feat: update validation for uns['spatial'] (#1129)

Co-authored-by: Evan Molinelli <[email protected]>
Co-authored-by: Nayib Gloria <[email protected]>

cellxgene_schema_cli/cellxgene_schema/validate.py

@@ -28,8 +28,15 @@
 
 VISIUM_AND_IS_SINGLE_TRUE_MATRIX_SIZE = 4992
 SPATIAL_HIRES_IMAGE_MAX_DIMENSION_SIZE = 2000
+SPATIAL_HIRES_IMAGE_MAX_DIMENSION_SIZE_VISIUM_11MM = 4000
 
-ERROR_SUFFIX_VISIUM_AND_IS_SINGLE_TRUE = "descendants of obs['assay_ontology_term_id'] 'EFO:0010961' (Visium Spatial Gene Expression) and uns['spatial']['is_single'] is True"
+CONDITION_IS_VISIUM = "a descendant of 'EFO:0010961' (Visium Spatial Gene Expression)"
+CONDITION_IS_SEQV2 = f"'{ASSAY_SLIDE_SEQV2}' (Slide-seqV2)"
+
+
+ERROR_SUFFIX_SPATIAL = f"obs['assay_ontology_term_id'] is either {CONDITION_IS_VISIUM} or {CONDITION_IS_SEQV2}"
+ERROR_SUFFIX_VISIUM = f"obs['assay_ontology_term_id'] is {CONDITION_IS_VISIUM}"
+ERROR_SUFFIX_VISIUM_AND_IS_SINGLE_TRUE = f"{ERROR_SUFFIX_VISIUM} and uns['spatial']['is_single'] is True"
 ERROR_SUFFIX_VISIUM_AND_IS_SINGLE_TRUE_FORBIDDEN = f"is only allowed for {ERROR_SUFFIX_VISIUM_AND_IS_SINGLE_TRUE}"
 ERROR_SUFFIX_VISIUM_AND_IS_SINGLE_TRUE_REQUIRED = f"is required for {ERROR_SUFFIX_VISIUM_AND_IS_SINGLE_TRUE}"
 ERROR_SUFFIX_VISIUM_AND_IS_SINGLE_TRUE_IN_TISSUE_0 = f"{ERROR_SUFFIX_VISIUM_AND_IS_SINGLE_TRUE} and in_tissue is 0"
@@ -95,9 +102,11 @@ def _is_supported_spatial_assay(self) -> bool:
         """
         if self.is_spatial is None:
             try:
-                self.is_spatial = False
-                if self.adata.obs.assay_ontology_term_id.isin([ASSAY_VISIUM, ASSAY_SLIDE_SEQV2]).any():
-                    self.is_spatial = True
+                _spatial = (
+                    self._is_visium_including_descendants()
+                    or self.adata.obs.assay_ontology_term_id.isin([ASSAY_SLIDE_SEQV2]).any()
+                )
+                self.is_spatial = bool(_spatial)
             except AttributeError:
                 # specific error reporting will occur downstream in the validation
                 self.is_spatial = False
@@ -1466,10 +1475,7 @@ def _validate_spatial_assay_ontology_term_id(self):
         # Validate assay ontology term ids are identical.
         term_count = obs["assay_ontology_term_id"].nunique()
         if term_count > 1:
-            self.errors.append(
-                "When obs['assay_ontology_term_id'] is either 'EFO:0010961' (Visium Spatial Gene Expression) or "
-                "'EFO:0030062' (Slide-seqV2), all observations must contain the same value."
-            )
+            self.errors.append(f"When {ERROR_SUFFIX_SPATIAL}" ", all observations must contain the same value.")
 
     def _validate_spatial_cell_type_ontology_term_id(self):
         """
@@ -1599,10 +1605,7 @@ def _check_spatial_uns(self):
         uns_spatial = self.adata.uns.get("spatial")
         is_supported_spatial_assay = self._is_supported_spatial_assay()
         if uns_spatial is not None and not is_supported_spatial_assay:
-            self.errors.append(
-                "uns['spatial'] is only allowed for obs['assay_ontology_term_id'] values "
-                "'EFO:0010961' (Visium Spatial Gene Expression) and 'EFO:0030062' (Slide-seqV2)."
-            )
+            self.errors.append(f"uns['spatial'] is only allowed when {ERROR_SUFFIX_SPATIAL}")
             return
 
         # Exit if we aren't dealing with a supported spatial assay as no further checks are necessary.
@@ -1611,10 +1614,7 @@ def _check_spatial_uns(self):
 
         # spatial is required for supported spatial assays.
         if not isinstance(uns_spatial, dict):
-            self.errors.append(
-                "A dict in uns['spatial'] is required for obs['assay_ontology_term_id'] values "
-                "'EFO:0010961' (Visium Spatial Gene Expression) and 'EFO:0030062' (Slide-seqV2)."
-            )
+            self.errors.append("A dict in uns['spatial'] is required when " f"{ERROR_SUFFIX_SPATIAL}.")
             return
 
         # is_single is required.
@@ -1693,7 +1693,11 @@ def _check_spatial_uns(self):
                 self.errors.append("uns['spatial'][library_id]['images'] must contain the key 'hires'.")
             # hires is specified: proceed with validation of hires.
             else:
-                self._validate_spatial_image_shape("hires", uns_images["hires"], SPATIAL_HIRES_IMAGE_MAX_DIMENSION_SIZE)
+                _assay_term = self.adata.obs["assay_ontology_term_id"].values[0]
+                _max_size = SPATIAL_HIRES_IMAGE_MAX_DIMENSION_SIZE
+                if is_ontological_descendant_of(ONTOLOGY_PARSER, _assay_term, "EFO:0022860", True):
+                    _max_size = SPATIAL_HIRES_IMAGE_MAX_DIMENSION_SIZE_VISIUM_11MM
+                self._validate_spatial_image_shape("hires", uns_images["hires"], _max_size)
 
             # fullres is optional.
             uns_fullres = uns_images.get("fullres")
@@ -1802,12 +1806,12 @@ def _is_visium_including_descendants(self) -> bool:
             # check if any assay_ontology_term_ids are descendants of VISIUM
             includes_and_visium = (
                 self.adata.obs[_assay_key]
+                .astype("string")
                 .apply(lambda assay: is_ontological_descendant_of(ONTOLOGY_PARSER, assay, ASSAY_VISIUM, True))
                 .any()
             )
+            self.is_visium = includes_and_visium
 
-        # save state and return
-        self.is_visium = includes_and_visium
         return includes_and_visium
 
     def _validate_spatial_image_shape(self, image_name: str, image: np.ndarray, max_dimension: int = None):

cellxgene_schema_cli/tests/test_schema_compliance.py

@@ -4,6 +4,7 @@
 
 import tempfile
 import unittest
+from copy import deepcopy
 
 import anndata
 import fixtures.examples_validate as examples
@@ -495,7 +496,7 @@ def test_column_presence_in_tissue(self, validator_with_visium_assay, assay_onto
             assert validator.errors == []
         else:
             assert validator.errors == [
-                "obs['in_tissue'] is only allowed for descendants of obs['assay_ontology_term_id'] 'EFO:0010961' (Visium Spatial Gene Expression) and uns['spatial']['is_single'] is True."
+                "obs['in_tissue'] is only allowed for obs['assay_ontology_term_id'] is a descendant of 'EFO:0010961' (Visium Spatial Gene Expression) and uns['spatial']['is_single'] is True."
             ]
 
     @pytest.mark.parametrize("reserved_column", schema_def["components"]["obs"]["reserved_columns"])
@@ -1673,11 +1674,16 @@ def test_should_warn_for_low_gene_count(self, validator_with_adata):
         Raise a warning if there are too few genes
         """
         validator = validator_with_adata
+        # NOTE:[EM] changing the schema def here is stateful and results in unpredictable test results.
+        #  Reset after mutating.
+        _old_schema = deepcopy(validator.schema_def.copy())
+
         validator.schema_def["components"]["var"]["warn_if_less_than_rows"] = 100
         validator.validate_adata()
         assert validator.warnings == [
             "WARNING: Dataframe 'var' only has 4 rows. Features SHOULD NOT be filtered from expression matrix."
         ]
+        validator.schema_def = _old_schema
 
     @pytest.mark.parametrize(
         "df,column",
@@ -2198,7 +2204,6 @@ def test_obsm_values_no_X_embedding__non_spatial_dataset(self, validator_with_ad
         ]
         assert validator.is_spatial is False
         assert validator.warnings == [
-            "WARNING: Dataframe 'var' only has 4 rows. Features SHOULD NOT be filtered from expression matrix.",
             "WARNING: Embedding key in 'adata.obsm' harmony is not 'spatial' nor does it start with 'X_'. "
             "Thus, it will not be available in Explorer",
             "WARNING: Validation of raw layer was not performed due to current errors, try again after fixing current errors.",
@@ -2248,7 +2253,6 @@ def test_obsm_values_warn_start_with_X(self, validator_with_adata):
         validator.adata.obsm["harmony"] = pd.DataFrame(validator.adata.obsm["X_umap"], index=validator.adata.obs_names)
         validator.validate_adata()
         assert validator.warnings == [
-            "WARNING: Dataframe 'var' only has 4 rows. Features SHOULD NOT be filtered from expression matrix.",
             "WARNING: Embedding key in 'adata.obsm' harmony is not 'spatial' nor does it start with 'X_'. "
             "Thus, it will not be available in Explorer",
             "WARNING: Validation of raw layer was not performed due to current errors, try again after fixing current errors.",
@@ -2282,7 +2286,6 @@ def test_obsm_values_key_start_with_number(self, validator_with_adata):
             "'pandas.core.frame.DataFrame'>').",
         ]
         assert validator.warnings == [
-            "WARNING: Dataframe 'var' only has 4 rows. Features SHOULD NOT be filtered from expression matrix.",
             "WARNING: Embedding key in 'adata.obsm' 3D is not 'spatial' nor does it start with 'X_'. "
             "Thus, it will not be available in Explorer",
             "WARNING: Validation of raw layer was not performed due to current errors, try again after fixing current errors.",