pertpy 1.0.1__py3-none-any.whl → 1.0.3__py3-none-any.whl

pertpy/tools/_perturbation_space/_perturbation_space.py

@@ -6,7 +6,6 @@ import numpy as np
 import pandas as pd
 from anndata import AnnData
 from lamin_utils import logger
-from rich import print
 from scipy.stats import entropy
 
 if TYPE_CHECKING:
@@ -27,6 +26,7 @@ class PerturbationSpace:
     def compute_control_diff(  # type: ignore
         self,
         adata: AnnData,
+        *,
         target_col: str = "perturbation",
         group_col: str = None,
         reference_key: str = "control",
@@ -41,8 +41,8 @@ class PerturbationSpace:
 
         Args:
             adata: Anndata object of size cells x genes.
-            target_col: .obs column name that stores the label of the perturbation applied to each cell.
-            group_col: .obs column name that stores the label of the group of each cell. If None, ignore groups.
+            target_col: `.obs` column name that stores the label of the perturbation applied to each cell.
+            group_col: `.obs` column name that stores the label of the group of each cell. If None, ignore groups.
             reference_key: The key of the control values.
             layer_key: Key of the AnnData layer to use for computation.
             new_layer_key: the results are stored in the given layer.
@@ -146,6 +146,7 @@ class PerturbationSpace:
     def add(
         self,
         adata: AnnData,
+        *,
         perturbations: Iterable[str],
         reference_key: str = "control",
         ensure_consistency: bool = False,
@@ -157,8 +158,8 @@ class PerturbationSpace:
             adata: Anndata object of size n_perts x dim.
             perturbations: Perturbations to add.
             reference_key: perturbation source from which the perturbation summation starts.
-            ensure_consistency: If True, runs differential expression on all data matrices to ensure consistency of linear space.
-            target_col: .obs column name that stores the label of the perturbation applied to each cell.
+            ensure_consistency: Whether to run differential expression on all data matrices to ensure consistency of linear space.
+            target_col: `.obs` column name that stores the label of the perturbation applied to each cell.
 
         Returns:
             Anndata object of size (n_perts+1) x dim, where the last row is the addition of the specified perturbations.
@@ -255,6 +256,7 @@ class PerturbationSpace:
     def subtract(
         self,
         adata: AnnData,
+        *,
         perturbations: Iterable[str],
         reference_key: str = "control",
         ensure_consistency: bool = False,
@@ -266,8 +268,8 @@ class PerturbationSpace:
             adata: Anndata object of size n_perts x dim.
             perturbations: Perturbations to subtract.
             reference_key: Perturbation source from which the perturbation subtraction starts.
-            ensure_consistency: If True, runs differential expression on all data matrices to ensure consistency of linear space.
-            target_col: .obs column name that stores the label of the perturbation applied to each cell.
+            ensure_consistency: Whether to run differential expression on all data matrices to ensure consistency of linear space.
+            target_col: `.obs` column name that stores the label of the perturbation applied to each cell.
 
         Returns:
             Anndata object of size (n_perts+1) x dim, where the last row is the subtraction of the specified perturbations.
@@ -361,13 +363,15 @@ class PerturbationSpace:
 
         return new_perturbation
 
-    def label_transfer(
+    def label_transfer(  # noqa: D417
         self,
         adata: AnnData,
-        column: str = "perturbation",
+        *,
+        target_column: str = "perturbation",
         column_uncertainty_score_key: str = "perturbation_transfer_uncertainty",
         target_val: str = "unknown",
         neighbors_key: str = "neighbors",
+        **kwargs,
     ) -> None:
         """Impute missing values in the specified column using KNN imputation in the space defined by `use_rep`.
 
@@ -377,7 +381,7 @@ class PerturbationSpace:
 
         Args:
             adata: The AnnData object containing single-cell data.
-            column: The column name in adata.obs to perform imputation on.
+            target_column: The column name in adata.obs to perform imputation on.
             column_uncertainty_score_key: The column name in adata.obs to store the uncertainty score of the label transfer.
             target_val: The target value to impute.
             neighbors_key: The key in adata.uns where the neighbors are stored.
@@ -399,12 +403,16 @@ class PerturbationSpace:
         if neighbors_key not in adata.uns:
             raise ValueError(f"Key {neighbors_key} not found in adata.uns. Please run `sc.pp.neighbors` first.")
 
-        labels = adata.obs[column].astype(str)
+        # backwards compatibility
+        if "column" in kwargs:
+            target_column = kwargs.pop("column")
+
+        labels = adata.obs[target_column].astype(str)
         target_cells = labels == target_val
 
         connectivities = adata.obsp[adata.uns[neighbors_key]["connectivities_key"]]
         # convert labels to an incidence matrix
-        one_hot_encoded_labels = adata.obs[column].astype(str).str.get_dummies()
+        one_hot_encoded_labels = adata.obs[target_column].astype(str).str.get_dummies()
         # convert to distance-weighted neighborhood incidence matrix
         weighted_label_occurence = pd.DataFrame(
             (one_hot_encoded_labels.values.T * connectivities).T,
@@ -413,8 +421,8 @@ class PerturbationSpace:
         )
         # choose best label for each target cell
         best_labels = weighted_label_occurence.drop(target_val, axis=1)[target_cells].idxmax(axis=1)
-        adata.obs[column] = labels
-        adata.obs.loc[target_cells, column] = best_labels
+        adata.obs[target_column] = labels
+        adata.obs.loc[target_cells, target_column] = best_labels
 
         # calculate uncertainty
         uncertainty = np.zeros(adata.n_obs)

pertpy/tools/_perturbation_space/_simple.py

@@ -3,6 +3,7 @@ from __future__ import annotations
 from typing import Literal
 
 import numpy as np
+import pandas as pd
 import scanpy as sc
 from anndata import AnnData
 from sklearn.cluster import DBSCAN, KMeans
@@ -29,8 +30,8 @@ class CentroidSpace(PerturbationSpace):
             target_col: .obs column that stores the label of the perturbation applied to each cell.
             layer_key: If specified pseudobulk computation is done by using the specified layer. Otherwise, computation is done with .X
             embedding_key: `obsm` key of the AnnData embedding to use for computation. Defaults to the 'X' matrix otherwise.
-            keep_obs: Whether .obs columns in the input AnnData should be kept in the output pseudobulk AnnData. Only .obs columns with the same value for
-                each cell of one perturbation are kept.
+            keep_obs: Whether .obs columns in the input AnnData should be kept in the output pseudobulk AnnData.
+                Only .obs columns with the same value for each cell of one perturbation are kept.
 
         Returns:
             AnnData object with one observation per perturbation, storing the embedding data of the
@@ -170,10 +171,15 @@ class PseudobulkSpace(PerturbationSpace):
         if mode in ps_adata.layers:
             ps_adata.X = ps_adata.layers[mode]
 
-        for col in original_obs.columns:
-            if col not in ps_adata.obs.columns:
-                grouped_values = original_obs.groupby(grouping_cols)[col].first()
-                ps_adata.obs[col] = grouped_values.reindex(ps_adata.obs.index).values
+        missing_cols = [col for col in original_obs.columns if col not in ps_adata.obs.columns]
+        new_cols_data = {}
+
+        for col in missing_cols:
+            grouped_values = original_obs.groupby(grouping_cols, observed=False)[col].first()
+            new_cols_data[col] = grouped_values.reindex(ps_adata.obs.index).values
+
+        if new_cols_data:
+            ps_adata.obs = pd.concat([ps_adata.obs, pd.DataFrame(new_cols_data, index=ps_adata.obs.index)], axis=1)
 
         ps_adata.obs[target_col] = ps_adata.obs[target_col].astype("category")
 

pertpy/tools/_scgen/_scgenvae.py

@@ -4,7 +4,8 @@ import flax.linen as nn
 import jax.numpy as jnp
 import numpyro.distributions as dist
 from scvi import REGISTRY_KEYS
-from scvi.module.base import JaxBaseModuleClass, LossOutput, flax_configure
+from scvi.module._jaxvae import LossOutput
+from scvi.module.base import JaxBaseModuleClass, flax_configure
 
 from ._base_components import FlaxDecoder, FlaxEncoder
 

pertpy/tools/core.py

@@ -0,0 +1,18 @@
+import numpy as np
+from scipy import sparse
+
+
+def _is_raw_counts(X: np.ndarray | sparse.spmatrix) -> bool:
+    """Check if data appears to be raw counts."""
+    if sparse.issparse(X):
+        sample = X[:1000, :1000] if X.shape[0] > 1000 else X
+        data = sample.data
+    else:
+        sample = X[:1000, :1000] if X.shape[0] > 1000 else X
+        data = sample.ravel()
+
+    non_zero_data = data[data > 0]
+    if len(non_zero_data) == 0:
+        return True
+
+    return np.all(data >= 0) and np.all(data == np.round(data))

{pertpy-1.0.1.dist-info → pertpy-1.0.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pertpy
-Version: 1.0.1
+Version: 1.0.3
 Summary: Perturbation Analysis in the scverse ecosystem.
 Project-URL: Documentation, https://pertpy.readthedocs.io
 Project-URL: Source, https://github.com/scverse/pertpy
@@ -50,8 +50,11 @@ Requires-Dist: adjusttext
 Requires-Dist: arviz
 Requires-Dist: blitzgsea
 Requires-Dist: fast-array-utils[accel,sparse]
+Requires-Dist: flax
+Requires-Dist: funsor
 Requires-Dist: lamin-utils
 Requires-Dist: mudata
+Requires-Dist: numpyro
 Requires-Dist: openpyxl
 Requires-Dist: ott-jax
 Requires-Dist: pubchempy
@@ -61,8 +64,15 @@ Requires-Dist: rich
 Requires-Dist: scanpy
 Requires-Dist: scikit-learn>=1.4
 Requires-Dist: scikit-misc
-Requires-Dist: scvi-tools
 Requires-Dist: sparsecca
+Provides-Extra: all
+Requires-Dist: ete4; extra == 'all'
+Requires-Dist: formulaic; extra == 'all'
+Requires-Dist: formulaic-contrasts>=0.2.0; extra == 'all'
+Requires-Dist: pydeseq2>=v0.5.0; extra == 'all'
+Requires-Dist: pyqt6; extra == 'all'
+Requires-Dist: scvi-tools[jax]; extra == 'all'
+Requires-Dist: toytree>=3.0; extra == 'all'
 Provides-Extra: de
 Requires-Dist: formulaic; extra == 'de'
 Requires-Dist: formulaic-contrasts>=0.2.0; extra == 'de'
@@ -90,6 +100,8 @@ Requires-Dist: sphinx-remove-toctrees; extra == 'doc'
 Requires-Dist: sphinx>=8.1; extra == 'doc'
 Requires-Dist: sphinxcontrib-bibtex>=1.0.0; extra == 'doc'
 Requires-Dist: sphinxext-opengraph; extra == 'doc'
+Provides-Extra: scgen
+Requires-Dist: scvi-tools[jax]; extra == 'scgen'
 Provides-Extra: tcoda
 Requires-Dist: ete4; extra == 'tcoda'
 Requires-Dist: pyqt6; extra == 'tcoda'

{pertpy-1.0.1.dist-info → pertpy-1.0.3.dist-info}/RECORD

@@ -1,34 +1,35 @@
-pertpy/__init__.py,sha256=R-RrfgZrhMfn7G60kmTDN88ECqS90AyY9Ed5615hQEg,972
+pertpy/__init__.py,sha256=hrz1ULRH4dscWdjRR-qELR8RJAGHCsOGcQswOodD8Z8,972
 pertpy/_doc.py,sha256=j5TMNC-DA9yIMqIIUNpjpcVgWfRqyBBfvbRjnCM_OLs,427
 pertpy/_types.py,sha256=IcHCojCUqx8CapibNkcYf2TUqjBFP2ujeELvn_IBSBQ,154
 pertpy/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pertpy/data/__init__.py,sha256=ah3yvoxkgbdMUNAWxS3SyqcUuVamBOSeuWkF2QRAEwM,2703
-pertpy/data/_dataloader.py,sha256=Cb08iJj7vH-VishU4NJ5nzPPgviFLY1f5p3K4eVvTeg,4679
-pertpy/data/_datasets.py,sha256=4IceyYURpstZSFRrD6gBjoYg8uRbEPo1QLXTt-SwB5k,65507
+pertpy/data/_dataloader.py,sha256=1xiux3_eb4-0ZeirM0L7VAhTg_Tos0t_d8oBLIBTCrs,4679
+pertpy/data/_datasets.py,sha256=5HF7k2snJFUveidgRdLeaiane43FI2OAgwB6gl2Vp8Q,66301
 pertpy/metadata/__init__.py,sha256=wROPCXmJX2v5schJaBTPQtGW-FGCNWPfO_6bpnXwk-c,276
-pertpy/metadata/_cell_line.py,sha256=hKmaZvjIsQ3wHo__0aKo3JlWvsf8-4OD-gIBNQnW8_E,42716
+pertpy/metadata/_cell_line.py,sha256=dtHjyFPtVzA31fib3IdURCBbsHDjbKyGDrJo9veSEU8,42854
 pertpy/metadata/_compound.py,sha256=JsAv_KCcNkgVVrXTyhu-BeM8rBX8a93Wq5Z6avpxN7Y,4764
-pertpy/metadata/_drug.py,sha256=8QDSyxiFl25JdS80EQJC_krg6fEe5LIQEE6BsV1r8nY,9006
+pertpy/metadata/_drug.py,sha256=vfd6I3a9nc7vvB4Z4KVgdBIFMyCPdsQ8-cqO46b_2sA,9062
 pertpy/metadata/_look_up.py,sha256=0nrI_xy-qBZ3tyt4dwhEBwm0A9WP95ZaDiUQFf_88FU,28663
 pertpy/metadata/_metadata.py,sha256=hzaLHRyf6YtEMdkZ7_fqTvnlYhSmjQINHz42FqVYrSU,2805
 pertpy/metadata/_moa.py,sha256=kMpjqReu-WV_tbVJLrKe7gc-WyGkkEX-59V-ZUY3X5g,4536
 pertpy/plot/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pertpy/preprocessing/__init__.py,sha256=VAPFaeq2_qCvdFkQTCj_Hm460HC4Tersu8Rig_tnp_Y,71
-pertpy/preprocessing/_guide_rna.py,sha256=ijL-bjQ-9qn4r3DlhBxzsqk-bD4RqPsFlok-Otj4hg8,15872
-pertpy/preprocessing/_guide_rna_mixture.py,sha256=pT_YkjmN4iEJ-THBROu_dpbr8E6u8GJw36YoGseikD0,6422
-pertpy/tools/__init__.py,sha256=oOhB99SZBx1XUohaqXV7T_hZoN6xf-WMOpqgvw5gn1I,2073
-pertpy/tools/_augur.py,sha256=tc1YKyc0BwzrEGgctsfyy7DsTNKxyvy7ZvWraTWCc1A,55262
+pertpy/preprocessing/_guide_rna.py,sha256=eJ4ARuVsNJ3t3TFXeHGjbbd3UxBAwomPDR1gGlL-3yo,16107
+pertpy/preprocessing/_guide_rna_mixture.py,sha256=tLFcgeNOe5K6dNUzXN2rJ4JzYW0d6q9sjEHpULB04FI,6799
+pertpy/tools/__init__.py,sha256=kIYPSixvRYqprWnS09JCS2gJXd822tmbZP1xQDcyWzs,2387
+pertpy/tools/_augur.py,sha256=8DPFLPoP-CTJC8ODCadhCIybEaSgp-XnqtfzUMDOGr0,56138
 pertpy/tools/_cinemaot.py,sha256=54-rS0AEj31dMe7iU4kEmLoAunq3jNuhsBE3IEp9hrI,38071
 pertpy/tools/_dialogue.py,sha256=xWW5XiQUEHTvB7WURzndmm-EF4EhLeEnOV_-7NP6heU,52360
 pertpy/tools/_enrichment.py,sha256=55mwotLH9DXQOhl85MCkxXu-MX0RysLyrPheJysAnF0,21369
 pertpy/tools/_milo.py,sha256=PfLgEsYa5i35j25BNgGEkXk9UPM-ZhFxQbEWDA1e_fc,48192
-pertpy/tools/_mixscape.py,sha256=HfrpBeRlxHXaOpZkF2FmX7dg35kUB1rL0_-n2aSi2_0,57905
+pertpy/tools/_mixscape.py,sha256=uL6iotgBc5qcmUamhTg4iirp7GxPKqyJurVzKTN2wuU,58413
+pertpy/tools/core.py,sha256=hr4aIPJlWy4Q0rJXPghNGwhwpjyQRz9tUnVprf792JM,526
 pertpy/tools/decoupler_LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
 pertpy/tools/transferlearning_MMD_LICENSE,sha256=MUvDA-o_j9htRpI8fStVdCRuyLdPkQUuIH0a_EIc57w,1069
 pertpy/tools/_coda/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pertpy/tools/_coda/_base_coda.py,sha256=2YIB7rVf9CxwYyQCpC8e3VYCxfurvyAqUs-4qJ5pubg,111817
-pertpy/tools/_coda/_sccoda.py,sha256=FaXn20K4ROYtbrZop_dWRokfwX0vlCizKV02V3Cf7zo,24611
-pertpy/tools/_coda/_tasccoda.py,sha256=BTaOAmL458zQ_og3x4ENlDnJHD6_F4YkdCoXWsF4i1U,30465
+pertpy/tools/_coda/_sccoda.py,sha256=TRNJhY5IonCMsyvnGwRBK8w8fYqPH_hjWiT7zL25RiI,22948
+pertpy/tools/_coda/_tasccoda.py,sha256=AdJTtBBFj5fUBKUSmbuu67nkFSO2cVp53Lyt7t-HBlE,30866
 pertpy/tools/_differential_gene_expression/__init__.py,sha256=8_u7nsHY5GfFITT0Rs3v1p1vXpsGIWcBzwipuhXM3Ww,1653
 pertpy/tools/_differential_gene_expression/_base.py,sha256=GbBi8o7rTA3wH5DZJ9C1QzfqB5yak4r3xMvKQrizsTY,38274
 pertpy/tools/_differential_gene_expression/_checks.py,sha256=hH_GP0lWGO-5zrCFX4YiIVCZBCuK0ZJ0jFmdlx2Qm4k,1639
@@ -42,17 +43,17 @@ pertpy/tools/_distances/_distance_tests.py,sha256=wDDRkM-WmcfT5m5Zat-3ianGU1aC6H
 pertpy/tools/_distances/_distances.py,sha256=iJNqMc9CxgZfEMHcxIocKGc4X4S2dJsRy3YerxVnFKo,51003
 pertpy/tools/_perturbation_space/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pertpy/tools/_perturbation_space/_clustering.py,sha256=pNx_SpPkZfCbgF7vzHWqAaiiHdbxPaA-L-hTWTbzFhI,3528
-pertpy/tools/_perturbation_space/_comparison.py,sha256=-NzCPRT-IlhJ9hOz7NQLSk0riIzr2C0yZvX6zm3kon4,4291
-pertpy/tools/_perturbation_space/_discriminator_classifiers.py,sha256=ARdNatcmsz370CF-PexDHPwUrih7KW4A5URzHVDNrcw,23126
+pertpy/tools/_perturbation_space/_comparison.py,sha256=2sxlnHu-kEn8jApl8uZ8AIwV_gAnIf7SmuOjLaN0kgw,4291
+pertpy/tools/_perturbation_space/_discriminator_classifiers.py,sha256=4nX_PwQp3JvWPeN8FADaukPfNF87Bn1r2IvZKCy3n8I,20076
 pertpy/tools/_perturbation_space/_metrics.py,sha256=y8-baP8WRdB1iDgvP3uuQxSCDxA2lcxvEHHM2C_vWHY,3248
-pertpy/tools/_perturbation_space/_perturbation_space.py,sha256=Vyh15wWw9dcu2YUWhziQd2mA9-4IY8EC5dzkBT9HaIo,19457
-pertpy/tools/_perturbation_space/_simple.py,sha256=xS7Lrq3RzJC8IgVKKs2Utqbs7iJ5L1DANquCRcS3Fhg,13109
+pertpy/tools/_perturbation_space/_perturbation_space.py,sha256=xqSC_jLzsIl4Y_uxVJX7-m3z2HWy5ZVPOAmWMno1xoQ,19677
+pertpy/tools/_perturbation_space/_simple.py,sha256=8qq1skSnsvxkV9sRgDip-E-_suy2dAs7Fgu9JgHeCkQ,13349
 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/_scgenvae.py,sha256=L6Jfssqo7eNoZPTk4560XIU_ocvhoCpQJFb0DqWC-Nc,3920
 pertpy/tools/_scgen/_utils.py,sha256=qz5QUn_Bvk2NGyYVzp3jgjWTFOMt1YyHwUo6HWtoThY,2871
-pertpy-1.0.1.dist-info/METADATA,sha256=U9XINrPTrqx9UfLIsUt1X9p6LQLvNSV89GGAZnEHnks,8939
-pertpy-1.0.1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-pertpy-1.0.1.dist-info/licenses/LICENSE,sha256=XuiT2hxeRInhquEIBKMZ5M21n5syhDQ4XbABoposIAg,1100
-pertpy-1.0.1.dist-info/RECORD,,
+pertpy-1.0.3.dist-info/METADATA,sha256=vPEEe65P5kDErs7u0hByiNenDuPG15uqpkYIXhw4hGA,9380
+pertpy-1.0.3.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+pertpy-1.0.3.dist-info/licenses/LICENSE,sha256=XuiT2hxeRInhquEIBKMZ5M21n5syhDQ4XbABoposIAg,1100
+pertpy-1.0.3.dist-info/RECORD,,