remove experimental ontology support (#2300)

* remove experimental ontology support

* lint

* remove ontologies from unit tests

* additional test changes

backend/czi_hosted/common/annotations/annotations.py

@@ -1,10 +1,8 @@
-import fastobo
-import fsspec
 import os
 
 from flask import current_app, has_request_context
 
-from backend.common.errors import OntologyLoadFailure, DisabledFeatureError
+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
@@ -12,14 +10,9 @@ from backend.common.utils.utils import path_join
 
 
 class Annotations:
-    """ baseclass for annotations, including ontologies and genesets """
-
-    """ our default ontology is the PURL for the Cell Ontology.
-    See http://www.obofoundry.org/ontology/cl.html """
-    DefaultOnotology = "http://purl.obolibrary.org/obo/cl.obo"
+    """baseclass for annotations and genesets"""
 
     def __init__(self, config={}):
-        self.ontology_data = None
         self.config = config
 
     def user_annotations_enabled(self):
@@ -29,27 +22,6 @@ class Annotations:
         if not self.user_annotations_enabled():
             raise DisabledFeatureError("User annotations are disabled.")
 
-    def load_ontology(self, path):
-        """Load and parse ontologies - currently support OBO files only."""
-        if path is None:
-            path = self.DefaultOnotology
-
-        try:
-            with fsspec.open(path) as f:
-                obo = fastobo.iter(f)
-                terms = filter(lambda stanza: type(stanza) is fastobo.term.TermFrame, obo)
-                names = [tag.name for term in terms for tag in term if type(tag) is fastobo.term.NameClause]
-                self.ontology_data = names
-
-        except FileNotFoundError as e:
-            raise OntologyLoadFailure("Unable to find OBO ontology path") from e
-
-        except SyntaxError as e:
-            raise OntologyLoadFailure(f"{path}:{e.lineno}:{e.offset} OBO syntax error, unable to read ontology") from e
-
-        except Exception as e:
-            raise OntologyLoadFailure(f"{path}:Error loading OBO file") from e
-
     def get_schema(self, data_adaptor):
         schema = []
         labels = self.read_labels(data_adaptor)
@@ -126,7 +98,7 @@ class Annotations:
 
 
 def dataset_uri_to_geneset_uri(data_uri_or_path):
-    """ given a dataset URI, return the associated gene set URI """
+    """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

backend/czi_hosted/common/annotations/hosted_tiledb.py

@@ -164,10 +164,4 @@ class AnnotationsHostedTileDB(Annotations):
         params["annotations"] = True
         params["user_annotation_collection_name_enabled"] = False
 
-        if self.ontology_data:
-            params["annotations_cell_ontology_enabled"] = True
-            params["annotations_cell_ontology_terms"] = self.ontology_data
-        else:
-            params["annotations_cell_ontology_enabled"] = False
-
         parameters.update(params)

backend/czi_hosted/common/annotations/local_file_csv.py

@@ -115,7 +115,7 @@ class AnnotationsLocalFile(Annotations):
         return os.getcwd()
 
     def _get_filename(self, data_adaptor):
-        """ return the current annotation file name """
+        """return the current annotation file name"""
         if self.output_file:
             return self.output_file
 
@@ -175,12 +175,6 @@ class AnnotationsLocalFile(Annotations):
         params["annotations"] = True
         params["user_annotation_collection_name_enabled"] = True
 
-        if self.ontology_data:
-            params["annotations_cell_ontology_enabled"] = True
-            params["annotations_cell_ontology_terms"] = self.ontology_data
-        else:
-            params["annotations_cell_ontology_enabled"] = False
-
         if self.output_file is not None:
             # user has hard-wired the name of the annotation data collection
             fname = os.path.basename(self.output_file)

backend/czi_hosted/common/config/client_config.py

@@ -47,9 +47,6 @@ def get_client_config(app_config, data_adaptor):
         "annotations_genesets": True,  # feature flag
         "annotations_genesets_readonly": True,
         "annotations_genesets_summary_methods": ["mean"],
-        "annotations_cell_ontology_enabled": False,
-        "annotations_cell_ontology_obopath": None,
-        "annotations_cell_ontology_terms": None,
         "custom_colors": dataset_config.presentation__custom_colors,
         "diffexp-may-be-slow": False,
         "about_legal_tos": dataset_config.app__about_legal_tos,

backend/czi_hosted/common/config/dataset_config.py

@@ -5,7 +5,7 @@ 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, OntologyLoadFailure
+from backend.common.errors import ConfigurationError
 from backend.czi_hosted.compute.scanpy import get_scanpy_module
 from backend.czi_hosted.data_common.matrix_loader import MatrixDataLoader, MatrixDataType
 from backend.czi_hosted.db.db_utils import DbUtils
@@ -33,10 +33,6 @@ class DatasetConfig(BaseConfig):
                 "directory"
             ]
             self.user_annotations__local_file_csv__file = default_config["user_annotations"]["local_file_csv"]["file"]
-            self.user_annotations__ontology__enable = default_config["user_annotations"]["ontology"]["enable"]
-            self.user_annotations__ontology__obo_location = default_config["user_annotations"]["ontology"][
-                "obo_location"
-            ]
             self.user_annotations__hosted_tiledb_array__db_uri = default_config["user_annotations"][
                 "hosted_tiledb_array"
             ]["db_uri"]
@@ -55,7 +51,7 @@ class DatasetConfig(BaseConfig):
             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` 
+        # further configuration. Depending on configuration options, `complete_config`
         # may create a more specialized annotation object and replace this default.
         self.user_annotations = Annotations()
 
@@ -101,10 +97,6 @@ class DatasetConfig(BaseConfig):
         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__ontology__enable", bool)
-        self.validate_correct_type_of_configuration_attribute(
-            "user_annotations__ontology__obo_location", (type(None), str)
-        )
         self.validate_correct_type_of_configuration_attribute(
             "user_annotations__hosted_tiledb_array__db_uri", (type(None), str)
         )
@@ -125,11 +117,6 @@ class DatasetConfig(BaseConfig):
                 self.handle_hosted_tiledb_annotations()
             else:
                 raise ConfigurationError('The only annotation type support is "local_file_csv" or "hosted_tiledb_array')
-            if self.user_annotations__ontology__enable or self.user_annotations__ontology__obo_location:
-                try:
-                    self.user_annotations.load_ontology(self.user_annotations__ontology__obo_location)
-                except OntologyLoadFailure as e:
-                    raise ConfigurationError("Unable to load ontology terms\n" + str(e))
         else:
             self.check_annotation_config_vars_not_set(context)
 
@@ -197,13 +184,6 @@ class DatasetConfig(BaseConfig):
                     "Warning: hosted_file_directory for hosted_tiledb_array ignored as annotations are disabled."
                 )
 
-        if self.user_annotations__ontology__enable:
-            context["messagefn"]("Warning: --experimental-annotations-ontology ignored as annotations are disabled.")
-        if self.user_annotations__ontology__obo_location is not None:
-            context["messagefn"](
-                "Warning: --experimental-annotations-ontology-obo ignored as annotations are disabled."
-            )
-
     def handle_embeddings(self):
         self.validate_correct_type_of_configuration_attribute("embeddings__names", list)
         self.validate_correct_type_of_configuration_attribute("embeddings__enable_reembedding", bool)