Prep 1.7.2 release (#1785)

* Set release date
* Remove unused rubrics from release notes
* enables highly_variable_genes_seurat_v3 to accept pseudocounts (#1679) 
* Add hvg change to release notes

Co-authored-by: Isaac Virshup <[email protected]>
Co-authored-by: giovp <[email protected]>

docs/release-notes/1.7.2.rst

@@ -1,17 +1,12 @@
-1.7.2 :small:`the future`
+1.7.2 :small:`2021-04-07`
 ~~~~~~~~~~~~~~~~~~~~~~~~~
 
-.. rubric:: Performance enhancements
-
 .. rubric:: Bug fixes
 
 - :func:`scanpy.logging.print_versions` now works when `python<3.8` :pr:`1691` :smaller:`I Virshup`
 - :func:`scanpy.pp.regress_out` now uses `joblib` as the parallel backend, and should stop oversubscribing threads :pr:`1694` :smaller:`I Virshup`
 - :func:`scanpy.pp.highly_variable_genes` with `flavor="seurat_v3"` now returns correct gene means and -variances when used with `batch_key` :pr:`1732` :smaller:`J Lause`
-
-.. rubric:: Deprecations
-
-.. rubric:: Documentation
+- :func:`scanpy.pp.highly_variable_genes` now throws a warning instead of an error when non-integer values are passed for method `"seurat_v3"`. The check can be skipped by passing `check_values=False`. :pr:`1679` :smaller:`G Palla`
 
 .. rubric:: Ecosystem
 

scanpy/preprocessing/_highly_variable_genes.py

@@ -1,6 +1,5 @@
 import warnings
 from typing import Optional
-
 import numpy as np
 import pandas as pd
 import scipy.sparse as sp_sparse
@@ -21,7 +20,8 @@ def _highly_variable_genes_seurat_v3(
     layer: Optional[str] = None,
     n_top_genes: int = 2000,
     batch_key: Optional[str] = None,
-    span: Optional[float] = 0.3,
+    check_values: bool = True,
+    span: float = 0.3,
     subset: bool = False,
     inplace: bool = True,
 ) -> Optional[pd.DataFrame]:
@@ -58,10 +58,10 @@ def _highly_variable_genes_seurat_v3(
     df = pd.DataFrame(index=adata.var_names)
     X = adata.layers[layer] if layer is not None else adata.X
 
-    if check_nonnegative_integers(X) is False:
-        raise ValueError(
-            "`pp.highly_variable_genes` with `flavor='seurat_v3'` expects "
-            "raw count data."
+    if check_values and not check_nonnegative_integers(X):
+        warnings.warn(
+            "`flavor='seurat_v3'` expects raw count data, but non-integers were found.",
+            UserWarning,
         )
 
     df['means'], df['variances'] = _get_mean_var(X)
@@ -300,6 +300,7 @@ def highly_variable_genes(
     subset: bool = False,
     inplace: bool = True,
     batch_key: Optional[str] = None,
+    check_values: bool = True,
 ) -> Optional[pd.DataFrame]:
     """\
     Annotate highly variable genes [Satija15]_ [Zheng17]_ [Stuart19]_.
@@ -366,6 +367,9 @@ def highly_variable_genes(
         by how many batches they are a HVG. For dispersion-based flavors ties are broken
         by normalized dispersion. If `flavor = 'seurat_v3'`, ties are broken by the median
         (across batches) rank based on within-batch normalized variance.
+    check_values
+        Check if counts in selected layer are integers. A Warning is returned if set to True.
+        Only used if `flavor='seurat_v3'`.
 
     Returns
     -------
@@ -417,6 +421,7 @@ def highly_variable_genes(
             layer=layer,
             n_top_genes=n_top_genes,
             batch_key=batch_key,
+            check_values=check_values,
             span=span,
             subset=subset,
             inplace=inplace,

scanpy/tests/test_highly_variable_genes.py

@@ -1,3 +1,4 @@
+import pytest
 import pandas as pd
 import numpy as np
 import scanpy as sc
@@ -149,6 +150,13 @@ 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
 
+    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')
+
 
 def test_filter_genes_dispersion_compare_to_seurat():
     seurat_hvg_info = pd.read_csv(FILE, sep=' ')