fix: load SparseDatasets into memory (#898)

cellxgene_schema_cli/cellxgene_schema/validate.py

@@ -11,6 +11,7 @@
 import numpy as np
 import pandas as pd
 import scipy
+from anndata._core.sparse_dataset import SparseDataset
 from cellxgene_ontology_guide.ontology_parser import OntologyParser
 from pandas.core.computation.ops import UndefinedVariableError
 from scipy import sparse
@@ -1222,7 +1223,9 @@ def _validate_raw_data(self, x: Union[np.ndarray, sparse.spmatrix], is_sparse_ma
             self._raw_layer_exists = False
             self.errors.append("All non-zero values in raw matrix must be positive integers of type numpy.float32.")
 
-    def _validate_raw_data_with_in_tissue_0(self, x: Union[np.ndarray, sparse.spmatrix], is_sparse_matrix: bool):
+    def _validate_raw_data_with_in_tissue_0(
+        self, x: Union[np.ndarray, sparse.spmatrix, SparseDataset], is_sparse_matrix: bool
+    ):
         """
         Special case validation checks for Visium data with is_single = True and in_tissue column in obs where in_tissue
         has at least one value 0. Static matrix size of 4992 rows, so chunking is not required.
@@ -1232,6 +1235,8 @@ def _validate_raw_data_with_in_tissue_0(self, x: Union[np.ndarray, sparse.spmatr
         """
         has_tissue_0_non_zero_row = False
         has_tissue_1_zero_row = False
+        if isinstance(x, SparseDataset):
+            x = x.to_memory()
         if is_sparse_matrix:
             nonzero_row_indices, _ = x.nonzero()
         else:  # must be dense matrix

cellxgene_schema_cli/tests/test_validate.py

@@ -325,6 +325,17 @@ def test__validate_spatial_visium_ok(self):
         validator.validate_adata()
         assert not validator.errors
 
+    def test__validate_from_file(self):
+        """Testing compatibility with SparseDatset types in Anndata"""
+        validator: Validator = Validator()
+        validator._set_schema_def()
+        with tempfile.TemporaryDirectory() as temp_dir:
+            file_path = os.path.join(temp_dir, "slide_seqv2.h5ad")
+            adata_slide_seqv2.write_h5ad(file_path)
+            # Confirm spatial is valid.
+            validator.validate_adata(file_path)
+        assert not validator.errors
+
     def test__validate_spatial_visium_dense_matrix_ok(self):
         validator: Validator = Validator()
         validator._set_schema_def()