From c6a7ae18e041bb23983dc0130dc2188571b447b0 Mon Sep 17 00:00:00 2001
From: Severin Dicks <37635888+Intron7@users.noreply.github.com>
Date: Thu, 14 Mar 2024 13:02:26 +0100
Subject: [PATCH] Scale clips low (#2913)

Co-authored-by: Philipp A <flying-sheep@web.de>
---
 docs/release-notes/1.10.0.md    | 1 +
 scanpy/preprocessing/_simple.py | 5 ++++-
 scanpy/tests/test_scaling.py    | 9 +++++++++
 3 files changed, 14 insertions(+), 1 deletion(-)

diff --git a/docs/release-notes/1.10.0.md b/docs/release-notes/1.10.0.md
index afe72f87bf..9373c27370 100644
--- a/docs/release-notes/1.10.0.md
+++ b/docs/release-notes/1.10.0.md
@@ -25,6 +25,7 @@
 * {func}`scanpy.external.pp.harmony_integrate` now runs with 64 bit floats improving reproducibility {pr}`2655` {smaller}`S Dicks`
 * {func}`scanpy.tl.rank_genes_groups` no longer warns that it's default was changed from t-test_overestim_var to t-test {pr}`2798` {smaller}`L Heumos`
 * `scanpy.pp.calculate_qc_metrics` now allows `qc_vars` to be passed as a string {pr}`2859` {smaller}`N Teyssier`
+* {func}`scanpy.pp.scale` now clips `np.ndarray` also at `- max_value` for zero-centering {pr}`2913` {smaller}`S Dicks`
 
 ```{rubric} Docs
 ```
diff --git a/scanpy/preprocessing/_simple.py b/scanpy/preprocessing/_simple.py
index 7fba1a71f8..8b21588669 100644
--- a/scanpy/preprocessing/_simple.py
+++ b/scanpy/preprocessing/_simple.py
@@ -871,7 +871,10 @@ def scale_array(
     # do the clipping
     if max_value is not None:
         logg.debug(f"... clipping at max_value {max_value}")
-        X[X > max_value] = max_value
+        if zero_center:
+            X = np.clip(X, a_min=-max_value, a_max=max_value)
+        else:
+            X[X > max_value] = max_value
     if return_mean_std:
         return X, mean, std
     else:
diff --git a/scanpy/tests/test_scaling.py b/scanpy/tests/test_scaling.py
index d6b004c1ff..ba425e4408 100644
--- a/scanpy/tests/test_scaling.py
+++ b/scanpy/tests/test_scaling.py
@@ -104,3 +104,12 @@ def test_mask_string():
     sc.pp.scale(adata, mask_obs="some cells")
     assert np.array_equal(adata.X, X_centered_for_mask)
     assert "mean of some cells" in adata.var.keys()
+
+
+@pytest.mark.parametrize("zero_center", [True, False])
+def test_clip(zero_center):
+    adata = sc.datasets.pbmc3k()
+    sc.pp.scale(adata, max_value=1, zero_center=zero_center)
+    if zero_center:
+        assert adata.X.min() >= -1
+    assert adata.X.max() <= 1