mirror of
https://github.com/chanzuckerberg/cellxgene.git
synced 2026-09-26 07:28:11 +08:00
Merge branch 'master' of https://github.com/chanzuckerberg/cellxgene into bkmartinjr-crossfiltergroups
This commit is contained in:
bkmartinjr
+36
@@ -14,3 +14,39 @@ npm-debug.log
|
||||
.vscode
|
||||
|
||||
data
|
||||
|
||||
|
||||
*.idea*
|
||||
|
||||
__pycache__
|
||||
*.DS_Store*
|
||||
|
||||
# Elastic Beanstalk Files
|
||||
.elasticbeanstalk/*
|
||||
!.elasticbeanstalk/*.cfg.yml
|
||||
!.elasticbeanstalk/*.global.yml
|
||||
|
||||
GBM
|
||||
venv
|
||||
extesting
|
||||
|
||||
Dockerfile-*
|
||||
*-data/*
|
||||
data/*
|
||||
runServer.py
|
||||
templates/favicon.png
|
||||
templates/index.html
|
||||
templates/service-worker.js
|
||||
templates/static/*
|
||||
Graph.dot*
|
||||
|
||||
server/app/web/static/css/
|
||||
server/app/web/static/img/
|
||||
server/app/web/static/js/
|
||||
server/app/web/templates/index\.html
|
||||
|
||||
|
||||
*.egg-info
|
||||
dist/*
|
||||
build/*
|
||||
|
||||
|
||||
+19
@@ -0,0 +1,19 @@
|
||||
language: python
|
||||
python:
|
||||
- "3.6"
|
||||
node_js:
|
||||
- "8"
|
||||
cache:
|
||||
pip: true
|
||||
install:
|
||||
- set -eo pipefail
|
||||
- pip install flake8 httpie
|
||||
- ./bin/build-client
|
||||
- python setup.py install
|
||||
script:
|
||||
- set -eo pipefail
|
||||
- flake8 server/app/
|
||||
- pytest -s server/test/test_filter.py server/test/test_scanpy_engine.py
|
||||
- cellxgene &
|
||||
- for i in {1..90}; do if http :5005/api/v0.1/initialize > /dev/null; then break; else echo "Waiting for server..."; sleep 1; fi; done
|
||||
- pytest server/test/test_api.py
|
||||
@@ -0,0 +1,3 @@
|
||||
recursive-include server/app/web/templates *
|
||||
recursive-include server/app/web/static *
|
||||
|
||||
@@ -2,8 +2,37 @@
|
||||
|
||||
A React + Redux web application for exploring large scale single cell RNA sequence data.
|
||||
|
||||
##### Quickstart:
|
||||
### Requirements
|
||||
- OS: OSX, Windows, Linux
|
||||
- python 3.6
|
||||
- npm
|
||||
- Google Chrome
|
||||
|
||||
* `npm install`
|
||||
* `npm start`
|
||||
* `localhost:3000`
|
||||
|
||||
## Installation
|
||||
|
||||
#### clone project
|
||||
|
||||
git clone https://github.com/chanzuckerberg/cellxgene.git
|
||||
|
||||
#### install client
|
||||
|
||||
cd cellxgene
|
||||
./bin/build-client
|
||||
|
||||
#### To use with virtual env for python (optional, but recommended)
|
||||
|
||||
ENV_NAME=cellxgene
|
||||
python3 -m venv ${ENV_NAME}
|
||||
source ${ENV_NAME}/bin/activate
|
||||
|
||||
#### install server
|
||||
|
||||
python3 setup.py install
|
||||
|
||||
#### run (with demo data)
|
||||
|
||||
cellxgene
|
||||
|
||||
|
||||
*Thanks to Alex Wolf his help with test data*
|
||||
|
||||
Executable
+10
@@ -0,0 +1,10 @@
|
||||
#!/bin/bash
|
||||
|
||||
npm install --prefix client/ client
|
||||
npm run --prefix client build
|
||||
mkdir -p server/app/web/static/img
|
||||
cp client/build/index.html server/app/web/templates/
|
||||
cp -r client/build/static server/app/web/
|
||||
|
||||
cp client/build/favicon.png server/app/web/static/img
|
||||
cp client/build/service-worker.js server/app/web/static/js/
|
||||
|
Before Width: | Height: | Size: 43 KiB After Width: | Height: | Size: 43 KiB |
@@ -3,7 +3,7 @@
|
||||
<head>
|
||||
<meta charset="utf-8">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1">
|
||||
<title>Cellx</title>
|
||||
<title>cellxgene</title>
|
||||
<link href="https://fonts.googleapis.com/css?family=Roboto:400,400i,700" rel="stylesheet">
|
||||
<style>
|
||||
html, body, p, h1, h2, h3, h4, h5, h6, span, button, input {
|
||||
@@ -3,7 +3,7 @@
|
||||
<head>
|
||||
<meta charset="utf-8">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1">
|
||||
<title>Cellx</title>
|
||||
<title>cellxgene</title>
|
||||
<style>
|
||||
html, body, p, h1, h2, h3, h4, h5, h6, span, button, input {
|
||||
font-family: Helvetica Neue,Helvetica,Arial,sans-serif;
|
||||
@@ -115,6 +115,8 @@
|
||||
"whatwg-fetch": "^2.0.1"
|
||||
},
|
||||
"jest": {
|
||||
"testMatch": ["**/__tests__/**/?(*.)(spec|test).js?(x)"]
|
||||
"testMatch": [
|
||||
"**/__tests__/**/?(*.)(spec|test).js?(x)"
|
||||
]
|
||||
}
|
||||
}
|
||||
+3
-2
@@ -11,7 +11,6 @@ import FaPaintBrush from "react-icons/lib/fa/paint-brush";
|
||||
import * as globals from "../../globals";
|
||||
|
||||
@connect(state => {
|
||||
console.log("state in histo brush", state)
|
||||
const ranges =
|
||||
state.cells.cells && state.cells.cells.data.ranges
|
||||
? state.cells.cells.data.ranges
|
||||
@@ -172,7 +171,9 @@ class HistogramBrush extends React.Component {
|
||||
this.props.dispatch({
|
||||
type: "color by continuous metadata",
|
||||
colorAccessor: this.props.metadataField,
|
||||
rangeMaxForColorAccessor: this.props.initializeRanges[this.props.metadataField].range.max
|
||||
rangeMaxForColorAccessor: this.props.initializeRanges[
|
||||
this.props.metadataField
|
||||
].range.max
|
||||
});
|
||||
}
|
||||
render() {
|
||||
+1
-7
@@ -39,13 +39,7 @@ export default function(regl) {
|
||||
distance: regl.prop("distance"),
|
||||
view: regl.prop("view"),
|
||||
projection: (context, props) => {
|
||||
return mat4.perspective(
|
||||
[],
|
||||
Math.PI / 2,
|
||||
context.viewportWidth * props.scale / context.viewportHeight,
|
||||
0.01,
|
||||
1000
|
||||
);
|
||||
return mat4.perspective([], Math.PI / 2, 1, 0.01, 1000);
|
||||
}
|
||||
},
|
||||
|
||||
@@ -47,6 +47,39 @@ class Graph extends React.Component {
|
||||
mode: "brush"
|
||||
};
|
||||
}
|
||||
reglDraw(regl, drawPoints, sizeBuffer, colorBuffer, pointBuffer, camera) {
|
||||
regl.clear({
|
||||
depth: 1,
|
||||
color: [1, 1, 1, 1]
|
||||
});
|
||||
drawPoints({
|
||||
size: sizeBuffer,
|
||||
distance: camera.distance,
|
||||
color: colorBuffer,
|
||||
position: pointBuffer,
|
||||
count: this.count,
|
||||
view: camera.view()
|
||||
});
|
||||
}
|
||||
restartReglLoop() {
|
||||
const reglRender = this.state.regl.frame(() => {
|
||||
this.reglDraw(
|
||||
this.state.regl,
|
||||
this.state.drawPoints,
|
||||
this.state.sizeBuffer,
|
||||
this.state.colorBuffer,
|
||||
this.state.pointBuffer,
|
||||
this.state.camera
|
||||
);
|
||||
this.state.camera.tick();
|
||||
});
|
||||
|
||||
this.reglRenderState = "rendering";
|
||||
|
||||
this.setState({
|
||||
reglRender
|
||||
});
|
||||
}
|
||||
componentDidMount() {
|
||||
// setup canvas and camera
|
||||
const camera = _camera(this.reglCanvas, { scale: true, rotate: false });
|
||||
@@ -59,34 +92,31 @@ class Graph extends React.Component {
|
||||
const colorBuffer = regl.buffer();
|
||||
const sizeBuffer = regl.buffer();
|
||||
|
||||
regl.frame(({ viewportWidth, viewportHeight }) => {
|
||||
regl.clear({
|
||||
depth: 1,
|
||||
color: [1, 1, 1, 1]
|
||||
});
|
||||
|
||||
drawPoints({
|
||||
size: sizeBuffer,
|
||||
distance: camera.distance,
|
||||
color: colorBuffer,
|
||||
position: pointBuffer,
|
||||
count: this.count,
|
||||
view: camera.view(),
|
||||
scale: viewportHeight / viewportWidth
|
||||
});
|
||||
|
||||
this.setState({ camera });
|
||||
/* first time, but this duplicates above function, should be possile to avoid this */
|
||||
const reglRender = regl.frame(() => {
|
||||
this.reglDraw(
|
||||
regl,
|
||||
drawPoints,
|
||||
sizeBuffer,
|
||||
colorBuffer,
|
||||
pointBuffer,
|
||||
camera
|
||||
);
|
||||
camera.tick();
|
||||
});
|
||||
|
||||
this.reglRenderState = "rendering";
|
||||
|
||||
this.setState({
|
||||
regl,
|
||||
drawPoints,
|
||||
pointBuffer,
|
||||
colorBuffer,
|
||||
sizeBuffer
|
||||
sizeBuffer,
|
||||
camera,
|
||||
reglRender
|
||||
});
|
||||
}
|
||||
|
||||
componentWillReceiveProps(nextProps) {
|
||||
if (this.state.regl && nextProps.crossfilter) {
|
||||
/* update the regl state */
|
||||
@@ -156,6 +186,16 @@ class Graph extends React.Component {
|
||||
this.state.sizeBuffer({ data: this.renderCache.sizes, dimension: 1 });
|
||||
|
||||
this.count = cellCount;
|
||||
|
||||
this.state.regl._refresh();
|
||||
this.reglDraw(
|
||||
this.state.regl,
|
||||
this.state.drawPoints,
|
||||
this.state.sizeBuffer,
|
||||
this.state.colorBuffer,
|
||||
this.state.pointBuffer,
|
||||
this.state.camera
|
||||
);
|
||||
}
|
||||
|
||||
if (
|
||||
@@ -164,8 +204,9 @@ class Graph extends React.Component {
|
||||
nextProps.responsive.width !== this.props.responsive.width
|
||||
) {
|
||||
/* clear out whatever was on the div, even if nothing, but usually the brushes etc */
|
||||
d3.select("#graphAttachPoint")
|
||||
.selectAll("*")
|
||||
d3
|
||||
.select("#graphAttachPoint")
|
||||
.selectAll("svg")
|
||||
.remove();
|
||||
const { svg, brush, brushContainer } = setupSVGandBrushElements(
|
||||
this.handleBrushSelectAction.bind(this),
|
||||
@@ -176,6 +217,16 @@ class Graph extends React.Component {
|
||||
this.setState({ svg, brush, brushContainer });
|
||||
}
|
||||
}
|
||||
componentDidUpdate() {
|
||||
if (
|
||||
this.state.reglRender &&
|
||||
this.reglRenderState === "rendering" &&
|
||||
this.state.mode !== "zoom"
|
||||
) {
|
||||
this.state.reglRender.cancel();
|
||||
this.reglRenderState = "paused";
|
||||
}
|
||||
}
|
||||
handleBrushSelectAction() {
|
||||
/* This conditional handles procedural brush deselect. Brush emits an event on procedural deselect because it is move: null */
|
||||
if (d3.event.sourceEvent !== null) {
|
||||
@@ -200,7 +251,7 @@ class Graph extends React.Component {
|
||||
// transform screen coordinates -> cell coordinates
|
||||
const invert = pin => {
|
||||
const x =
|
||||
(2 * pin[0]) / (this.props.responsive.height - this.graphPaddingTop) -
|
||||
2 * pin[0] / (this.props.responsive.height - this.graphPaddingTop) -
|
||||
1;
|
||||
const y =
|
||||
2 *
|
||||
@@ -318,6 +369,7 @@ class Graph extends React.Component {
|
||||
<button
|
||||
onClick={() => {
|
||||
this.handleBrushDeselectAction();
|
||||
this.restartReglLoop();
|
||||
this.setState({ mode: "zoom" });
|
||||
}}
|
||||
style={{
|
||||
@@ -34,7 +34,7 @@ class LeftSideBar extends React.Component {
|
||||
width: "100%"
|
||||
}}
|
||||
>
|
||||
CELLxGENE {globals.datasetTitle}{" "}
|
||||
cellxgene {globals.datasetTitle}{" "}
|
||||
</p>
|
||||
<div style={{ padding: 10 }}>
|
||||
<button
|
||||
@@ -2,7 +2,7 @@
|
||||
import _ from "lodash";
|
||||
import { parseRGB } from "../util/parseRGB";
|
||||
import { createSchemaByDataSniffing } from "../util/schema";
|
||||
var crossfilter = require("../util/typedCrossfilter");
|
||||
import crossfilter from "../util/typedCrossfilter";
|
||||
|
||||
// Deduce the correct crossfilter dimension type from a metadata
|
||||
// schema description.
|
||||
+1
-1
@@ -251,4 +251,4 @@ class BitArray {
|
||||
}
|
||||
}
|
||||
|
||||
module.exports = BitArray;
|
||||
export default BitArray;
|
||||
@@ -29,9 +29,9 @@ more complex API. In a few cases, elements of that API were incorporated.
|
||||
|
||||
*/
|
||||
|
||||
var PositiveIntervals = require("./positiveIntervals");
|
||||
var BitArray = require("./bitArray");
|
||||
var Util = require("./util");
|
||||
import PositiveIntervals from "./positiveIntervals";
|
||||
import BitArray from "./bitArray";
|
||||
import {fillRange, lowerBound, lowerBoundIndirect, upperBound, upperBoundIndirect} from "./util";
|
||||
|
||||
class TypedCrossfilter {
|
||||
constructor(data) {
|
||||
@@ -118,7 +118,7 @@ class ScalarDimension {
|
||||
this.value = array;
|
||||
|
||||
// create sort index
|
||||
this.index = Util.fillRange(new Uint32Array(this.crossfilter.data.length));
|
||||
this.index = fillRange(new Uint32Array(this.crossfilter.data.length));
|
||||
this.index.sort((a, b) => array[a] - array[b]);
|
||||
|
||||
// groups, if any
|
||||
@@ -199,14 +199,14 @@ class ScalarDimension {
|
||||
// filter by value - exact match
|
||||
filterExact(value) {
|
||||
const newFilter = [
|
||||
Util.lowerBoundIndirect(
|
||||
lowerBoundIndirect(
|
||||
this.value,
|
||||
this.index,
|
||||
value,
|
||||
0,
|
||||
this.value.length
|
||||
),
|
||||
Util.upperBoundIndirect(
|
||||
upperBoundIndirect(
|
||||
this.value,
|
||||
this.index,
|
||||
value,
|
||||
@@ -227,14 +227,14 @@ class ScalarDimension {
|
||||
const newFilter = [];
|
||||
for (let v = 0, len = values.length; v < len; v++) {
|
||||
const intv = [
|
||||
Util.lowerBoundIndirect(
|
||||
lowerBoundIndirect(
|
||||
this.value,
|
||||
this.index,
|
||||
values[v],
|
||||
0,
|
||||
this.value.length
|
||||
),
|
||||
Util.upperBoundIndirect(
|
||||
upperBoundIndirect(
|
||||
this.value,
|
||||
this.index,
|
||||
values[v],
|
||||
@@ -253,14 +253,14 @@ class ScalarDimension {
|
||||
filterRange(range) {
|
||||
const newFilter = [];
|
||||
const intv = [
|
||||
Util.lowerBoundIndirect(
|
||||
lowerBoundIndirect(
|
||||
this.value,
|
||||
this.index,
|
||||
range[0],
|
||||
0,
|
||||
this.value.length
|
||||
),
|
||||
Util.upperBoundIndirect(
|
||||
upperBoundIndirect(
|
||||
this.value,
|
||||
this.index,
|
||||
range[1],
|
||||
@@ -380,7 +380,7 @@ class EnumDimension extends ScalarDimension {
|
||||
const enumLen = this.enumIndex.length;
|
||||
for (let i = 0; i < len; i++) {
|
||||
const v = value(data[i]);
|
||||
const e = Util.lowerBound(this.enumIndex, v, 0, enumLen);
|
||||
const e = lowerBound(this.enumIndex, v, 0, enumLen);
|
||||
array[i] = e;
|
||||
}
|
||||
return array;
|
||||
@@ -388,14 +388,14 @@ class EnumDimension extends ScalarDimension {
|
||||
|
||||
filterExact(value) {
|
||||
return super.filterExact(
|
||||
Util.lowerBound(this.enumIndex, value, 0, this.enumIndex.length)
|
||||
lowerBound(this.enumIndex, value, 0, this.enumIndex.length)
|
||||
);
|
||||
}
|
||||
|
||||
filterEnum(values) {
|
||||
return super.filterEnum(
|
||||
values.map(v =>
|
||||
Util.lowerBound(this.enumIndex, v, 0, this.enumIndex.length)
|
||||
lowerBound(this.enumIndex, v, 0, this.enumIndex.length)
|
||||
)
|
||||
);
|
||||
}
|
||||
@@ -403,7 +403,7 @@ class EnumDimension extends ScalarDimension {
|
||||
filterRange(range) {
|
||||
return super.filterEnum(
|
||||
range.map(v =>
|
||||
Util.lowerBound(this.enumIndex, v, 0, this.enumIndex.length)
|
||||
lowerBound(this.enumIndex, v, 0, this.enumIndex.length)
|
||||
)
|
||||
);
|
||||
}
|
||||
@@ -609,4 +609,4 @@ crossfilter.TypedCrossfilter = TypedCrossfilter;
|
||||
crossfilter.ScalarDimension = ScalarDimension;
|
||||
crossfilter.EnumDimension = EnumDimension;
|
||||
|
||||
module.exports = crossfilter;
|
||||
export default crossfilter;
|
||||
+1
-1
@@ -129,4 +129,4 @@ class PositiveIntervals {
|
||||
}
|
||||
}
|
||||
|
||||
module.exports = PositiveIntervals;
|
||||
export default PositiveIntervals;
|
||||
@@ -8,7 +8,7 @@
|
||||
// fill an array or typedarray with a sequential range of numbers,
|
||||
// starting with `start`
|
||||
//
|
||||
function fillRange(arr, start = 0) {
|
||||
export function fillRange(arr, start = 0) {
|
||||
for (let i = 0, len = arr.length; i < len; i++) {
|
||||
arr[i] = i + start;
|
||||
}
|
||||
@@ -30,7 +30,7 @@ function fillRange(arr, start = 0) {
|
||||
// a factory version of lowerBound that takes an accessor (rather than having
|
||||
// a special-cased version for lining the indirection).
|
||||
//
|
||||
function lowerBound(valueArray, value, first, last) {
|
||||
export function lowerBound(valueArray, value, first, last) {
|
||||
// this is just a binary search
|
||||
while (first < last) {
|
||||
const middle = (first + last) >>> 1;
|
||||
@@ -45,7 +45,7 @@ function lowerBound(valueArray, value, first, last) {
|
||||
|
||||
// Inlined performance optimization - used to indirect through a sort map.
|
||||
//
|
||||
function lowerBoundIndirect(valueArray, indexArray, value, first, last) {
|
||||
export function lowerBoundIndirect(valueArray, indexArray, value, first, last) {
|
||||
// this is just a binary search
|
||||
while (first < last) {
|
||||
const middle = (first + last) >>> 1;
|
||||
@@ -69,7 +69,7 @@ function lowerBoundIndirect(valueArray, indexArray, value, first, last) {
|
||||
// C++: upper_bound()
|
||||
// Python: bisect.bisect_right()
|
||||
//
|
||||
function upperBound(valueArray, value, first, last) {
|
||||
export function upperBound(valueArray, value, first, last) {
|
||||
// this is just a binary search
|
||||
while (first < last) {
|
||||
const middle = (first + last) >>> 1;
|
||||
@@ -84,7 +84,7 @@ function upperBound(valueArray, value, first, last) {
|
||||
|
||||
// Inline performance optimization
|
||||
//
|
||||
function upperBoundIndirect(valueArray, indexArray, value, first, last) {
|
||||
export function upperBoundIndirect(valueArray, indexArray, value, first, last) {
|
||||
// this is just a binary search
|
||||
while (first < last) {
|
||||
const middle = (first + last) >>> 1;
|
||||
@@ -96,11 +96,3 @@ function upperBoundIndirect(valueArray, indexArray, value, first, last) {
|
||||
}
|
||||
return first;
|
||||
}
|
||||
|
||||
module.exports = {
|
||||
fillRange,
|
||||
lowerBound,
|
||||
lowerBoundIndirect,
|
||||
upperBound,
|
||||
upperBoundIndirect
|
||||
};
|
||||
Binary file not shown.
@@ -0,0 +1,32 @@
|
||||
{
|
||||
"CellName": {
|
||||
"type": "string",
|
||||
"variabletype": "categorical",
|
||||
"displayname": "Name",
|
||||
"include": true
|
||||
},
|
||||
"n_genes": {
|
||||
"type": "int",
|
||||
"variabletype": "continuous",
|
||||
"displayname": "Num Genes",
|
||||
"include": true
|
||||
},
|
||||
"percent_mito": {
|
||||
"type": "float",
|
||||
"variabletype": "continuous",
|
||||
"displayname": "Mitochondrial Percentage",
|
||||
"include": true
|
||||
},
|
||||
"n_counts": {
|
||||
"type": "float",
|
||||
"variabletype": "continuous",
|
||||
"displayname": "Num Counts",
|
||||
"include": true
|
||||
},
|
||||
"louvain": {
|
||||
"type": "string",
|
||||
"variabletype": "categorical",
|
||||
"displayname": "Louvain Cluster",
|
||||
"include": true
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,57 @@
|
||||
import os
|
||||
|
||||
from flask import Flask
|
||||
from flask_compress import Compress
|
||||
from flask_cors import CORS
|
||||
from flask_restful_swagger_2 import get_swagger_blueprint
|
||||
|
||||
from .web import webapp
|
||||
from .rest_api.rest import get_api_resources
|
||||
|
||||
REACTIVE_LIMIT = 1_000_000
|
||||
|
||||
app = Flask(__name__)
|
||||
Compress(app)
|
||||
CORS(app)
|
||||
|
||||
# Config
|
||||
CXG_DIR = os.environ.get("CXG_DIRECTORY", default="example-dataset/")
|
||||
SECRET_KEY = os.environ.get("CXG_SECRET_KEY", default="SparkleAndShine")
|
||||
ENGINE = os.environ.get("CXG_ENGINE", default="scanpy")
|
||||
TITLE = os.environ.get("DATASET_TITLE", default="PBMC 3K")
|
||||
# TODO remove the 2 when this is prod
|
||||
CXG_API_BASE = os.environ.get("CXG_API_BASE2", default="http://0.0.0.0:5005/api/")
|
||||
|
||||
app.config.update(
|
||||
SECRET_KEY=SECRET_KEY,
|
||||
CXG_API_BASE=CXG_API_BASE,
|
||||
ENGINE=ENGINE,
|
||||
DATA=CXG_DIR,
|
||||
DATASET_TITLE=TITLE
|
||||
)
|
||||
|
||||
app.config["PROFILE"] = True
|
||||
# app.wsgi_app = ProfilerMiddleware(app.wsgi_app, restrictions=[15])
|
||||
|
||||
# Application Data
|
||||
data = None
|
||||
if app.config["ENGINE"] == "scanpy":
|
||||
from .scanpy_engine.scanpy_engine import ScanpyEngine
|
||||
data = ScanpyEngine(app.config["DATA"], schema="data_schema.json")
|
||||
|
||||
# A list of swagger document objects
|
||||
docs = []
|
||||
resources = get_api_resources()
|
||||
docs.append(resources.get_swagger_doc())
|
||||
|
||||
app.register_blueprint(webapp.bp)
|
||||
app.register_blueprint(resources.blueprint)
|
||||
app.register_blueprint(
|
||||
get_swagger_blueprint(docs, "/api/swagger", produces=["application/json"], title="cellxgene rest api",
|
||||
description="An API connecting ExpressionMatrix2 clustering algorithm to cellxgene"))
|
||||
|
||||
app.add_url_rule("/", endpoint="index")
|
||||
|
||||
|
||||
def main():
|
||||
app.run(host="0.0.0.0", debug=True, port=5005)
|
||||
@@ -0,0 +1,81 @@
|
||||
from abc import ABCMeta, abstractmethod
|
||||
|
||||
|
||||
class CXGDriver(metaclass=ABCMeta):
|
||||
def __init__(self, data, schema=None, graph_method=None, diffexp_method=None):
|
||||
self.data = self._load_data(data)
|
||||
|
||||
@staticmethod
|
||||
@abstractmethod
|
||||
def _load_data(data):
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
def _load_or_infer_schema(data):
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
def cells(self):
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
def genes(self):
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
def filter_cells(self, filter):
|
||||
"""
|
||||
Filter cells from data and return a subset of the data
|
||||
A filter is a dictionary where the key is a metadatata category
|
||||
Value is dictionary
|
||||
value_type: int, float, string
|
||||
variable_type: continuous, categorical
|
||||
query: filter value, for categorical [val1, val2], for continuous {min: x, max:y}
|
||||
Filters are combined with the and operator
|
||||
:param filter:
|
||||
:return: filtered dataframe
|
||||
"""
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
def metadata(self, df, fields=None):
|
||||
"""
|
||||
Gets metadata key:value for each cells
|
||||
|
||||
:param df: from filter_cells, dataframe
|
||||
:param fields: list of keys for metadata to return, returns all metadata values if not set.
|
||||
:return: list of metadata values
|
||||
"""
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
def create_graph(self, df):
|
||||
"""
|
||||
Computes a n-d layout for cells through dimensionality reduction.
|
||||
:param df: from filter_cells, dataframe
|
||||
:return: [cellid, x, y]
|
||||
"""
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
def diffexp(self, df1, df2):
|
||||
"""
|
||||
Computes the top differentially expressed genes between two clusters
|
||||
:param df1: from filter_cells, dataframe containing first set of cells
|
||||
:param df2: from filter_cells, dataframe containing second set of cells
|
||||
:return: top genes, stats and expression values for top genes
|
||||
"""
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
def expression(self, df):
|
||||
"""
|
||||
Retrieves expression for each gene for cells in data frame
|
||||
:param df:
|
||||
:return: {
|
||||
"genes": list of genes,
|
||||
"cells": list of cells and expression list,
|
||||
"nonzero_gene_count": number of nonzero genes
|
||||
}
|
||||
"""
|
||||
pass
|
||||
@@ -0,0 +1,439 @@
|
||||
from flask import (
|
||||
Blueprint, request
|
||||
)
|
||||
from flask_restful_swagger_2 import Api, swagger, Resource
|
||||
|
||||
from ..util.utils import make_payload
|
||||
from ..util.filter import parse_filter
|
||||
|
||||
|
||||
class InitializeAPI(Resource):
|
||||
@swagger.doc({
|
||||
"summary": "get metadata schema, ranges for values, and cell count to initialize cellxgene app",
|
||||
"tags": ["initialize"],
|
||||
"parameters": [],
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "initialization data for UI",
|
||||
"examples": {
|
||||
"application/json": {
|
||||
"data": {
|
||||
"cellcount": 3589,
|
||||
"options": {
|
||||
"Sample.type": {
|
||||
"options": {
|
||||
"Glioblastoma": 3589
|
||||
}
|
||||
},
|
||||
"Selection": {
|
||||
"options": {
|
||||
"Astrocytes(HEPACAM)": 714,
|
||||
"Endothelial(BSC)": 123,
|
||||
"Microglia(CD45)": 1108,
|
||||
"Neurons(Thy1)": 685,
|
||||
"Oligodendrocytes(GC)": 294,
|
||||
"Unpanned": 665
|
||||
}
|
||||
},
|
||||
"Splice_sites_AT.AC": {
|
||||
"range": {
|
||||
"max": 1025,
|
||||
"min": 152
|
||||
}
|
||||
},
|
||||
"Splice_sites_Annotated": {
|
||||
"range": {
|
||||
"max": 1075869,
|
||||
"min": 26
|
||||
}
|
||||
}
|
||||
},
|
||||
"schema": {
|
||||
"CellName": {
|
||||
"displayname": "Name",
|
||||
"type": "string",
|
||||
"variabletype": "categorical"
|
||||
},
|
||||
"Class": {
|
||||
"displayname": "Class",
|
||||
"type": "string",
|
||||
"variabletype": "categorical"
|
||||
},
|
||||
"ERCC_reads": {
|
||||
"displayname": "ERCC Reads",
|
||||
"type": "int",
|
||||
"variabletype": "continuous"
|
||||
},
|
||||
"ERCC_to_non_ERCC": {
|
||||
"displayname": "ERCC:Non-ERCC",
|
||||
"type": "float",
|
||||
"variabletype": "continuous"
|
||||
},
|
||||
"Genes_detected": {
|
||||
"displayname": "Genes Detected",
|
||||
"type": "int",
|
||||
"variabletype": "continuous"
|
||||
}
|
||||
},
|
||||
"genes": ["1/2-SBSRNA4", "A1BG", "A1BG-AS1"]
|
||||
|
||||
},
|
||||
"status": {
|
||||
"error": False,
|
||||
"errormessage": ""
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
})
|
||||
def get(self):
|
||||
from server.app.app import data, REACTIVE_LIMIT
|
||||
return make_payload({
|
||||
"schema": data.schema,
|
||||
"cellcount": data.cell_count,
|
||||
"reactivelimit": REACTIVE_LIMIT,
|
||||
"genes": data.genes(),
|
||||
"ranges": data.metadata_ranges(),
|
||||
|
||||
})
|
||||
|
||||
|
||||
class CellsAPI(Resource):
|
||||
@swagger.doc({
|
||||
"summary": "filter based on metadata fields to get a subset cells, expression data, and metadata",
|
||||
"tags": ["cells"],
|
||||
"description": "Cells takes query parameters defined in the schema retrieved from the /initialize enpoint. "
|
||||
"<br>For categorical metadata keys filter based on `key=value` <br>"
|
||||
" For continuous metadata keys filter by `key=min,max`<br> Either value "
|
||||
"can be replaced by a \*. To have only a minimum value `key=min,\*` To have only a maximum "
|
||||
"value `key=\*,max` <br>Graph data (if retrieved) is normalized"
|
||||
" To only retrieve cells that don't have a value for the key filter by `key`",
|
||||
"parameters": [],
|
||||
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "initialization data for UI",
|
||||
"examples": {
|
||||
"application/json": {
|
||||
"data": {
|
||||
"badmetadatacount": 0,
|
||||
"cellcount": 0,
|
||||
"cellids": ["..."],
|
||||
"metadata": [
|
||||
{
|
||||
"CellName": "1001000173.G8",
|
||||
"Class": "Neoplastic",
|
||||
"Cluster_2d": "11",
|
||||
"Cluster_2d_color": "#8C564B",
|
||||
"Cluster_CNV": "1",
|
||||
"Cluster_CNV_color": "#1F77B4",
|
||||
"ERCC_reads": "152104",
|
||||
"ERCC_to_non_ERCC": "0.562454470489481",
|
||||
"Genes_detected": "1962",
|
||||
"Location": "Tumor",
|
||||
"Location.color": "#FF7F0E",
|
||||
"Multimapping_reads_percent": "2.67",
|
||||
"Neoplastic": "Neoplastic",
|
||||
"Non_ERCC_reads": "270429",
|
||||
"Sample.name": "BT_S2",
|
||||
"Sample.name.color": "#AEC7E8",
|
||||
"Sample.type": "Glioblastoma",
|
||||
"Sample.type.color": "#1F77B4",
|
||||
"Selection": "Unpanned",
|
||||
"Selection.color": "#98DF8A",
|
||||
"Splice_sites_AT.AC": "102",
|
||||
"Splice_sites_Annotated": "122397",
|
||||
"Splice_sites_GC.AG": "761",
|
||||
"Splice_sites_GT.AG": "125741",
|
||||
"Splice_sites_non_canonical": "56",
|
||||
"Splice_sites_total": "126660",
|
||||
"Total_reads": "1741039",
|
||||
"Unique_reads": "1400382",
|
||||
"Unique_reads_percent": "80.43",
|
||||
"Unmapped_mismatch": "2.15",
|
||||
"Unmapped_other": "0.18",
|
||||
"Unmapped_short": "14.56",
|
||||
"housekeeping_cluster": "2",
|
||||
"housekeeping_cluster_color": "#AEC7E8",
|
||||
"recluster_myeloid": "NA",
|
||||
"recluster_myeloid_color": "NA"
|
||||
},
|
||||
],
|
||||
"reactive": True,
|
||||
"graph": [
|
||||
[
|
||||
"1001000173.G8",
|
||||
0.93836,
|
||||
0.28623
|
||||
],
|
||||
|
||||
[
|
||||
"1001000173.D4",
|
||||
0.1662,
|
||||
0.79438
|
||||
]
|
||||
|
||||
],
|
||||
"status": {
|
||||
"error": False,
|
||||
"errormessage": ""
|
||||
}
|
||||
|
||||
},
|
||||
}
|
||||
},
|
||||
},
|
||||
|
||||
"400": {
|
||||
"description": "bad query params",
|
||||
}
|
||||
}
|
||||
})
|
||||
def get(self):
|
||||
from server.app.app import data
|
||||
payload = {
|
||||
"metadata": [],
|
||||
"cellcount": 0,
|
||||
"graph": [],
|
||||
"ranges": {},
|
||||
}
|
||||
# get query params
|
||||
cells_filter = parse_filter(request.args, data.schema)
|
||||
filtered_data = data.filter_cells(cells_filter)
|
||||
payload["metadata"] = data.metadata(filtered_data)
|
||||
payload["ranges"] = data.metadata_ranges(filtered_data)
|
||||
payload["graph"] = data.create_graph(filtered_data)
|
||||
payload["cellcount"] = data.cell_count
|
||||
return make_payload(payload)
|
||||
|
||||
|
||||
class ExpressionAPI(Resource):
|
||||
@swagger.doc({
|
||||
"summary": "Json with gene list and expression data by cell, limited to first 40 cells",
|
||||
"tags": ["expression"],
|
||||
"parameters": [
|
||||
{
|
||||
"name": "include_unexpressed_genes",
|
||||
"description": "Include genes that have 0 expression across all cells in set",
|
||||
"in": "path",
|
||||
"type": "bool",
|
||||
}
|
||||
],
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "Json for heatmap",
|
||||
"examples": {
|
||||
"application/json": {
|
||||
"data": {
|
||||
"cells": [
|
||||
{
|
||||
"cellname": "1/2-SBSRNA4",
|
||||
"e": [0, 0, 214, 0, 0]
|
||||
},
|
||||
],
|
||||
"genes": [
|
||||
"1001000173.G8",
|
||||
"1001000173.D4",
|
||||
"1001000173.B4",
|
||||
"1001000173.A2",
|
||||
"1001000173.E2"
|
||||
],
|
||||
"nonzero_gene_count": 2857
|
||||
},
|
||||
"status": {
|
||||
"error": False,
|
||||
"errormessage": ""
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
})
|
||||
def get(self):
|
||||
from server.app.app import data
|
||||
expression_data = data.expression()
|
||||
return make_payload(expression_data)
|
||||
|
||||
@swagger.doc({
|
||||
"summary": "Json with gene list and expression data by cell",
|
||||
"tags": ["expression"],
|
||||
"parameters": [
|
||||
{
|
||||
"name": "body",
|
||||
"in": "body",
|
||||
"schema": {
|
||||
"example": {
|
||||
"celllist": ["1001000173.G8", "1001000173.D4"],
|
||||
"genelist": ["1/2-SBSRNA4", "A1BG", "A1BG-AS1", "A1CF", "A2LD1", "A2M", "A2ML1", "A2MP1",
|
||||
"A4GALT"],
|
||||
"include_unexpressed_genes": True,
|
||||
}
|
||||
|
||||
}
|
||||
},
|
||||
],
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "Json for expressiondata",
|
||||
"examples": {
|
||||
"application/json": {
|
||||
"data": {
|
||||
"cells": [
|
||||
{
|
||||
"cellname": "1001000173.D4",
|
||||
"e": [0, 0]
|
||||
},
|
||||
{
|
||||
"cellname": "1001000173.G8",
|
||||
"e": [0, 0]
|
||||
}
|
||||
],
|
||||
"genes": [
|
||||
"ABCD4",
|
||||
"ZWINT"
|
||||
],
|
||||
"nonzero_gene_count": 2857
|
||||
},
|
||||
"status": {
|
||||
"error": False,
|
||||
"errormessage": ""
|
||||
}
|
||||
|
||||
}
|
||||
}
|
||||
},
|
||||
"400": {
|
||||
"description": "Required parameter missing/incorrect",
|
||||
}
|
||||
}
|
||||
})
|
||||
def post(self):
|
||||
from server.app.app import data
|
||||
args = request.get_json()
|
||||
cell_list = args.get("celllist", [])
|
||||
gene_list = args.get("genelist", [])
|
||||
if not cell_list and not gene_list:
|
||||
return make_payload([], "must include celllist and/or genelist parameter", 400)
|
||||
|
||||
expression_data = data.expression(cell_list, gene_list)
|
||||
|
||||
if cell_list and len(expression_data["cells"]) < len(cell_list):
|
||||
return make_payload([], "Some cell ids not available", 400)
|
||||
if gene_list and len(expression_data["genes"]) < len(gene_list):
|
||||
return make_payload([], "Some genes not available", 400)
|
||||
|
||||
return make_payload(expression_data)
|
||||
|
||||
|
||||
class DifferentialExpressionAPI(Resource):
|
||||
@swagger.doc({
|
||||
"summary": "Get the top expressed genes for two cell sets. Calculated using t-test",
|
||||
"tags": ["expression"],
|
||||
"parameters": [
|
||||
{
|
||||
"name": "body",
|
||||
"in": "body",
|
||||
"schema": {
|
||||
"example": {
|
||||
"celllist1": ["1001000176.C12", "1001000176.C7", "1001000177.F11"],
|
||||
"celllist2": ["1001000012.D2", "1001000017.F10", "1001000033.C3", "1001000229.D4"],
|
||||
"num_genes": 5,
|
||||
"pval": 0.000001,
|
||||
},
|
||||
}
|
||||
}
|
||||
],
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "top expressed genes for cellset1, cellset2",
|
||||
"examples": {
|
||||
"application/json": {
|
||||
"data": {
|
||||
"celllist1": {
|
||||
"ave_diff": [
|
||||
432.0132935431362,
|
||||
12470.5623982637,
|
||||
957.0246880086814
|
||||
],
|
||||
"mean_expression_cellset1": [
|
||||
438.6185567010309,
|
||||
13315.536082474227,
|
||||
1076.5773195876288
|
||||
],
|
||||
"mean_expression_cellset2": [
|
||||
6.605263157894737,
|
||||
844.9736842105264,
|
||||
119.55263157894737
|
||||
],
|
||||
"pval": [
|
||||
3.8906598089944563e-35,
|
||||
1.9086226376018916e-25,
|
||||
7.847480544069826e-21
|
||||
],
|
||||
"topgenes": [
|
||||
"TMSB10",
|
||||
"FTL",
|
||||
"TMSB4X"
|
||||
]
|
||||
},
|
||||
"celllist2": {
|
||||
"ave_diff": [
|
||||
-6860.599158979924,
|
||||
-519.1314432989691,
|
||||
-10278.328269126423
|
||||
],
|
||||
"mean_expression_cellset1": [
|
||||
2.8350515463917527,
|
||||
0.6185567010309279,
|
||||
23.09278350515464
|
||||
],
|
||||
"mean_expression_cellset2": [
|
||||
6863.434210526316,
|
||||
519.75,
|
||||
10301.421052631578
|
||||
],
|
||||
"pval": [
|
||||
4.662891833748732e-44,
|
||||
3.6278087029927103e-37,
|
||||
8.396825170618402e-35
|
||||
],
|
||||
"topgenes": [
|
||||
"SPARCL1",
|
||||
"C1orf61",
|
||||
"CLU"
|
||||
]
|
||||
}
|
||||
},
|
||||
"status": {
|
||||
"error": False,
|
||||
"errormessage": ""
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
})
|
||||
def post(self):
|
||||
from server.app.app import data
|
||||
args = request.get_json()
|
||||
cell_list_1 = args.get("celllist1", [])
|
||||
cell_list_2 = args.get("celllist2", [])
|
||||
num_genes = args.get("num_genes", 7)
|
||||
pval = args.get("pval", 0.5)
|
||||
if not (cell_list_1 and cell_list_2):
|
||||
return make_payload([],
|
||||
"must include celllist1 and celllist2 parameters",
|
||||
400)
|
||||
data = data.diffexp(cell_list_1, cell_list_2, pval, num_genes)
|
||||
return make_payload(data)
|
||||
|
||||
|
||||
def get_api_resources():
|
||||
bp = Blueprint("api", __name__, url_prefix="/api/v0.1")
|
||||
api = Api(bp, add_api_spec_resource=False)
|
||||
api.add_resource(InitializeAPI, "/initialize")
|
||||
api.add_resource(CellsAPI, "/cells")
|
||||
api.add_resource(ExpressionAPI, "/expression")
|
||||
api.add_resource(DifferentialExpressionAPI, "/diffexpression")
|
||||
return api
|
||||
@@ -0,0 +1,198 @@
|
||||
import os
|
||||
|
||||
import numpy as np
|
||||
import scanpy.api as sc
|
||||
from scipy import stats
|
||||
|
||||
from ..util.schema_parse import parse_schema
|
||||
from ..driver.driver import CXGDriver
|
||||
|
||||
|
||||
class ScanpyEngine(CXGDriver):
|
||||
|
||||
def __init__(self, data, schema=None, graph_method="umap", diffexp_method="ttest"):
|
||||
self.data = self._load_data(data)
|
||||
self.schema = self._load_or_infer_schema(data, schema)
|
||||
self._set_cell_names()
|
||||
self.cell_count = self.data.shape[0]
|
||||
self.gene_count = self.data.shape[1]
|
||||
self.graph_method = graph_method
|
||||
self.diffexp_method = diffexp_method
|
||||
|
||||
def _set_cell_names(self):
|
||||
self.data.obs["cell_name"] = list(self.data.obs.index)
|
||||
|
||||
@staticmethod
|
||||
def _load_data(data):
|
||||
return sc.read(os.path.join(data, "data.h5ad"))
|
||||
|
||||
@staticmethod
|
||||
def _load_or_infer_schema(data, schema):
|
||||
data_schema = None
|
||||
if not schema:
|
||||
pass
|
||||
else:
|
||||
data_schema = parse_schema(os.path.join(data, schema))
|
||||
return data_schema
|
||||
|
||||
def cells(self):
|
||||
return list(self.data.obs.index)
|
||||
|
||||
def genes(self):
|
||||
return self.data.var.index.tolist()
|
||||
|
||||
def filter_cells(self, filter):
|
||||
"""
|
||||
Filter cells from data and return a subset of the data
|
||||
A filter is a dictionary where the key is a metadatata category
|
||||
Value is dictionary
|
||||
value_type: int, float, string
|
||||
variable_type: continuous, categorical
|
||||
query: filter value, for categorical [val1, val2], for continuous {min: x, max:y}
|
||||
Filters are combined with the and operator
|
||||
:param filter:
|
||||
:return: filtered dataframe
|
||||
"""
|
||||
cell_idx = np.ones((self.cell_count,), dtype=bool)
|
||||
for key, value in filter.items():
|
||||
if value["variable_type"] == "categorical":
|
||||
key_idx = np.in1d(getattr(self.data.obs, key), value["query"])
|
||||
cell_idx = np.logical_and(cell_idx, key_idx)
|
||||
else:
|
||||
min_ = value["query"]["min"]
|
||||
max_ = value["query"]["max"]
|
||||
if min_ is not None:
|
||||
key_idx = np.array((getattr(self.data.obs, key) >= min_).data)
|
||||
cell_idx = np.logical_and(cell_idx, key_idx)
|
||||
if max_ is not None:
|
||||
key_idx = np.array((getattr(self.data.obs, key) <= max_).data)
|
||||
cell_idx = np.logical_and(cell_idx, key_idx)
|
||||
return self.data[cell_idx, :]
|
||||
|
||||
def metadata_ranges(self, df=None):
|
||||
metadata_ranges = {}
|
||||
if not df:
|
||||
df = self.data
|
||||
for field in self.schema:
|
||||
if self.schema[field]["variabletype"] == "categorical":
|
||||
group_by = field
|
||||
if group_by == "CellName":
|
||||
group_by = "cell_name"
|
||||
metadata_ranges[field] = {"options": df.obs.groupby(group_by).size().to_dict()}
|
||||
else:
|
||||
metadata_ranges[field] = {
|
||||
"range": {
|
||||
"min": df.obs[field].min(),
|
||||
"max": df.obs[field].max()
|
||||
}
|
||||
}
|
||||
return metadata_ranges
|
||||
|
||||
def metadata(self, df, fields=None):
|
||||
"""
|
||||
Gets metadata key:value for each cells
|
||||
|
||||
:param df: from filter_cells, dataframe
|
||||
:param fields: list of keys for metadata to return, returns all metadata values if not set.
|
||||
:return: list of metadata values
|
||||
"""
|
||||
metadata = df.obs.to_dict(orient="records")
|
||||
for idx in range(len(metadata)):
|
||||
metadata[idx]["CellName"] = metadata[idx].pop("cell_name", None)
|
||||
return metadata
|
||||
|
||||
def create_graph(self, df):
|
||||
"""
|
||||
Computes a n-d layout for cells through dimensionality reduction.
|
||||
:param df: from filter_cells, dataframe
|
||||
:return: [cellid, x, y]
|
||||
"""
|
||||
getattr(sc.tl, self.graph_method)(df, random_state=123)
|
||||
graph = df.obsm["X_{graph_method}".format(graph_method=self.graph_method)]
|
||||
normalized_graph = (graph - graph.min()) / (graph.max() - graph.min())
|
||||
return np.hstack((df.obs["cell_name"].values.reshape(len(df.obs.index), 1), normalized_graph)).tolist()
|
||||
|
||||
def diffexp(self, cell_list_1, cell_list_2, pval, num_genes):
|
||||
"""
|
||||
Computes the top differentially expressed genes between two clusters
|
||||
:param df1: from filter_cells, dataframe containing first set of cells
|
||||
:param df2: from filter_cells, dataframe containing second set of cells
|
||||
:return: top genes, stats and expression values for top genes
|
||||
"""
|
||||
cells_idx_1 = np.in1d(self.data.obs["cell_name"], cell_list_1)
|
||||
cells_idx_2 = np.in1d(self.data.obs["cell_name"], cell_list_2)
|
||||
expression_1 = self.data.X[cells_idx_1, :]
|
||||
expression_2 = self.data.X[cells_idx_2, :]
|
||||
diff_exp = stats.ttest_ind(expression_1, expression_2)
|
||||
# TODO break this up into functions
|
||||
set1 = np.logical_and(diff_exp.pvalue < pval, diff_exp.statistic > 0)
|
||||
set2 = np.logical_and(diff_exp.pvalue < pval, diff_exp.statistic < 0)
|
||||
stat1 = diff_exp.statistic[set1]
|
||||
stat2 = diff_exp.statistic[set2]
|
||||
sort_set1 = np.argsort(stat1)[::-1]
|
||||
sort_set2 = np.argsort(stat2)
|
||||
pval1 = diff_exp.pvalue[set1][sort_set1]
|
||||
pval2 = diff_exp.pvalue[set2][sort_set2]
|
||||
mean_ex1_set1 = np.mean(expression_1[:, set1], axis=0)[sort_set1]
|
||||
mean_ex2_set1 = np.mean(expression_2[:, set1], axis=0)[sort_set1]
|
||||
mean_ex1_set2 = np.mean(expression_1[:, set2], axis=0)[sort_set2]
|
||||
mean_ex2_set2 = np.mean(expression_2[:, set2], axis=0)[sort_set2]
|
||||
mean_diff1 = mean_ex1_set1 - mean_ex2_set1
|
||||
mean_diff2 = mean_ex1_set2 - mean_ex2_set2
|
||||
genes_cellset_1 = self.data.var_names[set1][sort_set1]
|
||||
genes_cellset_2 = self.data.var_names[set2][sort_set2]
|
||||
return {
|
||||
"celllist1": {
|
||||
"topgenes": genes_cellset_1.tolist()[:num_genes],
|
||||
"mean_expression_cellset1": mean_ex1_set1.tolist()[:num_genes],
|
||||
"mean_expression_cellset2": mean_ex2_set1.tolist()[:num_genes],
|
||||
"pval": pval1.tolist()[:num_genes],
|
||||
"ave_diff": mean_diff1.tolist()[:num_genes]
|
||||
},
|
||||
"celllist2": {
|
||||
"topgenes": genes_cellset_2.tolist()[:num_genes],
|
||||
"mean_expression_cellset1": mean_ex1_set2.tolist()[:num_genes],
|
||||
"mean_expression_cellset2": mean_ex2_set2.tolist()[:num_genes],
|
||||
"pval": pval2.tolist()[:num_genes],
|
||||
"ave_diff": mean_diff2.tolist()[:num_genes]
|
||||
},
|
||||
}
|
||||
|
||||
def expression(self, cells=None, genes=None):
|
||||
"""
|
||||
Retrieves expression for each gene for cells in data frame
|
||||
:param df:
|
||||
:return: {
|
||||
"genes": list of genes,
|
||||
"cells": list of cells and expression list,
|
||||
"nonzero_gene_count": number of nonzero genes
|
||||
}
|
||||
"""
|
||||
if cells:
|
||||
cells_idx = np.in1d(self.data.obs["cell_name"], cells)
|
||||
else:
|
||||
cells_idx = np.ones((self.cell_count,), dtype=bool)
|
||||
if genes:
|
||||
genes_idx = np.in1d(self.data.var_names, genes)
|
||||
else:
|
||||
genes_idx = np.ones((self.gene_count,), dtype=bool)
|
||||
index = np.ix_(cells_idx, genes_idx)
|
||||
expression = self.data.X[index]
|
||||
|
||||
if not genes:
|
||||
genes = self.data.var.index.tolist()
|
||||
if not cells:
|
||||
cells = self.data.obs["cell_name"].tolist()
|
||||
|
||||
cell_data = []
|
||||
for idx, cell in enumerate(cells):
|
||||
cell_data.append({
|
||||
"cellname": cell,
|
||||
"e": list(expression[idx]),
|
||||
})
|
||||
|
||||
return {
|
||||
"genes": genes,
|
||||
"cells": cell_data,
|
||||
"nonzero_gene_count": int(np.sum(expression.any(axis=0)))
|
||||
}
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user