Add feature_type column to var (#1310)

chanzuckerberg · Nov 14, 2024 · 1b73528 · 1b73528
1 parent f8b1862
commit 1b73528
Show file tree

Hide file tree

Showing 3 changed files with 5 additions and 2 deletions.
diff --git a/tools/cellxgene_census_builder/src/cellxgene_census_builder/build_soma/experiment_builder.py b/tools/cellxgene_census_builder/src/cellxgene_census_builder/build_soma/experiment_builder.py
@@ -297,7 +297,7 @@ def get_obs_and_var(
             var_df = (
                 adata.var.copy()
                 .rename_axis("feature_id")
-                .reset_index()[["feature_id", "feature_name", "feature_length"]]
+                .reset_index()[["feature_id", "feature_name", "feature_length", "feature_type"]]
             )
 
             return obs_df, var_df

diff --git a/tools/cellxgene_census_builder/src/cellxgene_census_builder/build_soma/globals.py b/tools/cellxgene_census_builder/src/cellxgene_census_builder/build_soma/globals.py
@@ -186,19 +186,21 @@
     "feature_length",
     "feature_reference",
     "feature_biotype",
+    "feature_type",
 )
 CENSUS_VAR_TABLE_SPEC = TableSpec.create(
     [
         ("soma_joinid", pa.int64()),
         ("feature_id", pa.large_string()),
         ("feature_name", pa.large_string()),
+        ("feature_type", pa.large_string()),
         ("feature_length", pa.int64()),
         ("nnz", pa.int64()),
         ("n_measured_obs", pa.int64()),
     ],
     use_arrow_dictionary=USE_ARROW_DICTIONARY,
 )
-_StringLabelVar = ["feature_id", "feature_name"]
+_StringLabelVar = ["feature_id", "feature_name", "feature_type"]
 _NumericVar = ["nnz", "n_measured_obs", "feature_length"]
 CENSUS_VAR_PLATFORM_CONFIG = {
     "tiledb": {

diff --git a/tools/cellxgene_census_builder/tests/conftest.py b/tools/cellxgene_census_builder/tests/conftest.py
@@ -99,6 +99,7 @@ def get_anndata(
             "feature_biotype": "gene",
             "feature_is_filtered": False,
             "feature_name": "ERCC-00002 (spike-in control)",
+            "feature_type": "synthetic",
             "feature_reference": organism.organism_ontology_term_id,
             "feature_length": 1000,
         },