Add check for number of normalized dispersions (scverse#2231)

* Add check for number of normalized dispersions In sc.pp.highly_variable_genes() when flavor='cell_ranger' and n_top_genes is set check that enough normalized dispersions have been calculated and if not raise a warning and set n_top_genes to the number of calculated dispersions. Fixes scverse#2230 * Use .size instead of len() * Add test for n_top_genes warning * Add release note * Remove blank line Co-authored-by: Isaac Virshup <[email protected]>
jacob-evarts · Aug 12, 2022 · 1844b91 · 1844b91
1 parent 4623bb7
commit 1844b91
Show file tree

Hide file tree

Showing 3 changed files with 20 additions and 1 deletion.
diff --git a/docs/release-notes/1.9.2.md b/docs/release-notes/1.9.2.md
@@ -7,7 +7,7 @@
 ```{rubric} Bug fixes
 ```
 - {func}`~scanpy.pp.highly_variable_genes` `layer` argument now works in tandem with `batches` {pr}`2302` {smaller}`D Schaumont`
-
+- {func}`~scanpy.pp.highly_variable_genes` with `flavor='cell_ranger'` now handles the case in {issue}`2230` where the number of calculated dispersions is less than `n_top_genes` {pr}`2231` {smaller}`L Zappia`
 
 ```{rubric} Performance
 ```
diff --git a/scanpy/preprocessing/_highly_variable_genes.py b/scanpy/preprocessing/_highly_variable_genes.py
@@ -265,6 +265,12 @@ def _highly_variable_genes_single_batch(
         if n_top_genes > adata.n_vars:
             logg.info('`n_top_genes` > `adata.n_var`, returning all genes.')
             n_top_genes = adata.n_vars
+        if n_top_genes > dispersion_norm.size:
+            warnings.warn(
+                '`n_top_genes` > number of normalized dispersions, returning all genes with normalized dispersions.',
+                UserWarning,
+            )
+            n_top_genes = dispersion_norm.size
         disp_cut_off = dispersion_norm[n_top_genes - 1]
         gene_subset = np.nan_to_num(df['dispersions_norm'].values) >= disp_cut_off
         logg.debug(

diff --git a/scanpy/tests/test_highly_variable_genes.py b/scanpy/tests/test_highly_variable_genes.py
@@ -506,3 +506,16 @@ def test_seurat_v3_mean_var_output_with_batchkey():
     )
     np.testing.assert_allclose(true_mean, result_df['means'], rtol=2e-05, atol=2e-05)
     np.testing.assert_allclose(true_var, result_df['variances'], rtol=2e-05, atol=2e-05)
+
+
+def test_cellranger_n_top_genes_warning():
+    X = np.random.poisson(2, (100, 30))
+    adata = sc.AnnData(X, dtype=X.dtype)
+    sc.pp.normalize_total(adata)
+    sc.pp.log1p(adata)
+
+    with pytest.warns(
+        UserWarning,
+        match="`n_top_genes` > number of normalized dispersions, returning all genes with normalized dispersions.",
+    ):
+        sc.pp.highly_variable_genes(adata, n_top_genes=1000, flavor="cell_ranger")