Backport PR #2546: Fix getting log1p base (#2549)

Co-authored-by: Simon P Shen <[email protected]>

Author: flying-sheep

scanpy/preprocessing/_highly_variable_genes.py

@@ -194,7 +194,7 @@ def _highly_variable_genes_single_batch(
     """
     X = adata.layers[layer] if layer is not None else adata.X
     if flavor == 'seurat':
-        if 'log1p' in adata.uns_keys() and adata.uns['log1p']['base'] is not None:
+        if 'log1p' in adata.uns_keys() and adata.uns['log1p'].get('base') is not None:
             X *= np.log(adata.uns['log1p']['base'])
         X = np.expm1(X)
 

scanpy/tests/test_rank_genes_groups.py

@@ -248,6 +248,21 @@ def test_emptycat():
         rank_genes_groups(pbmc, groupby='louvain')
 
 
+def test_log1p_save_restore(tmp_path):
+    """tests the sequence log1p→save→load→rank_genes_groups"""
+    from anndata import read
+
+    pbmc = pbmc68k_reduced()
+    sc.pp.log1p(pbmc)
+
+    path = tmp_path / 'test.h5ad'
+    pbmc.write(path)
+
+    pbmc = read(path)
+
+    sc.tl.rank_genes_groups(pbmc, groupby='bulk_labels', use_raw=True)
+
+
 def test_wilcoxon_symmetry():
     pbmc = pbmc68k_reduced()
 

scanpy/tools/_rank_genes_groups.py

@@ -88,8 +88,7 @@ def __init__(
         layer=None,
         comp_pts=False,
     ):
-
-        if 'log1p' in adata.uns_keys() and adata.uns['log1p']['base'] is not None:
+        if 'log1p' in adata.uns_keys() and adata.uns['log1p'].get('base') is not None:
             self.expm1_func = lambda x: np.expm1(x * np.log(adata.uns['log1p']['base']))
         else:
             self.expm1_func = np.expm1
@@ -362,7 +361,6 @@ def compute_statistics(
         tie_correct=False,
         **kwds,
     ):
-
         if method in {'t-test', 't-test_overestim_var'}:
             generate_test_results = self.t_test(method)
         elif method == 'wilcoxon':
@@ -753,7 +751,7 @@ def filter_rank_genes_groups(
             index=gene_names.index,
         )
 
-        if 'log1p' in adata.uns_keys() and adata.uns['log1p']['base'] is not None:
+        if 'log1p' in adata.uns_keys() and adata.uns['log1p'].get('base') is not None:
             expm1_func = lambda x: np.expm1(x * np.log(adata.uns['log1p']['base']))
         else:
             expm1_func = np.expm1