Fix Seurat n_top_genes default (#2782)

Author: flying-sheep

docs/release-notes/1.9.7.md

@@ -7,3 +7,4 @@
 - Fix {func}`scanpy.pl.violin` usage of `seaborn.catplot` {pr}`2739` {smaller}`E Roellin`
 - Fix {func}`scanpy.pp.highly_variable_genes` to handle the combinations of `inplace` and `subset` consistently {pr}`2757` {smaller}`E Roellin`
 - Replace usage of various deprecated functionality from {mod}`anndata` and {mod}`pandas` {pr}`2678` {pr}`2779` {smaller}`P Angerer`
+- Allow to use default `n_top_genes` when using {func}`scanpy.pp.highly_variable_genes` flavor `'seurat_v3'` {pr}`2782` {smaller}`P Angerer`

scanpy/preprocessing/_highly_variable_genes.py

@@ -1,7 +1,8 @@
 from __future__ import annotations
 
 import warnings
-from typing import Literal
+from inspect import signature
+from typing import Literal, cast
 
 import numpy as np
 import pandas as pd
@@ -328,7 +329,7 @@ def highly_variable_genes(
     max_disp: float | None = np.inf,
     min_mean: float | None = 0.0125,
     max_mean: float | None = 3,
-    span: float | None = 0.3,
+    span: float = 0.3,
     n_bins: int = 20,
     flavor: Literal["seurat", "cell_ranger", "seurat_v3"] = "seurat",
     subset: bool = False,
@@ -455,6 +456,9 @@ def highly_variable_genes(
         )
 
     if flavor == "seurat_v3":
+        if n_top_genes is None:
+            sig = signature(_highly_variable_genes_seurat_v3)
+            n_top_genes = cast(int, sig.parameters["n_top_genes"].default)
         return _highly_variable_genes_seurat_v3(
             adata,
             layer=layer,

scanpy/tests/test_highly_variable_genes.py

@@ -387,12 +387,16 @@ def test_higly_variable_genes_compare_to_seurat_v3():
     seu = pd.Index(seurat_hvg_info_batch["x"].values)
     assert len(seu.intersection(df.index)) / 4000 > 0.95
 
+
+@needs.skmisc
+def test_higly_variable_genes_seurat_v3_warning():
+    pbmc = pbmc3k()[:200].copy()
     sc.pp.log1p(pbmc)
     with pytest.warns(
         UserWarning,
         match="`flavor='seurat_v3'` expects raw count data, but non-integers were found.",
     ):
-        sc.pp.highly_variable_genes(pbmc, n_top_genes=1000, flavor="seurat_v3")
+        sc.pp.highly_variable_genes(pbmc, flavor="seurat_v3")
 
 
 def test_filter_genes_dispersion_compare_to_seurat():