data = self.data.to_memory()  # loads data
-            self.X_approximate_distribution = estimate_distribution.estimate_approximate_distribution(self.data.X)
-
-        return self.X_approximate_distribution
-
-    def get_shape(self):
-        return self.data.shape
-
-    def query_var_array(self, term_name):
-        return getattr(self.data.var, term_name)
-
-    def query_obs_array(self, term_name):
-        return getattr(self.data.obs, term_name)
-
-    def get_obs_index(self):
-        name = self.server_config.single_dataset__obs_names
-        if name is None:
-            return self.original_obs_index
-        else:
-            return self.data.obs[name]
-
-    def get_obs_columns(self):
-        return self.data.obs.columns
-
-    def get_obs_keys(self):
-        # return list of keys
-        return self.data.obs.keys().to_list()
-
-    def get_var_keys(self):
-        # return list of keys
-        return self.data.var.keys().to_list()

backend/server/data_common/data_adaptor.py

@@ -1,423 +0,0 @@
-from abc import ABCMeta, abstractmethod
-from os.path import basename, splitext
-import numpy as np
-import pandas as pd
-from scipy import sparse
-from server_timing import Timing as ServerTiming
-
-from backend.server.common.config.app_config import AppConfig
-from backend.common.constants import Axis, XApproximateDistribution
-from backend.common.errors import FilterError, JSONEncodingValueError, ExceedsLimitError, UnsupportedSummaryMethod
-from backend.common.utils.utils import jsonify_numpy
-from backend.common.fbs.matrix import encode_matrix_fbs
-from backend.common.genesets import validate_gene_sets
-
-
-class DataAdaptor(metaclass=ABCMeta):
-    """Base class for loading and accessing matrix data"""
-
-    def __init__(self, data_locator, app_config, dataset_config=None):
-        if not isinstance(app_config, AppConfig):
-            raise TypeError("config expected to be of type AppConfig")
-
-        # location to the dataset
-        self.data_locator = data_locator
-
-        # config is the application configuration
-        self.app_config = app_config
-        self.server_config = self.app_config.server_config
-        self.dataset_config = dataset_config or app_config.dataset_config
-
-        # parameters set by this data adaptor based on the data.
-        self.parameters = {}
-
-    @staticmethod
-    @abstractmethod
-    def pre_load_validation(data_locator):
-        pass
-
-    @staticmethod
-    @abstractmethod
-    def open(data_locator, app_config, dataset_config):
-        pass
-
-    @staticmethod
-    @abstractmethod
-    def file_size(data_locator):
-        pass
-
-    @abstractmethod
-    def get_name(self):
-        """return a string name for this data adaptor"""
-        pass
-
-    @abstractmethod
-    def get_library_versions(self):
-        """return a dictionary of library name to library versions"""
-        pass
-
-    @abstractmethod
-    def get_embedding_names(self):
-        """return a list of pre-computed embedding names"""
-        pass
-
-    @abstractmethod
-    def get_embedding_array(self, ename, dims=2):
-        """return an numpy array for the given pre-computed embedding name."""
-        pass
-
-    @abstractmethod
-    def get_X_array(self, obs_mask=None, var_mask=None):
-        """return the X array, possibly filtered by obs_mask or var_mask.
-        the return type is either ndarray or scipy.sparse.spmatrix."""
-        pass
-
-    def get_X_approximate_distribution(self) -> XApproximateDistribution:
-        """return the approximate distribution of the X matrix."""
-        return XApproximateDistribution.NORMAL
-
-    @abstractmethod
-    def get_shape(self):
-        pass
-
-    @abstractmethod
-    def query_var_array(self, term_var):
-        pass
-
-    @abstractmethod
-    def query_obs_array(self, term_var):
-        pass
-
-    @abstractmethod
-    def get_colors(self):
-        pass
-
-    @abstractmethod
-    def get_obs_index(self):
-        pass
-
-    @abstractmethod
-    def get_obs_columns(self):
-        pass
-
-    @abstractmethod
-    def get_obs_keys(self):
-        # return list of keys
-        pass
-
-    @abstractmethod
-    def get_var_keys(self):
-        # return list of keys
-        pass
-
-    @abstractmethod
-    def cleanup(self):
-        pass
-
-    def get_data_locator(self):
-        return self.data_locator
-
-    def get_location(self):
-        return self.data_locator.uri_or_path
-
-    def get_about(self):
-        return None
-
-    def get_title(self):
-        # default to file name
-        location = self.get_location()
-        if location.endswith("/"):
-            location = location[:-1]
-        return splitext(basename(location))[0]
-
-    def get_corpora_props(self):
-        return None
-
-    @abstractmethod
-    def get_schema(self):
-        """
-        Return current schema
-        """
-        pass
-
-    @abstractmethod
-    def annotation_to_fbs_matrix(self, axis, field=None, uid=None):
-        """
-        Gets annotation value for each observation
-        :param axis: string obs or var
-        :param fields: list of keys for annotation to return, returns all annotation values if not set.
-        :return: flatbuffer: in fbs/matrix.fbs encoding
-        """
-        pass
-
-    def update_parameters(self, parameters):
-        parameters.update(self.parameters)
-
-    def _index_filter_to_mask(self, filter, count):
-        mask = np.zeros((count,), dtype=np.bool)
-        for i in filter:
-            if isinstance(i, list):
-                mask[i[0] : i[1]] = True
-            else:
-                mask[i] = True
-        return mask
-
-    def _axis_filter_to_mask(self, axis, filter, count):
-        mask = np.ones((count,), dtype=np.bool)
-        if "index" in filter:
-            mask = np.logical_and(mask, self._index_filter_to_mask(filter["index"], count))
-        if "annotation_value" in filter:
-            mask = np.logical_and(mask, self._annotation_filter_to_mask(axis, filter["annotation_value"], count))
-
-        return mask
-
-    def _annotation_filter_to_mask(self, axis, filter, count):
-        mask = np.ones((count,), dtype=np.bool)
-        for v in filter:
-            name = v["name"]
-            if axis == Axis.VAR:
-                anno_data = self.query_var_array(name)
-            elif axis == Axis.OBS:
-                anno_data = self.query_obs_array(name)
-
-            if anno_data.dtype.name in ["boolean", "category", "object"]:
-                values = v.get("values", [])
-                key_idx = np.in1d(anno_data, values)
-                mask = np.logical_and(mask, key_idx)
-
-            else:
-                min_ = v.get("min", None)
-                max_ = v.get("max", None)
-                if min_ is not None:
-                    key_idx = (anno_data >= min_).ravel()
-                    mask = np.logical_and(mask, key_idx)
-                if max_ is not None:
-                    key_idx = (anno_data <= max_).ravel()
-                    mask = np.logical_and(mask, key_idx)
-
-        return mask
-
-    def _filter_to_mask(self, filter):
-        """
-        Return the filter as a row and column selection list.
-        No filter on a dimension means 'all'
-        """
-        shape = self.get_shape()
-        var_selector = None
-        obs_selector = None
-        if filter is not None:
-            if Axis.OBS in filter:
-                obs_selector = self._axis_filter_to_mask(Axis.OBS, filter["obs"], shape[0])
-
-            if Axis.VAR in filter:
-                var_selector = self._axis_filter_to_mask(Axis.VAR, filter["var"], shape[1])
-
-        return (obs_selector, var_selector)
-
-    def check_new_labels(self, labels_df):
-        """Check the new annotations labels, then set the labels_df index"""
-        if labels_df is None or labels_df.empty:
-            return
-
-        labels_df.index = self.get_obs_index()
-        if labels_df.index.name is None:
-            labels_df.index.name = "index"
-
-        # all labels must have a name, which must be unique and not used in obs column names
-        if not labels_df.columns.is_unique:
-            raise KeyError("All column names specified in user annotations must be unique.")
-
-        # the label index must be unique, and must have same values the anndata obs index
-        if not labels_df.index.is_unique:
-            raise KeyError("All row index values specified in user annotations must be unique.")
-
-        obs_columns = self.get_obs_columns()
-
-        duplicate_columns = list(set(labels_df.columns) & set(obs_columns))
-        if len(duplicate_columns) > 0:
-            raise KeyError(
-                "Labels file may not contain column names which overlap " f"with h5ad obs columns {duplicate_columns}"
-            )
-
-        # labels must have same count as obs annotations
-        shape = self.get_shape()
-        if labels_df.shape[0] != shape[0]:
-            raise ValueError("Labels file must have same number of rows as data file.")
-
-        # This will convert a float column that contains integer data into an integer type.
-        # This case can occur when a user makes a copy of a category that originally contained integer data.
-        # The client always copies array data to floats, therefore the copy will contain floats instead of integers.
-        # float data is not allowed as a categorical type.
-        if any([np.issubdtype(coltype.type, np.floating) for coltype in labels_df.dtypes]):
-            labels_df = labels_df.convert_dtypes()
-            for col, dtype in zip(labels_df, labels_df.dtypes):
-                if isinstance(dtype, pd.Int32Dtype):
-                    labels_df[col] = labels_df[col].astype("int32")
-                if isinstance(dtype, pd.Int64Dtype):
-                    labels_df[col] = labels_df[col].astype("int64")
-
-        if any([np.issubdtype(coltype.type, np.floating) for coltype in labels_df.dtypes]):
-            raise ValueError("Columns may not have floating point types")
-
-        return labels_df
-
-    def check_new_gene_sets(self, genesets, context=None):
-        var_names = set(self.query_var_array(self.parameters.get("var_names")))
-        return validate_gene_sets(genesets, var_names)
-
-    def data_frame_to_fbs_matrix(self, filter, axis):
-        """
-        Retrieves data 'X' and returns in a flatbuffer Matrix.
-        :param filter: filter: dictionary with filter params
-        :param axis: string obs or var
-        :return: flatbuffer Matrix
-
-        Caveats:
-        * currently only supports access on VAR axis
-        * currently only supports filtering on VAR axis
-        """
-        if axis != Axis.VAR:
-            raise ValueError("Only VAR dimension access is supported")
-
-        try:
-            obs_selector, var_selector = self._filter_to_mask(filter)
-        except (KeyError, IndexError, TypeError, AttributeError):
-            raise FilterError("Error parsing filter")
-
-        if obs_selector is not None:
-            raise FilterError("filtering on obs unsupported")
-
-        num_columns = self.get_shape()[1] if var_selector is None else np.count_nonzero(var_selector)
-        if self.server_config.exceeds_limit("column_request_max", num_columns):
-            raise ExceedsLimitError("Requested dataframe columns exceed column request limit")
-
-        X = self.get_X_array(obs_selector, var_selector)
-        col_idx = np.nonzero([] if var_selector is None else var_selector)[0]
-        return encode_matrix_fbs(X, col_idx=col_idx, row_idx=None)
-
-    def diffexp_topN(self, obsFilterA, obsFilterB, top_n=None):
-        """
-        Computes the top N differentially expressed variables between two observation sets. If mode
-        is "TOP_N", then stats for the top N
-        dataframes
-        contain a subset of variables, then statistics for all variables will be returned, otherwise
-        only the top N vars will be returned.
-        :param obsFilterA: filter: dictionary with filter params for first set of observations
-        :param obsFilterB: filter: dictionary with filter params for second set of observations
-        :param top_n: Limit results to top N (Top var mode only)
-        :return: top N genes and corresponding stats
-        """
-        if Axis.VAR in obsFilterA or Axis.VAR in obsFilterB:
-            raise FilterError("Observation filters may not contain variable conditions")
-        try:
-            shape = self.get_shape()
-            obs_mask_A = self._axis_filter_to_mask(Axis.OBS, obsFilterA["obs"], shape[0])
-            obs_mask_B = self._axis_filter_to_mask(Axis.OBS, obsFilterB["obs"], shape[0])
-        except (KeyError, IndexError):
-            raise FilterError("Error parsing filter")
-        if top_n is None:
-            top_n = self.dataset_config.diffexp__top_n
-
-        if self.server_config.exceeds_limit(
-            "diffexp_cellcount_max", np.count_nonzero(obs_mask_A) + np.count_nonzero(obs_mask_B)
-        ):
-            raise ExceedsLimitError("Diffexp request exceeds max cell count limit")
-
-        result = self.compute_diffexp_ttest(
-            maskA=obs_mask_A,
-            maskB=obs_mask_B,
-            top_n=top_n,
-            lfc_cutoff=self.dataset_config.diffexp__lfc_cutoff,
-        )
-
-        try:
-            return jsonify_numpy(result)
-        except ValueError:
-            raise JSONEncodingValueError("Error encoding differential expression to JSON")
-
-    @abstractmethod
-    def compute_diffexp_ttest(self, maskA, maskB, top_n, lfc_cutoff):
-        pass
-
-    @staticmethod
-    def normalize_embedding(embedding):
-        """Normalize embedding layout to meet client assumptions.
-        Embedding is an ndarray, shape (n_obs, n)., where n is normally 2
-        """
-
-        # scale isotropically
-        try:
-            min = np.nanmin(embedding, axis=0)
-            max = np.nanmax(embedding, axis=0)
-        except RuntimeError:
-            # indicates entire array was NaN, which should propagate
-            min = np.NaN
-            max = np.NaN
-
-        scale = np.amax(max - min)
-        normalized_layout = (embedding - min) / scale
-
-        # translate to center on both axis
-        translate = 0.5 - ((max - min) / scale / 2)
-        normalized_layout = normalized_layout + translate
-
-        normalized_layout = normalized_layout.astype(dtype=np.float32)
-        return normalized_layout
-
-    def layout_to_fbs_matrix(self, fields):
-        """
-        return specified embeddings as a flatbuffer, using the cellxgene matrix fbs encoding.
-
-        * returns only first two dimensions, with name {ename}_0 and {ename}_1,
-          where {ename} is the embedding name.
-        * client assumes each will be individually centered & scaled (isotropically)
-          to a [0, 1] range.
-        * does not support filtering
-
-        """
-        embeddings = self.get_embedding_names() if fields is None or len(fields) == 0 else fields
-        layout_data = []
-        with ServerTiming.time("layout.query"):
-            for ename in embeddings:
-                embedding = self.get_embedding_array(ename, 2)
-                normalized_layout = DataAdaptor.normalize_embedding(embedding)
-                layout_data.append(pd.DataFrame(normalized_layout, columns=[f"{ename}_0", f"{ename}_1"]))
-
-        with ServerTiming.time("layout.encode"):
-            if layout_data:
-                df = pd.concat(layout_data, axis=1, copy=False)
-            else:
-                df = pd.DataFrame()
-            fbs = encode_matrix_fbs(df, col_idx=df.columns, row_idx=None)
-
-        return fbs
-
-    def get_last_mod_time(self):
-        try:
-            lastmod = self.get_data_locator().lastmodtime()
-        except RuntimeError:
-            lastmod = None
-        return lastmod
-
-    def summarize_var(self, method, filter, query_hash):
-        if method != "mean":
-            raise UnsupportedSummaryMethod("Unknown gene set summary method.")
-
-        obs_selector, var_selector = self._filter_to_mask(filter)
-        if obs_selector is not None:
-            raise FilterError("filtering on obs unsupported")
-
-        # if no filter, just return zeros.  We don't have a use case
-        # for summarizing the entire X without a filter, and it would
-        # potentially be quite compute / memory intensive.
-        if var_selector is None or np.count_nonzero(var_selector) == 0:
-            mean = np.zeros((self.get_shape()[0], 1), dtype=np.float32)
-        else:
-            X = self.get_X_array(obs_selector, var_selector)
-            if sparse.issparse(X):
-                mean = X.mean(axis=1).A
-            else:
-                mean = X.mean(axis=1, keepdims=True)
-
-        col_idx = pd.Index([query_hash])
-        return encode_matrix_fbs(mean, col_idx=col_idx, row_idx=None)

backend/server/data_common/matrix_loader.py

@@ -1,56 +0,0 @@
-from enum import Enum
-
-from backend.common.utils.data_locator import DataLocator
-from backend.common.errors import DatasetAccessError
-from http import HTTPStatus
-
-
-class MatrixDataType(Enum):
-    H5AD = "h5ad"
-    UNKNOWN = "unknown"
-
-
-class MatrixDataLoader(object):
-    def __init__(self, location, matrix_data_type=None, app_config=None):
-        """ location can be a string or DataLocator """
-        region_name = None if app_config is None else app_config.server_config.data_locator__s3__region_name
-        self.location = DataLocator(location, region_name=region_name)
-        if not self.location.exists():
-            raise DatasetAccessError("Dataset does not exist.", HTTPStatus.NOT_FOUND)
-
-        # matrix_data_type is an enum value of type MatrixDataType
-        self.matrix_data_type = matrix_data_type
-        # matrix_type is a DataAdaptor type, which corresonds to the matrix_data_type
-        self.matrix_type = None
-
-        if matrix_data_type is None:
-            self.matrix_data_type = self.__matrix_data_type()
-
-        if not self.__matrix_data_type_allowed(app_config):
-            raise DatasetAccessError("Dataset does not have an allowed type.")
-
-        if self.matrix_data_type == MatrixDataType.H5AD:
-            from backend.server.data_anndata.anndata_adaptor import AnndataAdaptor
-
-            self.matrix_type = AnndataAdaptor
-
-    def __matrix_data_type(self):
-        if self.location.path.endswith(".h5ad"):
-            return MatrixDataType.H5AD
-        else:
-            return MatrixDataType.UNKNOWN
-
-    def __matrix_data_type_allowed(self, app_config):
-        return self.matrix_data_type != MatrixDataType.UNKNOWN
-
-    def pre_load_validation(self):
-        if self.matrix_data_type == MatrixDataType.UNKNOWN:
-            raise DatasetAccessError("Dataset does not have a recognized type: .h5ad")
-        self.matrix_type.pre_load_validation(self.location)
-
-    def file_size(self):
-        return self.matrix_type.file_size(self.location)
-
-    def open(self, app_config, dataset_config=None):
-        # create and return a DataAdaptor object
-        return self.matrix_type.open(self.location, app_config, dataset_config)

backend/server/default_config.py

@@ -1,137 +0,0 @@
-import yaml
-
-default_config = """
-server:
-  app:
-    verbose: false
-    debug: false
-    host: localhost
-    port : null
-    open_browser: false
-    force_https: false
-    flask_secret_key: null
-    generate_cache_control_headers: false
-
-  authentication:
-    # The authentication types may be "none" or "session"
-    # none:  No authentication support, features like user_annotations must not be enabled.
-    # session:  A session based userid is automatically generated. (no params needed)
-    type: session
-    insecure_test_environment: false
-
-  single_dataset:
-    # If datapath is set, then cellxgene with serve a single dataset located at datapath.
-    datapath: null
-    obs_names: null
-    var_names: null
-    about: null
-    title: null
-
-  data_locator:
-    s3:
-      # s3 region name.
-      #   if true, then the s3 location is automatically determined from the datapath or dataroot.
-      #   if false/null, then do not set.
-      #   if a string, then use that value (e.g. us-east-1).
-      region_name: true
-
-  adaptor:
-    anndata_adaptor:
-      backed: false
-
-  limits:
-    column_request_max: 32
-    diffexp_cellcount_max: null
-
-
-dataset:
-  app:
-    # Scripts can be a list of either file names (string) or dicts containing keys src, integrity and crossorigin.
-    # these will be injected into the index template as script tags with these attributes set.
-    scripts: []
-    # Inline scripts are a list of file names, where the contents of the file will be injected into the index.
-    inline_scripts: []
-
-    # allow authentication support
-    authentication_enable: true
-
-  presentation:
-    max_categories: 1000
-    custom_colors: true
-
-  user_annotations:
-    enable: true
-    type: local_file_csv
-    local_file_csv:
-      directory: null
-      file: null            # annotations file name
-      gene_sets_file: null  # gene sets file name
-    gene_sets:
-      readonly: false       # gene sets CRUD enabled/disabled
-
-  embeddings:
-    names : []
-
-  diffexp:
-    enable: true
-    lfc_cutoff: 0.01
-    top_n: 10
-
-  X_approximate_distribution: auto
-
-external:
-  # You can retrieve configuration parameters from this config file, the environment,
-  # the AWS secrets manager, or from the "cellxgene launch" command line arguments.
-  # They are applied in that order, meaning that if a parameter is defined in more
-  # than one location, the last one applied takes effect.
-
-  # environment variables:
-  # This section describes how to map environment variables to configuration parameters.
-  # The format is a list defining an environment variable.
-  # Each entry in the list is a dictionary with three entries:
-  # name:  the name of the environment variable
-  # path: the path within the cellxgene configuration to update.
-  # required: (default=False) a boolean.  If true, then it is an error if the environment variable is not set.
-
-  environment:
-     - name: CXG_SECRET_KEY
-       path: [server, app, flask_secret_key]
-       required: false
-
-  # AWS Secrets Manager
-  # This section describes how to map aws secrets to configuration parameters.
-  # The format is the region for the secrets manager, then a list of secrets.
-  # each secret has a name, and a list of values.
-  # Each entry in the list of values is a dictionary with three entries:
-  # key:  the key of the aws secret.
-  # path: the path within the cellxgene configuration to update.
-  # required: (default=False) a boolean.  If true, then it is an error if the key does not exist in the secret.
-  #
-  # example:
-  # aws_secrets_manager:
-  #   region: us-west-2
-  #    - name: my_first_secret
-  #      values:
-  #      - key: flask_secret_key
-  #        path: [server, app, flask_secret_key]
-  #        required: true
-  #      - key: db_uri
-  #        path: [dataset, user_annotations, db_uri]
-  #        required: true
-  #    - name:  my_auth_secret
-  #      values:
-  #      - key: client_secret
-  #        path: [server, authentication, client_secret]
-  #        required: true
-  #      - key: client_id
-  #        path: [server, authentication, client_id]
-  #        required: true
-
-  aws_secrets_manager:
-    region: null
-    secrets: []
-"""
-
-
-def get_default_config():
-    return yaml.load(default_config, Loader=yaml.Loader)

backend/server/requirements-prepare.txt

@@ -1,4 +0,0 @@
-python-igraph>=0.8
-louvain>=0.6
-scanpy
-umap-learn<0.5.0 # The pinned version scanpy is not compatible with latest umap-learn

backend/server/requirements.txt

@@ -1,23 +0,0 @@
-anndata>=0.7.6 # we need to_memory(), added in 0.7.6
-boto3>=1.12.18
-click>=7.1.2
-Flask>=1.0.2,<2.0.0 # Flask 2.0 is not compatible with the latest version of Flask-RESTful (0.3.8)
-Flask-Compress>=1.4.0
-Flask-Cors>=3.0.9  # CVE-2020-25032
-Flask-RESTful>=0.3.6
-flask-server-timing>=0.1.2
-flask-talisman>=0.7.0
-flatbuffers>=1.11.0,<2.0.0 # cellxgene is not compatible with 2.0.0. Requires migration
-flatten-dict>=0.2.0
-fsspec>=0.4.4,<0.8.0
-gunicorn>=20.0.4
-h5py>=3.0.0
-jinja2>=2.11.3  # Flask sub-dependency. Added due to CVE-2020-28493
-numba>=0.51.2
-numpy>=1.17.5
-packaging>=20.0
-pandas>=1.0,!=1.1  # pandas 1.1 breaks tests, https://github.com/pandas-dev/pandas/issues/35446
-PyYAML>=5.4  # CVE-2020-14343
-scipy>=1.4
-requests>=2.22.0
-s3fs==0.4.2

backend/test/__init__.py

@@ -1,11 +0,0 @@
-import random
-import string
-from os import popen
-
-PROJECT_ROOT = popen("git rev-parse --show-toplevel").read().strip()
-FIXTURES_ROOT = PROJECT_ROOT + "/backend/test/fixtures"
-H5AD_FIXTURE = FIXTURES_ROOT + "/pbmc3k-CSC-gz.h5ad"
-
-
-def random_string(n):
-    return "".join(random.choice(string.ascii_letters) for _ in range(n))

backend/test/fixtures/czi_hosted_dataset_config_outline.py

@@ -1,35 +0,0 @@
-f"""
-dataset:
-  app:
-    scripts: {scripts} #list of strs (filenames) or dicts containing keys
-    inline_scripts: {inline_scripts} #list of strs (filenames)
-
-    about_legal_tos: {about_legal_tos}
-    about_legal_privacy: {about_legal_privacy}
-
-    authentication_enable: {authentication_enable}
-
-  presentation:
-    max_categories: {max_categories}
-    custom_colors: {custom_colors}
-
-  user_annotations:
-    enable: {enable_users_annotations}
-    type: {annotation_type}
-    hosted_tiledb_array:
-      db_uri: {db_uri}
-      hosted_file_directory: {hosted_file_directory}
-    local_file_csv:
-      directory: {local_file_csv_directory}
-      file: {local_file_csv_file}
-
-  embeddings:
-    names: {embedding_names}
-
-  diffexp:
-    enable: {enable_difexp}
-    lfc_cutoff: {lfc_cutoff}
-    top_n: {top_n}
-
-  X_approximate_distribution: {X_approximate_distribution}
-"""

backend/test/fixtures/czi_hosted_server_config_outline.py

@@ -1,63 +0,0 @@
-f"""server:
-  app:
-    verbose: {verbose}
-    debug: {debug}
-    host: {host}
-    port: {port}
-    open_browser: {open_browser}
-    force_https: {force_https}
-    flask_secret_key: {flask_secret_key}
-    generate_cache_control_headers: {generate_cache_control_headers}
-    server_timing_headers: {server_timing_headers}
-    csp_directives: {csp_directives}
-    api_base_url: {api_base_url}
-    web_base_url: {web_base_url}
-  authentication:
-    type: {auth_type}
-    insecure_test_environment: {insecure_test_environment}
-    params_oauth:
-      oauth_api_base_url: {oauth_api_base_url}
-      client_id: {client_id}
-      client_secret: {client_secret}
-      jwt_decode_options: {jwt_decode_options}
-      session_cookie:  {session_cookie}
-      cookie:  {cookie}
-
-  multi_dataset:
-    dataroot: {dataroot}
-    index: {index}
-    allowed_matrix_types: {allowed_matrix_types}
-    matrix_cache:
-      max_datasets: {max_cached_datasets}
-      timelimit_s: {timelimit_s}
-
-  single_dataset:
-    datapath: {dataset_datapath}
-    obs_names: {obs_names}
-    var_names: {var_names}
-    about: {about}
-    title: {title}
-
-  diffexp:
-    alg_cxg: # number of threads to use is computed from: min(max_workers, cpu_multipler * cpu_count)
-      max_workers: {diffexp_max_workers}
-      cpu_multiplier: {cpu_multiplier}
-      target_workunit: {target_workunit}  # The target number of matrix elements that are evaluated in one thread.
-
-  data_locator:
-    s3:
-      region_name: {data_locater_region_name}
-
-  adaptor:
-    cxg_adaptor:
-      tiledb_ctx:
-        sm.tile_cache_size:  {cxg_tile_cache_size}
-        sm.num_reader_threads:  {cxg_num_reader_threads}
-
-    anndata_adaptor:
-      backed: {anndata_backed}
-
-  limits:
-    column_request_max: {column_request_max}
-    diffexp_cellcount_max: {diffexp_cellcount_max}
-"""

backend/test/fixtures/dataset_config_outline.py

@@ -1,32 +0,0 @@
-f"""
-dataset:
-  app:
-    scripts: {scripts} #list of strs (filenames) or dicts containing keys
-    inline_scripts: {inline_scripts} #list of strs (filenames)
-
-    authentication_enable: {authentication_enable}
-
-  presentation:
-    max_categories: {max_categories}
-    custom_colors: {custom_colors}
-
-  user_annotations:
-    enable: {enable_users_annotations}
-    type: {annotation_type}
-    local_file_csv:
-      directory: {local_file_csv_directory}
-      file: {local_file_csv_file}
-      gene_sets_file: {local_file_csv_gene_sets_file}
-    gene_sets:
-      readonly: {gene_sets_readonly}
-
-  embeddings:
-    names: {embedding_names}
-
-  diffexp:
-    enable: {enable_difexp}
-    lfc_cutoff: {lfc_cutoff}
-    top_n: {top_n}
-
-  X_approximate_distribution: {X_approximate_distribution}
-"""

backend/test/fixtures/pbmc3k-genesets.csv

@@ -1,21 +0,0 @@
-# Test fixture
-gene_set_name,gene_set_description,gene_symbol,gene_description
-first gene set name,,F5, a gene_description
-first gene set name,a description,NO_SUCH_GENE, non-existent gene
-first gene set name,a description,F5, duplicate gene
-first gene set name, a description,SUMO3,
-first gene set name,,SRM,
-second_gene_set,,RER1
-second_gene_set,,SIK1
-third gene set,,NO_SUCH_GENE
-fourth_gene_set,fourth description,,gene intentionally missing
-fifth_dataset,,,
-summary test,,ACD,
-summary test,,AATF,
-summary test,,F5,
-summary test,,PIGU,
-geneset_to_delete,,,
-geneset_to_edit,,,
-fill_this_geneset,,,
-empty_this_geneset,,SIK1,
-brush_this_gene,,SIK1,

backend/test/fixtures/schema_test_data/generate_test_data.sh

@@ -1,139 +0,0 @@
-#!/bin/bash
-wget "https://s3-us-west-2.amazonaws.com/10x.files/samples/cell/pbmc3k/pbmc3k_filtered_gene_bc_matrices.tar.gz"
-tar xf "pbmc3k_filtered_gene_bc_matrices.tar.gz"
-
-python3 - <<MERGE_GENES
-import os
-from scipy.io import mmread, mmwrite
-import scipy.sparse
-import pandas as pd
-from server.converters.schema import gene_symbol
-
-mat = mmread("filtered_gene_bc_matrices/hg19/matrix.mtx").todense()
-genes = pd.read_csv("filtered_gene_bc_matrices/hg19/genes.tsv", sep='\t', names=["gene_id", "gene_symbol"])
-
-upgraded_genes = gene_symbol.get_upgraded_var_index(pd.DataFrame(index=genes["gene_symbol"]))
-df = pd.DataFrame(data=mat, index=upgraded_genes).T
-merged = df.sum(axis=1, level=0, skipna=False)
-
-os.makedirs("merged")
-merged.columns.to_frame().to_csv("merged/genes.tsv", index=False, header=False)
-mmwrite("merged/matrix.mtx", scipy.sparse.coo_matrix(merged).T)
-MERGE_GENES
-
-cp "filtered_gene_bc_matrices/hg19/barcodes.tsv" "merged/barcodes.tsv"
-awk '{print $1"\t"$1}' merged/genes.tsv > genes_tmp.tsv; mv genes_tmp.tsv merged/genes.tsv
-
-echo -e "\n\n\nRunning tutorial on original\n\n\n"
-Rscript - <<TUTORIAL
-library(Seurat)
-
-pbmc.data <- Read10X(data.dir = "filtered_gene_bc_matrices/hg19/")
-pbmc <- CreateSeuratObject(counts = pbmc.data, project = "pbmc3k", min.features = 200)
-pbmc <- NormalizeData(pbmc, normalization.method = "LogNormalize", scale.factor = 10000)
-pbmc <- FindVariableFeatures(pbmc, selection.method = "vst", nfeatures = 2000)
-pbmc[["percent.mt"]] <- PercentageFeatureSet(pbmc, pattern = "^MT-")
-all.genes <- rownames(pbmc)
-pbmc <- ScaleData(pbmc, features = all.genes)
-
-pbmc <- RunPCA(pbmc, features = VariableFeatures(object = pbmc))
-pbmc <- FindNeighbors(pbmc, dims = 1:10)
-pbmc <- FindClusters(pbmc, resolution = 0.5)
-pbmc <- RunUMAP(pbmc, dims = 1:10)
-saveRDS(pbmc, file = "./seurat_tutorial.rds")
-TUTORIAL
-
-echo -e "\n\n\nRunning tutorial on merged\n\n\n"
-Rscript - <<TUTORIAL_MERGED
-library(Seurat)
-
-pbmc.data <- Read10X(data.dir = "merged/")
-pbmc <- CreateSeuratObject(counts = pbmc.data, project = "pbmc3k", min.features = 200)
-pbmc <- NormalizeData(pbmc, normalization.method = "LogNormalize", scale.factor = 10000)
-pbmc <- FindVariableFeatures(pbmc, selection.method = "vst", nfeatures = 2000)
-pbmc[["percent.mt"]] <- PercentageFeatureSet(pbmc, pattern = "^MT-")
-all.genes <- rownames(pbmc)
-pbmc <- ScaleData(pbmc, features = all.genes)
-
-pbmc <- RunPCA(pbmc, features = VariableFeatures(object = pbmc))
-pbmc <- FindNeighbors(pbmc, dims = 1:10)
-pbmc <- FindClusters(pbmc, resolution = 0.5)
-pbmc <- RunUMAP(pbmc, dims = 1:10)
-saveRDS(pbmc, file = "./seurat_tutorial_merged.rds")
-TUTORIAL_MERGED
-
-echo -e "\n\n\nRunning SCTransform on original\n\n\n"
-Rscript - <<SCTRANSFORM
-library(Seurat)
-library(sctransform)
-
-pbmc.data <- Read10X(data.dir = "filtered_gene_bc_matrices/hg19/")
-pbmc <- CreateSeuratObject(counts = pbmc.data)
-pbmc <- PercentageFeatureSet(pbmc, pattern = "^MT-", col.name = "percent.mt")
-pbmc <- SCTransform(pbmc, vars.to.regress = "percent.mt", verbose = FALSE)
-pbmc <- RunPCA(pbmc, verbose = FALSE)
-pbmc <- RunUMAP(pbmc, dims = 1:30, verbose = FALSE)
-pbmc <- FindNeighbors(pbmc, dims = 1:30, verbose = FALSE)
-pbmc <- FindClusters(pbmc, verbose = FALSE)
-saveRDS(pbmc, file = "./sctransform.rds")
-SCTRANSFORM
-
-echo -e "\n\n\nRunning SCTransform on merged\n\n\n"
-Rscript - <<SCTRANSFORM_MERGED
-library(Seurat)
-library(sctransform)
-
-pbmc.data <- Read10X(data.dir = "merged/")
-pbmc <- CreateSeuratObject(counts = pbmc.data)
-pbmc <- PercentageFeatureSet(pbmc, pattern = "^MT-", col.name = "percent.mt")
-pbmc <- SCTransform(pbmc, vars.to.regress = "percent.mt", verbose = FALSE)
-pbmc <- RunPCA(pbmc, verbose = FALSE)
-pbmc <- RunUMAP(pbmc, dims = 1:30, verbose = FALSE)
-pbmc <- FindNeighbors(pbmc, dims = 1:30, verbose = FALSE)
-pbmc <- FindClusters(pbmc, verbose = FALSE)
-saveRDS(pbmc, file = "./sctransform_merged.rds")
-SCTRANSFORM_MERGED
-
-echo -e "\n\n\nConverting\n\n\n"
-Rscript - <<SCEASY
-library(sceasy)
-srt <- readRDS("seurat_tutorial.rds")
-sceasy::convertFormat(srt,
-                      outFile = "seurat_tutorial.h5ad",
-                      from = "seurat",
-                      to = "anndata",
-                      assay = "RNA",
-                      main_layer = "data",
-                      transfer_layers = c("data", "counts", "scale.data"),
-                      drop_single_values = FALSE)
-
-srt <- readRDS("seurat_tutorial_merged.rds")
-sceasy::convertFormat(srt,
-                      outFile = "seurat_tutorial_merged.h5ad",
-                      from = "seurat",
-                      to = "anndata",
-                      assay = "RNA",
-                      main_layer = "data",
-                      transfer_layers = c("data", "counts", "scale.data"),
-                      drop_single_values = FALSE)
-
-srt <- readRDS("sctransform.rds")
-sceasy::convertFormat(srt,
-                      outFile = "sctransform.h5ad",
-                      from = "seurat",
-                      to = "anndata",
-                      assay = "SCT",
-                      main_layer = "data",
-                      transfer_layers = c("data", "counts", "scale.data"),
-                      drop_single_values = FALSE)
-
-srt <- readRDS("sctransform_merged.rds")
-sceasy::convertFormat(srt,
-                      outFile = "sctransform_merged.h5ad",
-                      from = "seurat",
-                      to = "anndata",
-                      assay = "SCT",
-                      main_layer = "data",
-                      transfer_layers = c("data", "counts", "scale.data"),
-                      drop_single_values = FALSE)
-SCEASY

backend/test/fixtures/server_config_outline.py

@@ -1,33 +0,0 @@
-f"""server:
-  app:
-    verbose: {verbose}
-    debug: {debug}
-    host: {host}
-    port: {port}
-    open_browser: {open_browser}
-    force_https: {force_https}
-    flask_secret_key: {flask_secret_key}
-    generate_cache_control_headers: {generate_cache_control_headers}
-  authentication:
-    type: {auth_type}
-    insecure_test_environment: {insecure_test_environment}
-
-  single_dataset:
-    datapath: {dataset_datapath}
-    obs_names: {obs_names}
-    var_names: {var_names}
-    about: {about}
-    title: {title}
-
-  data_locator:
-    s3:
-      region_name: {data_locater_region_name}
-
-  adaptor:
-    anndata_adaptor:
-      backed: {anndata_backed}
-
-  limits:
-    column_request_max: {column_request_max}
-    diffexp_cellcount_max: {diffexp_cellcount_max}
-"""

backend/test/fixtures/test_bad_config.yaml

@@ -1,34 +0,0 @@
-fixup_gene_symbols:
-    X: log1p
-obs:
-    cell_type_ontology_term_id:
-        louvain:
-            CD4 T cells: CL:00001
-            B cells: CL:00002
-            CD14+ Monocytes: CL:00003
-            NK cells: CL:00004
-            CD8 T cells: CL:00005
-            FCGR3A+ Monocytes: CL:00006
-            Dendritic cells: CL:00007
-            Megakaryocytes: CL:00008
-    tissue_ontology_term_id: UBERON:12345
-    assay_ontology_term_id: EFO:12345
-    disease_ontology_term_id: MONDO:12345
-    ethnicity_ontology_term_id: MANCESTRO:12345
-    development_stage_ontology_term_id: HsapDv:12345
-    sex: other
-uns:
-    version:
-        corpora_schema_version: 1.0.0
-        corpora_encoding_version: 0.1.0
-    organism_ontology_term_id: NCBITaxon:9606
-    title: Test dataset
-    contributors:
-        - name: Marcus
-          institution: CZI
-    layer_descriptions:
-        X: raw
-    project_links:
-        - link_url: https://chanzuckerberg.com/
-          link_name: CZI
-          link_type: SUMMARY

backend/test/fixtures/test_config.yaml

@@ -1,34 +0,0 @@
-fixup_gene_symbols:
-    X: log1p
-obs:
-    cell_type_ontology_term_id:
-        louvain:
-            CD4 T cells: CL:00001
-            B cells: CL:00002
-            CD14+ Monocytes: CL:00003
-            NK cells: CL:00004
-            CD8 T cells: CL:00005
-            FCGR3A+ Monocytes: CL:00006
-            Dendritic cells: CL:00007
-            Megakaryocytes: CL:00008
-    tissue_ontology_term_id: UBERON:12345
-    assay_ontology_term_id: EFO:12345
-    disease_ontology_term_id: MONDO:12345
-    ethnicity_ontology_term_id: HANCESTRO:12345
-    development_stage_ontology_term_id: HsapDv:12345
-    sex: other
-uns:
-    version:
-        corpora_schema_version: 1.0.0
-        corpora_encoding_version: 0.1.0
-    organism_ontology_term_id: NCBITaxon:9606
-    title: Test dataset
-    contributors:
-        - name: Marcus
-          institution: CZI
-    layer_descriptions:
-        X: raw
-    project_links:
-        - link_url: https://chanzuckerberg.com/
-          link_name: CZI
-          link_type: SUMMARY

backend/test/test_common/unit/__init__.py

@@ -1 +0,0 @@
-