feat: differential tissue position row/col max sizes for visium and v…

…isium 11 (#1143)

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

cellxgene_schema_cli/cellxgene_schema/validate.py

@@ -4,7 +4,7 @@
 import os
 import re
 from datetime import datetime
-from typing import Dict, List, Mapping, Optional, Union
+from typing import Dict, List, Mapping, Optional, Tuple, Union
 
 import anndata
 import matplotlib.colors as mcolors
@@ -29,6 +29,10 @@
 
 VISIUM_AND_IS_SINGLE_TRUE_MATRIX_SIZE = 4992
 VISIUM_11MM_AND_IS_SINGLE_TRUE_MATRIX_SIZE = 14336
+VISIUM_TISSUE_POSITION_MAX_ROW = 77
+VISIUM_TISSUE_POSITION_MAX_COL = 127
+VISIUM_11MM_TISSUE_POSITION_MAX_ROW = 127
+VISIUM_11MM_TISSUE_POSITION_MAX_COL = 223
 SPATIAL_HIRES_IMAGE_MAX_DIMENSION_SIZE = 2000
 SPATIAL_HIRES_IMAGE_MAX_DIMENSION_SIZE_VISIUM_11MM = 4000
 
@@ -57,6 +61,7 @@ def __init__(self, ignore_labels=False):
         self._visium_and_is_single_true_matrix_size = None
         self._hires_max_dimension_size = None
         self._visium_error_suffix = None
+        self._visium_tissue_position_max = None
 
         # Values will be instances of gencode.GeneChecker,
         # keys will be one of gencode.SupportedOrganisms
@@ -122,6 +127,24 @@ def hires_max_dimension_size(self) -> Optional[int]:
                 self._hires_max_dimension_size = SPATIAL_HIRES_IMAGE_MAX_DIMENSION_SIZE
         return self._hires_max_dimension_size
 
+    @property
+    def tissue_position_maxes(self) -> Tuple[int, int]:
+        if self._visium_tissue_position_max is None and self._is_visium_and_is_single_true:
+            # visium 11 has different requirements than other visium
+            if (
+                self.adata.obs["assay_ontology_term_id"]
+                .apply(lambda t: is_ontological_descendant_of(ONTOLOGY_PARSER, t, ASSAY_VISIUM_11M, True))
+                .astype(bool)
+                .any()
+            ):
+                self._visium_tissue_position_max = (
+                    VISIUM_11MM_TISSUE_POSITION_MAX_ROW,
+                    VISIUM_11MM_TISSUE_POSITION_MAX_COL,
+                )
+            else:
+                self._visium_tissue_position_max = (VISIUM_TISSUE_POSITION_MAX_ROW, VISIUM_TISSUE_POSITION_MAX_COL)
+        return self._visium_tissue_position_max
+
     def _is_single(self) -> bool | None:
         """
         Determine value of uns.spatial.is_single. None if non-spatial.
@@ -1732,8 +1755,8 @@ def _validate_spatial_tissue_positions(self):
 
         :rtype none
         """
-        self._validate_spatial_tissue_position("array_col", 0, 127)
-        self._validate_spatial_tissue_position("array_row", 0, 77)
+        self._validate_spatial_tissue_position("array_col", 0, self.tissue_position_maxes[1])
+        self._validate_spatial_tissue_position("array_row", 0, self.tissue_position_maxes[0])
         self._validate_spatial_tissue_position("in_tissue", 0, 1)
 
     def _check_spatial_uns(self):

cellxgene_schema_cli/tests/test_validate.py

@@ -1,5 +1,6 @@
 import hashlib
 import os
+import re
 import tempfile
 from typing import Union
 from unittest import mock
@@ -1011,21 +1012,32 @@ def test__validate_tissue_position_required(self, tissue_position_name):
         validator.adata = adata_visium.copy()
         validator.adata.obs.pop(tissue_position_name)
 
+        # check visium
+        validator.adata.obs["assay_ontology_term_id"] = "EFO:0010961"
         validator._check_spatial_obs()
         assert validator.errors
         assert (
             f"obs['{tissue_position_name}'] {ERROR_SUFFIX_VISIUM_AND_IS_SINGLE_TRUE_REQUIRED}." in validator.errors[0]
         )
+        validator.reset()
+
+        # check visium descendant
+        validator.adata.obs["assay_ontology_term_id"] = "EFO:0022860"
+        validator._check_spatial_obs()
+        assert validator.errors
+        assert (
+            f"obs['{tissue_position_name}'] {ERROR_SUFFIX_VISIUM_AND_IS_SINGLE_TRUE_REQUIRED}." in validator.errors[0]
+        )
+        validator.reset()
 
-    @pytest.mark.parametrize("assay_ontology_term_id", ["EFO:0010961", "EFO:0030062"])
+    @pytest.mark.parametrize("assay_ontology_term_id", ["EFO:0010961", "EFO:0030062", "EFO:0022860"])
     def test__validate_tissue_position_not_required(self, assay_ontology_term_id):
         validator: Validator = Validator()
         validator._set_schema_def()
         validator.adata = adata_slide_seqv2.copy()
         validator.adata.obs["assay_ontology_term_id"] = assay_ontology_term_id
-        validator.adata.uns["spatial"]["is_single"] = False
+        validator.adata.uns["spatial"]["is_single"] = False  # setting to false removes the requirement
         validator.adata.obs["is_primary_data"] = False
-
         validator._check_spatial_obs()
         assert not validator.errors
 
@@ -1041,43 +1053,52 @@ def test__validate_tissue_position_int_error(self, tissue_position_name):
         assert validator.errors
         assert f"obs['{tissue_position_name}'] must be of int type" in validator.errors[0]
 
-    @pytest.mark.parametrize(
-        "tissue_position_name, min, error_message_token",
-        [
-            ("array_col", 0, "between 0 and 127"),
-            ("array_row", 0, "between 0 and 77"),
-            ("in_tissue", 0, "0 or 1"),
-        ],
-    )
-    def test__validate_tissue_position_int_min_error(self, tissue_position_name, min, error_message_token):
+    @pytest.mark.parametrize("assay_ontology_term_id", ["EFO:0010961", "EFO:0022860", "EFO:0022859"])
+    @pytest.mark.parametrize("tissue_position_name, min", [("array_col", 0), ("array_row", 0), ("in_tissue", 0)])
+    def test__validate_tissue_position_int_min_error(self, assay_ontology_term_id, tissue_position_name, min):
         validator: Validator = Validator()
         validator._set_schema_def()
         validator.adata = adata_visium.copy()
+        validator.adata.obs["assay_ontology_term_id"] = assay_ontology_term_id
         validator.adata.obs[tissue_position_name] = min - 1
 
         # Confirm tissue_position is identified as invalid.
         validator._check_spatial_obs()
-        assert validator.errors
-        assert f"obs['{tissue_position_name}'] must be {error_message_token}" in validator.errors[0]
+        assert (
+            re.match(f"^obs\['{tissue_position_name}'\] must be (between )?{min} (and|or) [0-9]+", validator.errors[0])
+            is not None
+        )
 
     @pytest.mark.parametrize(
-        "tissue_position_name, max, error_message_token",
+        "assay_ontology_term_id, tissue_position_name, tissue_position_max",
         [
-            ("array_col", 127, "between 0 and 127"),
-            ("array_row", 77, "between 0 and 77"),
-            ("in_tissue", 1, "0 or 1"),
+            ("EFO:0010961", "array_col", 127),
+            ("EFO:0010961", "array_row", 77),
+            ("EFO:0022860", "array_col", 223),
+            ("EFO:0022860", "array_row", 127),
+            ("EFO:0022859", "array_col", 127),
+            ("EFO:0022859", "array_row", 77),
+            ("EFO:0022859", "in_tissue", 1),
         ],
     )
-    def test__validate_tissue_position_int_max_error(self, tissue_position_name, max, error_message_token):
+    def test__validate_tissue_position_int_max_error(
+        self, assay_ontology_term_id, tissue_position_name, tissue_position_max
+    ):
         validator: Validator = Validator()
         validator._set_schema_def()
         validator.adata = adata_visium.copy()
-        validator.adata.obs[tissue_position_name] = max + 1
+        validator.adata.obs["assay_ontology_term_id"] = assay_ontology_term_id
+        validator.adata.obs[tissue_position_name] = tissue_position_max + 1
 
         # Confirm tissue_position is identified as invalid.
         validator._check_spatial_obs()
-        assert validator.errors
-        assert f"obs['{tissue_position_name}'] must be {error_message_token}" in validator.errors[0]
+        assert (
+            re.match(
+                f"^obs\['{tissue_position_name}'\] must be (between )?[0-9]+ (and|or) {tissue_position_max}",
+                validator.errors[0],
+            )
+            is not None
+        )
 
     @pytest.mark.parametrize(
         "cell_type_ontology_term_id, in_tissue, assay_ontology_term_id",