pertpy 0.11.5__py3-none-any.whl → 1.0.0__py3-none-any.whl

pertpy/__init__.py

@@ -2,10 +2,11 @@
 
 __author__ = "Lukas Heumos"
 __email__ = "lukas.heumos@posteo.net"
-__version__ = "0.11.5"
+__version__ = "1.0.0"
 
 import warnings
 
+from anndata._core.aligned_df import ImplicitModificationWarning
 from matplotlib import MatplotlibDeprecationWarning
 from numba import NumbaDeprecationWarning
 
@@ -13,6 +14,8 @@ warnings.filterwarnings("ignore", category=NumbaDeprecationWarning)
 warnings.filterwarnings("ignore", category=MatplotlibDeprecationWarning)
 warnings.filterwarnings("ignore", category=SyntaxWarning)
 warnings.filterwarnings("ignore", category=UserWarning, module="scvi._settings")
+warnings.filterwarnings("ignore", message="Environment variable.*redefined by R")
+warnings.filterwarnings("ignore", message="Transforming to str index.", category=ImplicitModificationWarning)
 
 import mudata
 

pertpy/tools/_milo.py

@@ -2,6 +2,7 @@ from __future__ import annotations
 
 import random
 import re
+from importlib.util import find_spec
 from typing import TYPE_CHECKING, Literal
 
 import matplotlib.pyplot as plt
@@ -29,18 +30,6 @@ from sklearn.metrics.pairwise import euclidean_distances
 class Milo:
     """Python implementation of Milo."""
 
-    def __init__(self):
-        try:
-            from rpy2.robjects import conversion, numpy2ri, pandas2ri
-            from rpy2.robjects.packages import STAP, PackageNotInstalledError, importr
-        except ModuleNotFoundError:
-            raise ImportError("milo requires rpy2 to be installed.") from None
-
-        try:
-            importr("edgeR")
-        except ImportError as e:
-            raise ImportError("milo requires a valid R installation with edger installed:\n") from e
-
     def load(
         self,
         input: AnnData,
@@ -266,7 +255,7 @@ class Milo:
         subset_samples: list[str] | None = None,
         add_intercept: bool = True,
         feature_key: str | None = "rna",
-        solver: Literal["edger", "batchglm"] = "edger",
+        solver: Literal["edger", "pydeseq2"] = "edger",
     ):
         """Performs differential abundance testing on neighbourhoods using QLF test implementation as implemented in edgeR.
 
@@ -279,7 +268,9 @@ class Milo:
             subset_samples: subset of samples (obs in `milo_mdata['milo']`) to use for the test.
             add_intercept: whether to include an intercept in the model. If False, this is equivalent to adding + 0 in the design formula. When model_contrasts is specified, this is set to False by default.
             feature_key: If input data is MuData, specify key to cell-level AnnData object.
-            solver: The solver to fit the model to. One of "edger" (requires R, rpy2 and edgeR to be installed) or "batchglm"
+            solver: The solver to fit the model to.
+                The "edger" solver requires R, rpy2 and edgeR to be installed and is the closest to the R implementation.
+                The "pydeseq2" requires pydeseq2 to be installed. It is still very comparable to the "edger" solver but might be a bit slower.
 
         Returns:
             None, modifies `milo_mdata['milo']` in place, adding the results of the DA test to `.var`:
@@ -298,7 +289,6 @@ class Milo:
             >>> milo.make_nhoods(mdata["rna"])
             >>> mdata = milo.count_nhoods(mdata, sample_col="orig.ident")
             >>> milo.da_nhoods(mdata, design="~label")
-
         """
         try:
             sample_adata = mdata["milo"]
@@ -425,13 +415,65 @@ class Milo:
                 res = pd.DataFrame(res)
             # The columns of res looks like e.g. table.A, table.B, so remove the prefix
             res.columns = [col.replace("table.", "") for col in res.columns]
-        # Save outputs
+        elif solver == "pydeseq2":
+            if find_spec("pydeseq2") is None:
+                raise ImportError("pydeseq2 is required but not installed. Install with: pip install pydeseq2")
+
+            from pydeseq2.dds import DeseqDataSet
+            from pydeseq2.ds import DeseqStats
+
+            counts_filtered = count_mat[np.ix_(keep_nhoods, keep_smp)]
+            design_df_filtered = design_df.iloc[keep_smp].copy()
+
+            design_df_filtered = design_df_filtered.astype(
+                dict.fromkeys(design_df_filtered.select_dtypes(exclude=["number"]).columns, "category")
+            )
+
+            design_clean = design if design.startswith("~") else f"~{design}"
+
+            dds = DeseqDataSet(
+                counts=pd.DataFrame(counts_filtered.T, index=design_df_filtered.index),
+                metadata=design_df_filtered,
+                design=design_clean,
+                refit_cooks=True,
+            )
+
+            dds.deseq2()
+
+            if model_contrasts is not None and "-" in model_contrasts:
+                if "(" in model_contrasts or "+" in model_contrasts.split("-")[1]:
+                    raise ValueError(
+                        f"Complex contrasts like '{model_contrasts}' are not supported by pydeseq2. "
+                        "Use simple pairwise contrasts (e.g., 'GroupA-GroupB') or switch to solver='edger'."
+                    )
+
+                parts = model_contrasts.split("-")
+                factor_name = design_clean.replace("~", "").split("+")[-1].strip()
+                group1 = parts[0].replace(factor_name, "").strip()
+                group2 = parts[1].replace(factor_name, "").strip()
+                stat_res = DeseqStats(dds, contrast=[factor_name, group1, group2])
+            else:
+                factor_name = design_clean.replace("~", "").split("+")[-1].strip()
+                if not isinstance(design_df_filtered[factor_name], pd.CategoricalDtype):
+                    design_df_filtered[factor_name] = design_df_filtered[factor_name].astype("category")
+                categories = design_df_filtered[factor_name].cat.categories
+                stat_res = DeseqStats(dds, contrast=[factor_name, categories[-1], categories[0]])
+
+            stat_res.summary()
+            res = stat_res.results_df
+
+            res = res.rename(
+                columns={"baseMean": "logCPM", "log2FoldChange": "logFC", "pvalue": "PValue", "padj": "FDR"}
+            )
+
+            res = res[["logCPM", "logFC", "PValue", "FDR"]]
+
         res.index = sample_adata.var_names[keep_nhoods]  # type: ignore
         if any(col in sample_adata.var.columns for col in res.columns):
             sample_adata.var = sample_adata.var.drop(res.columns, axis=1)
         sample_adata.var = pd.concat([sample_adata.var, res], axis=1)
-        # Run Graph spatial FDR correction
-        self._graph_spatial_fdr(sample_adata, neighbors_key=adata.uns["nhood_neighbors_key"])
+
+        self._graph_spatial_fdr(sample_adata)
 
     def annotate_nhoods(
         self,
@@ -674,6 +716,17 @@ class Milo:
         self,
     ):
         """Set up rpy2 to run edgeR."""
+        try:
+            from rpy2.robjects import conversion, numpy2ri, pandas2ri
+            from rpy2.robjects.packages import STAP, PackageNotInstalledError, importr
+        except ModuleNotFoundError:
+            raise ImportError("milo requires rpy2 to be installed.") from None
+
+        try:
+            importr("edgeR")
+        except ImportError as e:
+            raise ImportError("milo requires a valid R installation with edger installed.") from e
+
         from rpy2.robjects.packages import importr
 
         edgeR = self._try_import_bioc_library("edgeR")
@@ -685,26 +738,27 @@ class Milo:
 
     def _try_import_bioc_library(
         self,
-        name: str,
+        r_package: str,
     ):
         """Import R packages.
 
         Args:
-            name (str): R packages name
+            r_package: R packages name
         """
         from rpy2.robjects.packages import PackageNotInstalledError, importr
 
         try:
-            _r_lib = importr(name)
+            _r_lib = importr(r_package)
             return _r_lib
         except PackageNotInstalledError:
-            logger.error(f"Install Bioconductor library `{name!r}` first as `BiocManager::install({name!r}).`")
+            logger.error(
+                f"Install Bioconductor library `{r_package!r}` first as `BiocManager::install({r_package!r}).`"
+            )
             raise
 
     def _graph_spatial_fdr(
         self,
         sample_adata: AnnData,
-        neighbors_key: str | None = None,
     ):
         """FDR correction weighted on inverse of connectivity of neighbourhoods.
 
@@ -712,7 +766,6 @@ class Milo:
 
         Args:
             sample_adata: Sample-level AnnData.
-            neighbors_key: The key in `adata.obsp` to use as KNN graph.
         """
         # use 1/connectivity as the weighting for the weighted BH adjustment from Cydar
         w = 1 / sample_adata.var["kth_distance"]

pertpy/tools/_perturbation_space/_perturbation_space.py

@@ -80,7 +80,7 @@ class PerturbationSpace:
         group_masks = (
             [(adata.obs[group_col] == sample) for sample in adata.obs[group_col].unique()]
             if group_col
-            else [[True] * adata.n_obs]
+            else [np.array([True] * adata.n_obs)]
         )
 
         if layer_key:

{pertpy-0.11.5.dist-info → pertpy-1.0.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pertpy
-Version: 0.11.5
+Version: 1.0.0
 Summary: Perturbation Analysis in the scverse ecosystem.
 Project-URL: Documentation, https://pertpy.readthedocs.io
 Project-URL: Source, https://github.com/scverse/pertpy
@@ -155,7 +155,13 @@ pip install 'pertpy[tcoda]'
 
 ### milo
 
-milo further requires edger, statmod, and rpy2 to be installed:
+milo requires either the "de" extra for the "pydeseq2" solver:
+
+```console
+pip install 'pertpy[de]'
+```
+
+or, edger, statmod, and rpy2 for the "edger" solver:
 
 ```R
 BiocManager::install("edgeR")

{pertpy-0.11.5.dist-info → pertpy-1.0.0.dist-info}/RECORD

@@ -1,4 +1,4 @@
-pertpy/__init__.py,sha256=KIxMlqyHlppcGM5Uc2HpTwCEtGFavXRPW50dM5dFB7U,716
+pertpy/__init__.py,sha256=cZHJ7PIOhtLkxJMlHbJ2rzei5xhLB4vg0c8AaIShfzc,972
 pertpy/_doc.py,sha256=j5TMNC-DA9yIMqIIUNpjpcVgWfRqyBBfvbRjnCM_OLs,427
 pertpy/_types.py,sha256=IcHCojCUqx8CapibNkcYf2TUqjBFP2ujeELvn_IBSBQ,154
 pertpy/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -21,7 +21,7 @@ pertpy/tools/_augur.py,sha256=tc1YKyc0BwzrEGgctsfyy7DsTNKxyvy7ZvWraTWCc1A,55262
 pertpy/tools/_cinemaot.py,sha256=54-rS0AEj31dMe7iU4kEmLoAunq3jNuhsBE3IEp9hrI,38071
 pertpy/tools/_dialogue.py,sha256=mygIZm5i_bnEE37TTQtr1efl_KJq-ejzeL3V1Bmr7Pg,52354
 pertpy/tools/_enrichment.py,sha256=55mwotLH9DXQOhl85MCkxXu-MX0RysLyrPheJysAnF0,21369
-pertpy/tools/_milo.py,sha256=zIYG0aP8B39_eiNgpZONhTKmDvcRwCzOLo5FMOTMUms,45530
+pertpy/tools/_milo.py,sha256=9yoB9gkBNujqYDTKOlH2v3wiWhs5PdCuB8RgZ3xVI0Y,48049
 pertpy/tools/_mixscape.py,sha256=HfrpBeRlxHXaOpZkF2FmX7dg35kUB1rL0_-n2aSi2_0,57905
 pertpy/tools/decoupler_LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
 pertpy/tools/transferlearning_MMD_LICENSE,sha256=MUvDA-o_j9htRpI8fStVdCRuyLdPkQUuIH0a_EIc57w,1069
@@ -45,14 +45,14 @@ pertpy/tools/_perturbation_space/_clustering.py,sha256=pNx_SpPkZfCbgF7vzHWqAaiiH
 pertpy/tools/_perturbation_space/_comparison.py,sha256=-NzCPRT-IlhJ9hOz7NQLSk0riIzr2C0yZvX6zm3kon4,4291
 pertpy/tools/_perturbation_space/_discriminator_classifiers.py,sha256=a53-YmUwDHQBCT7ZWe_RH7PZsGXvoSHmJaQyL0CBJng,23383
 pertpy/tools/_perturbation_space/_metrics.py,sha256=y8-baP8WRdB1iDgvP3uuQxSCDxA2lcxvEHHM2C_vWHY,3248
-pertpy/tools/_perturbation_space/_perturbation_space.py,sha256=8RxVUkVEPZj5YZ-C-NP5zO4aYYVD04PzlsYuaIG-wjY,19447
+pertpy/tools/_perturbation_space/_perturbation_space.py,sha256=Vyh15wWw9dcu2YUWhziQd2mA9-4IY8EC5dzkBT9HaIo,19457
 pertpy/tools/_perturbation_space/_simple.py,sha256=AJlHRaEP-vViBeMDvvMtUnXMuIKqZVc7wggnjsHMfMw,12721
 pertpy/tools/_scgen/__init__.py,sha256=uERFlFyF88TH0uLiwmsUGEfHfLVCiZMFuk8gO5f7164,45
 pertpy/tools/_scgen/_base_components.py,sha256=Qq8myRUm43q9XBrZ9gBggfa2cSV2wbz_KYoLgH7iF1A,3009
 pertpy/tools/_scgen/_scgen.py,sha256=AQNGsDe-9HEqli3oq7UBDg68ofLCoXm-R_jnLFQ-rlc,30856
 pertpy/tools/_scgen/_scgenvae.py,sha256=bPk4v7EdJc7ROdLuDitHiX_Pvwa7Flw2qHRUwBvjLJY,3889
 pertpy/tools/_scgen/_utils.py,sha256=qz5QUn_Bvk2NGyYVzp3jgjWTFOMt1YyHwUo6HWtoThY,2871
-pertpy-0.11.5.dist-info/METADATA,sha256=YEYgYTHkjmyWyboRL3RhBaSxOw86O5vr0wpXdvaLTGk,8827
-pertpy-0.11.5.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-pertpy-0.11.5.dist-info/licenses/LICENSE,sha256=XuiT2hxeRInhquEIBKMZ5M21n5syhDQ4XbABoposIAg,1100
-pertpy-0.11.5.dist-info/RECORD,,
+pertpy-1.0.0.dist-info/METADATA,sha256=PnK9O-MyIPzSy5DNOqMN7G6zcxZ2ZTJnMFB5cEr5XJQ,8920
+pertpy-1.0.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+pertpy-1.0.0.dist-info/licenses/LICENSE,sha256=XuiT2hxeRInhquEIBKMZ5M21n5syhDQ4XbABoposIAg,1100
+pertpy-1.0.0.dist-info/RECORD,,