Add Harmony to scanpy

docs/api/preprocessing.md

@@ -47,18 +47,24 @@ For visual quality control, see {func}`~scanpy.pl.highest_expr_genes` and
    pp.recipe_seurat
 ```
 
-## Batch effect correction
+(pp-data-integration)=
 
-Also see {ref}`data-integration`. Note that a simple batch correction method is available via {func}`pp.regress_out`. Checkout {mod}`scanpy.external` for more.
+## Data integration
+
+Batch effect correction and other data integration.
+Note that a simple batch correction method is available via {func}`pp.regress_out`.
 
 ```{eval-rst}
 .. autosummary::
    :nosignatures:
    :toctree: generated/
 
    pp.combat
+   pp.harmony_integrate
 ```
 
+Also see {ref}`data integration tools <data-integration>` and external {ref}`external data integration <external-data-integration>`.
+
 ## Doublet detection
 
 ```{eval-rst}

docs/external/preprocessing.md

@@ -5,6 +5,11 @@
 .. currentmodule:: scanpy.external
 ```
 
+Previously found here, but now part of scanpy’s main API:
+- {func}`scanpy.pp.harmony_integrate`
+- {func}`scanpy.pp.scrublet`
+- {func}`scanpy.pp.scrublet_simulate_doublets`
+
 (external-data-integration)=
 
 ## Data integration
@@ -14,10 +19,8 @@
    :toctree: ../generated/
 
    pp.bbknn
-   pp.harmony_integrate
    pp.mnn_correct
    pp.scanorama_integrate
-
 ```
 
 ## Sample demultiplexing
@@ -39,5 +42,4 @@ Note that the fundamental limitations of imputation are still under [debate](htt
 
    pp.dca
    pp.magic
-
 ```

docs/release-notes/1.10.0.md

@@ -25,7 +25,7 @@ Some highlights:
 * {func}`scanpy.datasets.blobs` now accepts a `random_state` argument {pr}`2683` {smaller}`E Roellin`
 * {func}`scanpy.pp.pca` and {func}`scanpy.pp.regress_out` now accept a layer argument {pr}`2588` {smaller}`S Dicks`
 * {func}`scanpy.pp.subsample` with `copy=True` can now be called in backed mode {pr}`2624` {smaller}`E Roellin`
-* {func}`scanpy.external.pp.harmony_integrate` now runs with 64 bit floats improving reproducibility {pr}`2655` {smaller}`S Dicks`
+* {func}`scanpy.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.tl.leiden` and {func}`scanpy.tl.louvain` now store clustering parameters in the key provided by the `key_added` parameter instead of always writing to (or overwriting) a default key {pr}`2864` {smaller}`J Fan`

docs/release-notes/1.11.0.md

@@ -30,7 +30,7 @@ Release candidates:
 
 #### Documentation
 
-- {guilabel}`rc1` Improve {func}`~scanpy.external.pp.harmony_integrate` docs {smaller}`D Kühl` ({pr}`3362`)
+- {guilabel}`rc1` Improve {func}`~scanpy.pp.harmony_integrate` docs {smaller}`D Kühl` ({pr}`3362`)
 - {guilabel}`rc1` Raise {exc}`FutureWarning` when calling deprecated {mod}`scanpy.pp` functions {smaller}`P Angerer` ({pr}`3380`)
 - {guilabel}`rc1` {smaller}`P Angerer` ({pr}`3407`)
 

pyproject.toml

@@ -87,7 +87,6 @@ bbknn = [ "bbknn" ]
 dask = [ "anndata[dask]", "dask[array]>=2024.5.1" ]
 # PCA acceleration
 dask-ml = [ "dask-ml", "scanpy[dask]" ]
-harmony = [ "harmonypy" ]
 leiden = [ "igraph>=0.10.8", "leidenalg>=0.10.1" ]
 louvain = [ "igraph", "louvain>=0.8.2", "setuptools" ]
 magic = [ "magic-impute>=2.0.4" ]
@@ -136,6 +135,7 @@ doc = [
 ]
 test-min = [
     "dependency-groups",    # for CI scripts doctests
+    "pooch",
     "pytest",
     "pytest-cov",           # only for use from VS Code
     "pytest-mock",

src/scanpy/external/pp/__init__.py

@@ -3,26 +3,39 @@
 from __future__ import annotations
 
 from ..._compat import deprecated
-from ...preprocessing import _scrublet
 from ._bbknn import bbknn
 from ._dca import dca
-from ._harmony_integrate import harmony_integrate
 from ._hashsolo import hashsolo
 from ._magic import magic
 from ._mnn_correct import mnn_correct
 from ._scanorama_integrate import scanorama_integrate
 
-scrublet = deprecated("Import from sc.pp instead")(_scrublet.scrublet)
-scrublet_simulate_doublets = deprecated("Import from sc.pp instead")(
-    _scrublet.scrublet_simulate_doublets
-)
-
 __all__ = [
     "bbknn",
     "dca",
-    "harmony_integrate",
     "hashsolo",
     "magic",
     "mnn_correct",
     "scanorama_integrate",
 ]
+
+
+@deprecated("Import from sc.pp instead")
+def harmony_integrate(*args, **kwargs):
+    from ...preprocessing import harmony_integrate
+
+    return harmony_integrate(*args, **kwargs)
+
+
+@deprecated("Import from sc.pp instead")
+def scrublet(*args, **kwargs):
+    from ...preprocessing import scrublet
+
+    return scrublet(*args, **kwargs)
+
+
+@deprecated("Import from sc.pp instead")
+def scrublet_simulate_doublets(*args, **kwargs):
+    from ...preprocessing import scrublet_simulate_doublets
+
+    return scrublet_simulate_doublets(*args, **kwargs)

src/scanpy/preprocessing/__init__.py

@@ -6,6 +6,7 @@
 from ._combat import combat
 from ._deprecated.highly_variable_genes import filter_genes_dispersion
 from ._deprecated.sampling import subsample
+from ._harmony_integrate import harmony_integrate
 from ._highly_variable_genes import highly_variable_genes
 from ._normalization import normalize_total
 from ._pca import pca
@@ -31,6 +32,7 @@
     "filter_cells",
     "filter_genes",
     "filter_genes_dispersion",
+    "harmony_integrate",
     "highly_variable_genes",
     "log1p",
     "neighbors",