pertpy 0.7.0__py3-none-any.whl → 0.8.0__py3-none-any.whl

pertpy/tools/_enrichment.py

@@ -82,18 +82,15 @@ class Enrichment:
                      - A dictionary of dictionaries with group categories as keys. Use `nested=True` in this case.
                      If not provided, ChEMBL-derived drug target sets are used.
             nested: Indicates if `targets` is a dictionary of dictionaries with group categories as keys.
-                    Defaults to False.
             categories: To subset the gene groups to specific categories, especially when `targets=None` or `nested=True`.
                         For ChEMBL drug targets, these are ATC level 1/level 2 category codes.
             method: Method for scoring gene groups. `"mean"` calculates the mean over all genes,
                     while `"seurat"` uses a background profile subtraction approach.
-                    Defaults to 'mean'.
-            layer: Specifies which `.layers` of AnnData to use for expression values. Defaults to `.X` if None.
+            layer: Specifies which `.layers` of AnnData to use for expression values.
             n_bins: The number of expression bins for the `'seurat'` method.
             ctrl_size: The number of genes to randomly sample from each expression bin for the `"seurat"` method.
             key_added: Prefix key that adds the results to `uns`.
                        Note that the actual values are `key_added_score`, `key_added_variables`, `key_added_genes`, `key_added_all_genes`.
-                       Defaults to `pertpy_enrichment`.
 
         Returns:
             An AnnData object with scores.
@@ -259,16 +256,15 @@ class Enrichment:
                    in the original expression space.
             targets: The gene groups to evaluate, either as a dictionary with names of the
                      groups as keys and gene lists as values, or a dictionary of dictionaries
-                     with names of gene group categories as keys. Defaults to None, in which
+                     with names of gene group categories as keys.
                      case it uses `d2c.score()` output or loads ChEMBL-derived drug target sets.
             nested: Indicates if `targets` is a dictionary of dictionaries with group
-                    categories as keys. Defaults to False.
+                    categories as keys.
             categories: Used to subset the gene groups to one or more categories,
-                        applicable if `targets=None` or `nested=True`. Defaults to None.
+                        applicable if `targets=None` or `nested=True`.
             absolute: If True, passes the absolute values of scores to GSEA, improving
-                      statistical power. Defaults to False.
+                      statistical power.
             key_added: Prefix key that adds the results to `uns`.
-                       Defaults to `pertpy_enrichment_gsea`.
 
         Returns:
             A dictionary with clusters as keys and data frames of test results sorted on
@@ -317,13 +313,12 @@ class Enrichment:
             targets: Gene groups to evaluate, which can be targets of known drugs, GO terms, pathway memberships, etc.
                      Accepts a dictionary of dictionaries with group categories as keys.
                      If not provided, ChEMBL-derived or dgbidb drug target sets are used, given by `source`.
-            source: Source of drug target sets when `targets=None`, `chembl`, `dgidb` or `pharmgkb`. Defaults to `chembl`.
+            source: Source of drug target sets when `targets=None`, `chembl`, `dgidb` or `pharmgkb`.
             categories: To subset the gene groups to specific categories, especially when `targets=None`.
                             For ChEMBL drug targets, these are ATC level 1/level 2 category codes.
-            category_name: The name of category used to generate a nested drug target set when `targets=None` and `source=dgidb|pharmgkb`. Defaults to `interaction_type`.
+            category_name: The name of category used to generate a nested drug target set when `targets=None` and `source=dgidb|pharmgkb`.
             groupby: dotplot groupby such as clusters or cell types.
             key: Prefix key of enrichment results in `uns`.
-                 Defaults to `pertpy_enrichment`.
             kwargs: Passed to scanpy dotplot.
 
         Returns:
@@ -436,9 +431,9 @@ class Enrichment:
         Args:
             adata: AnnData object to plot.
             enrichment: Cluster names as keys, blitzgsea's ``gsea()`` output as values.
-            n: How many top scores to show for each group. Defaults to 10.
-            key: GSEA results key in `uns`. Defaults to "pertpy_enrichment_gsea".
-            interactive_plot: Whether to plot interactively or not. Defaults to False.
+            n: How many top scores to show for each group.
+            key: GSEA results key in `uns`.
+            interactive_plot: Whether to plot interactively or not.
 
         Examples:
             >>> import pertpy as pt

pertpy/tools/_kernel_pca.py

@@ -31,7 +31,7 @@ def kernel_pca(
 
     Returns:
         If `copy=True`, returns the copy of `adata` with kernel pca in `.obsm["X_kpca"]`.
-        Otherwise writes kernel pca directly to `.obsm["X_kpca"]` of the provided `adata`.
+        Otherwise, writes kernel pca directly to `.obsm["X_kpca"]` of the provided `adata`.
         If `return_transformer=True`, returns also the fitted `KernelPCA` transformer.
     """
     if copy:

pertpy/tools/_milo.py

@@ -11,22 +11,16 @@ import pandas as pd
 import scanpy as sc
 import seaborn as sns
 from anndata import AnnData
+from lamin_utils import logger
 from mudata import MuData
-from rich import print
 
 if TYPE_CHECKING:
     from collections.abc import Sequence
 
     from matplotlib.axes import Axes
     from matplotlib.colors import Colormap
+    from matplotlib.figure import Figure
 
-try:
-    from rpy2.robjects import conversion, numpy2ri, pandas2ri
-    from rpy2.robjects.packages import STAP, PackageNotInstalledError, importr
-except ModuleNotFoundError:
-    print(
-        "[bold yellow]ryp2 is not installed. Install with [green]pip install rpy2 [yellow]to run tools with R support."
-    )
 from scipy.sparse import csr_matrix
 from sklearn.metrics.pairwise import euclidean_distances
 
@@ -35,7 +29,16 @@ class Milo:
     """Python implementation of Milo."""
 
     def __init__(self):
-        pass
+        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,
@@ -48,7 +51,7 @@ class Milo:
             input: AnnData
             feature_key: Key to store the cell-level AnnData object in the MuData object
         Returns:
-            MuData: MuData object with original AnnData. Defaults to`mudata[feature_key]`.
+            MuData: MuData object with original AnnData.
 
         Examples:
             >>> import pertpy as pt
@@ -80,11 +83,10 @@ class Milo:
             neighbors_key: The key in `adata.obsp` or `mdata[feature_key].obsp` to use as KNN graph.
                            If not specified, `make_nhoods` looks .obsp[‘connectivities’] for connectivities (default storage places for `scanpy.pp.neighbors`).
                            If specified, it looks at .obsp[.uns[neighbors_key][‘connectivities_key’]] for connectivities.
-                           Defaults to None.
-            feature_key: If input data is MuData, specify key to cell-level AnnData object. Defaults to 'rna'.
-            prop: Fraction of cells to sample for neighbourhood index search. Defaults to 0.1.
-            seed: Random seed for cell sampling. Defaults to 0.
-            copy: Determines whether a copy of the `adata` is returned. Defaults to False.
+            feature_key: If input data is MuData, specify key to cell-level AnnData object.
+            prop: Fraction of cells to sample for neighbourhood index search.
+            seed: Random seed for cell sampling.
+            copy: Determines whether a copy of the `adata` is returned.
 
         Returns:
             If `copy=True`, returns the copy of `adata` with the result in `.obs`, `.obsm`, and `.uns`.
@@ -128,7 +130,7 @@ class Milo:
             try:
                 knn_graph = adata.obsp["connectivities"].copy()
             except KeyError:
-                print('No "connectivities" slot in adata.obsp -- please run scanpy.pp.neighbors(adata) first')
+                logger.error('No "connectivities" slot in adata.obsp -- please run scanpy.pp.neighbors(adata) first')
                 raise
         else:
             try:
@@ -183,6 +185,7 @@ class Milo:
         dist_mat = knn_dists[nhood_ixs, :]
         k_distances = dist_mat.max(1).toarray().ravel()
         adata.obs["nhood_kth_distance"] = 0
+        adata.obs["nhood_kth_distance"] = adata.obs["nhood_kth_distance"].astype(float)
         adata.obs.loc[adata.obs["nhood_ixs_refined"] == 1, "nhood_kth_distance"] = k_distances
 
         if copy:
@@ -199,7 +202,7 @@ class Milo:
         Args:
             data: AnnData object with neighbourhoods defined in `obsm['nhoods']` or MuData object with a modality with neighbourhoods defined in `obsm['nhoods']`
             sample_col: Column in adata.obs that contains sample information
-            feature_key: If input data is MuData, specify key to cell-level AnnData object. Defaults to 'rna'.
+            feature_key: If input data is MuData, specify key to cell-level AnnData object.
 
         Returns:
             MuData object storing the original (i.e. rna) AnnData in `mudata[feature_key]`
@@ -230,7 +233,7 @@ class Milo:
             try:
                 nhoods = adata.obsm["nhoods"]
             except KeyError:
-                print('Cannot find "nhoods" slot in adata.obsm -- please run milopy.make_nhoods(adata)')
+                logger.error('Cannot find "nhoods" slot in adata.obsm -- please run milopy.make_nhoods(adata)')
                 raise
         # Make nhood abundance matrix
         sample_dummies = pd.get_dummies(adata.obs[sample_col])
@@ -238,7 +241,7 @@ class Milo:
         sample_dummies = csr_matrix(sample_dummies.values)
         nhood_count_mat = nhoods.T.dot(sample_dummies)
         sample_obs = pd.DataFrame(index=all_samples)
-        sample_adata = AnnData(X=nhood_count_mat.T, obs=sample_obs, dtype=np.float32)
+        sample_adata = AnnData(X=nhood_count_mat.T, obs=sample_obs)
         sample_adata.uns["sample_col"] = sample_col
         # Save nhood index info
         sample_adata.var["index_cell"] = adata.obs_names[adata.obs["nhood_ixs_refined"] == 1]
@@ -270,10 +273,10 @@ class Milo:
             design: Formula for the test, following glm syntax from R (e.g. '~ condition').
                     Terms should be columns in `milo_mdata[feature_key].obs`.
             model_contrasts: A string vector that defines the contrasts used to perform DA testing, following glm syntax from R (e.g. "conditionDisease - conditionControl").
-                             If no contrast is specified (default), then the last categorical level in condition of interest is used as the test group. Defaults to None.
-            subset_samples: subset of samples (obs in `milo_mdata['milo']`) to use for the test. Defaults to None.
-            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. Defaults to True.
-            feature_key: If input data is MuData, specify key to cell-level AnnData object. Defaults to 'rna'.
+                             If no contrast is specified (default), then the last categorical level in condition of interest is used as the test group.
+            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"
 
         Returns:
@@ -297,8 +300,8 @@ class Milo:
         try:
             sample_adata = mdata["milo"]
         except KeyError:
-            print(
-                "[bold red]milo_mdata should be a MuData object with two slots:"
+            logger.error(
+                "milo_mdata should be a MuData object with two slots:"
                 " feature_key and 'milo' - please run milopy.count_nhoods() first"
             )
             raise
@@ -312,7 +315,7 @@ class Milo:
             sample_obs = adata.obs[covariates + [sample_col]].drop_duplicates()
         except KeyError:
             missing_cov = [x for x in covariates if x not in sample_adata.obs.columns]
-            print("Covariates {c} are not columns in adata.obs".format(c=" ".join(missing_cov)))
+            logger.warning("Covariates {c} are not columns in adata.obs".format(c=" ".join(missing_cov)))
             raise
         sample_obs = sample_obs[covariates + [sample_col]]
         sample_obs.index = sample_obs[sample_col].astype("str")
@@ -320,7 +323,7 @@ class Milo:
         try:
             assert sample_obs.loc[sample_adata.obs_names].shape[0] == len(sample_adata.obs_names)
         except AssertionError:
-            print(
+            logger.warning(
                 f"Values in mdata[{feature_key}].obs[{covariates}] cannot be unambiguously assigned to each sample"
                 f" -- each sample value should match a single covariate value"
             )
@@ -332,7 +335,9 @@ class Milo:
             design_df = sample_adata.obs[covariates]
         except KeyError:
             missing_cov = [x for x in covariates if x not in sample_adata.obs.columns]
-            print('Covariates {c} are not columns in adata.uns["sample_adata"].obs'.format(c=" ".join(missing_cov)))
+            logger.error(
+                'Covariates {c} are not columns in adata.uns["sample_adata"].obs'.format(c=" ".join(missing_cov))
+            )
             raise
         # Get count matrix
         count_mat = sample_adata.X.T.toarray()
@@ -376,6 +381,8 @@ class Milo:
                     return(colnames(m))
                 }
                 """
+                from rpy2.robjects.packages import STAP
+
                 get_model_cols = STAP(r_str, "get_model_cols")
                 model_mat_cols = get_model_cols.get_model_cols(design_df, design)
                 model_df = pd.DataFrame(model)
@@ -383,13 +390,16 @@ class Milo:
                 try:
                     mod_contrast = limma.makeContrasts(contrasts=model_contrasts, levels=model_df)
                 except ValueError:
-                    print("Model contrasts must be in the form 'A-B' or 'A+B'")
+                    logger.error("Model contrasts must be in the form 'A-B' or 'A+B'")
                     raise
                 res = base.as_data_frame(
                     edgeR.topTags(edgeR.glmQLFTest(fit, contrast=mod_contrast), sort_by="none", n=np.inf)
                 )
             else:
                 res = base.as_data_frame(edgeR.topTags(edgeR.glmQLFTest(fit, coef=n_coef), sort_by="none", n=np.inf))
+
+            from rpy2.robjects import conversion
+
             res = conversion.rpy2py(res)
             if not isinstance(res, pd.DataFrame):
                 res = pd.DataFrame(res)
@@ -414,7 +424,7 @@ class Milo:
         Args:
             mdata: MuData object
             anno_col: Column in adata.obs containing the cell annotations to use for nhood labelling
-            feature_key: If input data is MuData, specify key to cell-level AnnData object. Defaults to 'rna'.
+            feature_key: If input data is MuData, specify key to cell-level AnnData object.
 
         Returns:
             None. Adds in place:
@@ -437,7 +447,7 @@ class Milo:
         try:
             sample_adata = mdata["milo"]
         except KeyError:
-            print(
+            logger.error(
                 "milo_mdata should be a MuData object with two slots: feature_key and 'milo' - please run milopy.count_nhoods(adata) first"
             )
             raise
@@ -468,7 +478,7 @@ class Milo:
         Args:
             mdata: MuData object
             anno_col: Column in adata.obs containing the cell annotations to use for nhood labelling
-            feature_key: If input data is MuData, specify key to cell-level AnnData object. Defaults to 'rna'.
+            feature_key: If input data is MuData, specify key to cell-level AnnData object.
 
         Returns:
             None. Adds in place:
@@ -509,7 +519,7 @@ class Milo:
         Args:
             mdata: MuData object
             new_covariates: columns in `milo_mdata[feature_key].obs` to add to `milo_mdata['milo'].obs`.
-            feature_key: If input data is MuData, specify key to cell-level AnnData object. Defaults to 'rna'.
+            feature_key: If input data is MuData, specify key to cell-level AnnData object.
 
         Returns:
             None, adds columns to `milo_mdata['milo']` in place
@@ -528,7 +538,7 @@ class Milo:
         try:
             sample_adata = mdata["milo"]
         except KeyError:
-            print(
+            logger.error(
                 "milo_mdata should be a MuData object with two slots: feature_key and 'milo' - please run milopy.count_nhoods(adata) first"
             )
             raise
@@ -542,14 +552,14 @@ class Milo:
             sample_obs = adata.obs[covariates + [sample_col]].drop_duplicates()
         except KeyError:
             missing_cov = [covar for covar in covariates if covar not in sample_adata.obs.columns]
-            print("Covariates {c} are not columns in adata.obs".format(c=" ".join(missing_cov)))
+            logger.error("Covariates {c} are not columns in adata.obs".format(c=" ".join(missing_cov)))
             raise
         sample_obs = sample_obs[covariates + [sample_col]].astype("str")
         sample_obs.index = sample_obs[sample_col]
         try:
             assert sample_obs.loc[sample_adata.obs_names].shape[0] == len(sample_adata.obs_names)
         except ValueError:
-            print(
+            logger.error(
                 "Covariates cannot be unambiguously assigned to each sample -- each sample value should match a single covariate value"
             )
             raise
@@ -560,8 +570,8 @@ class Milo:
 
         Args:
             mdata: MuData object
-            basis: Name of the obsm basis to use for layout of neighbourhoods (key in `adata.obsm`). Defaults to "X_umap".
-            feature_key: If input data is MuData, specify key to cell-level AnnData object. Defaults to 'rna'.
+            basis: Name of the obsm basis to use for layout of neighbourhoods (key in `adata.obsm`).
+            feature_key: If input data is MuData, specify key to cell-level AnnData object.
 
         Returns:
             - `milo_mdata['milo'].varp['nhood_connectivities']`: graph of overlap between neighbourhoods (i.e. no of shared cells)
@@ -593,13 +603,13 @@ class Milo:
             "distances_key": "",
         }
 
-    def add_nhood_expression(self, mdata: MuData, layer: str | None = None, feature_key: str | None = "rna"):
+    def add_nhood_expression(self, mdata: MuData, layer: str | None = None, feature_key: str | None = "rna") -> None:
         """Calculates the mean expression in neighbourhoods of each feature.
 
         Args:
             mdata: MuData object
-            layer: If provided, use `milo_mdata[feature_key][layer]` as expression matrix instead of `milo_mdata[feature_key].X`. Defaults to None.
-            feature_key: If input data is MuData, specify key to cell-level AnnData object. Defaults to 'rna'.
+            layer: If provided, use `milo_mdata[feature_key][layer]` as expression matrix instead of `milo_mdata[feature_key].X`.
+            feature_key: If input data is MuData, specify key to cell-level AnnData object.
 
         Returns:
             Updates adata in place to store the matrix of average expression in each neighbourhood in `milo_mdata['milo'].varm['expr']`
@@ -618,7 +628,7 @@ class Milo:
         try:
             sample_adata = mdata["milo"]
         except KeyError:
-            print(
+            logger.error(
                 "milo_mdata should be a MuData object with two slots:"
                 " feature_key and 'milo' - please run milopy.count_nhoods(adata) first"
             )
@@ -642,6 +652,9 @@ class Milo:
         self,
     ):
         """Set up rpy2 to run edgeR"""
+        from rpy2.robjects import numpy2ri, pandas2ri
+        from rpy2.robjects.packages import importr
+
         numpy2ri.activate()
         pandas2ri.activate()
         edgeR = self._try_import_bioc_library("edgeR")
@@ -660,11 +673,13 @@ class Milo:
         Args:
             name (str): R packages name
         """
+        from rpy2.robjects.packages import PackageNotInstalledError, importr
+
         try:
             _r_lib = importr(name)
             return _r_lib
         except PackageNotInstalledError:
-            print(f"Install Bioconductor library `{name!r}` first as `BiocManager::install({name!r}).`")
+            logger.error(f"Install Bioconductor library `{name!r}` first as `BiocManager::install({name!r}).`")
             raise
 
     def _graph_spatial_fdr(
@@ -678,7 +693,7 @@ class Milo:
 
         Args:
             sample_adata: Sample-level AnnData.
-            neighbors_key: The key in `adata.obsp` to use as KNN graph. Defaults to None.
+            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"]
@@ -718,10 +733,10 @@ class Milo:
         Args:
             mdata: MuData object
             alpha: Significance threshold. (default: 0.1)
-            min_logFC: Minimum absolute log-Fold Change to show results. If is 0, show all significant neighbourhoods. Defaults to 0.
+            min_logFC: Minimum absolute log-Fold Change to show results. If is 0, show all significant neighbourhoods.
             min_size: Minimum size of nodes in visualization. (default: 10)
-            plot_edges: If edges for neighbourhood overlaps whould be plotted. Defaults to False.
-            title: Plot title. Defaults to "DA log-Fold Change".
+            plot_edges: If edges for neighbourhood overlaps whould be plotted.
+            title: Plot title.
             show: Show the plot, do not return axis.
             save: If `True` or a `str`, save the figure. A string is appended to the default filename.
                   Infer the filetype if ending on {`'.pdf'`, `'.png'`, `'.svg'`}.
@@ -807,7 +822,7 @@ class Milo:
         Args:
             mdata: MuData object with feature_key slot, storing neighbourhood assignments in `mdata[feature_key].obsm['nhoods']`
             ix: index of neighbourhood to visualize
-            basis: Embedding to use for visualization. Defaults to "X_umap".
+            basis: Embedding to use for visualization.
             show: Show the plot, do not return axis.
             save: If True or a str, save the figure. A string is appended to the default filename. Infer the filetype if ending on {'.pdf', '.png', '.svg'}.
             **kwargs: Additional arguments to `scanpy.pl.embedding`.
@@ -853,14 +868,14 @@ class Milo:
         return_fig: bool | None = None,
         save: bool | str | None = None,
         show: bool | None = None,
-    ) -> None:
+    ) -> Figure | Axes | None:
         """Plot beeswarm plot of logFC against nhood labels
 
         Args:
             mdata: MuData object
             anno_col: Column in adata.uns['nhood_adata'].obs to use as annotation. (default: 'nhood_annotation'.)
             alpha: Significance threshold. (default: 0.1)
-            subset_nhoods: List of nhoods to plot. If None, plot all nhoods. Defaults to None.
+            subset_nhoods: List of nhoods to plot. If None, plot all nhoods.
             palette: Name of Seaborn color palette for violinplots.
                      Defaults to pre-defined category colors for violinplots.
 
@@ -960,13 +975,17 @@ class Milo:
 
         if save:
             plt.savefig(save, bbox_inches="tight")
+            return None
         if show:
             plt.show()
+            return None
         if return_fig:
             return plt.gcf()
         if (not show and not save) or (show is None and save is None):
             return plt.gca()
 
+        return None
+
     def plot_nhood_counts_by_cond(
         self,
         mdata: MuData,
@@ -976,14 +995,14 @@ class Milo:
         return_fig: bool | None = None,
         save: bool | str | None = None,
         show: bool | None = None,
-    ) -> None:
+    ) -> Figure | Axes | None:
         """Plot boxplot of cell numbers vs condition of interest.
 
         Args:
             mdata: MuData object storing cell level and nhood level information
             test_var: Name of column in adata.obs storing condition of interest (y-axis for boxplot)
-            subset_nhoods: List of obs_names for neighbourhoods to include in plot. If None, plot all nhoods. Defaults to None.
-            log_counts: Whether to plot log1p of cell counts. Defaults to False.
+            subset_nhoods: List of obs_names for neighbourhoods to include in plot. If None, plot all nhoods.
+            log_counts: Whether to plot log1p of cell counts.
         """
         try:
             nhood_adata = mdata["milo"].T.copy()
@@ -1014,9 +1033,13 @@ class Milo:
 
         if save:
             plt.savefig(save, bbox_inches="tight")
+            return None
         if show:
             plt.show()
+            return None
         if return_fig:
             return plt.gcf()
         if not (show or save):
             return plt.gca()
+
+        return None

pertpy/tools/_mixscape.py

@@ -178,7 +178,7 @@ class Mixscape:
             split_by: Provide the column `.obs` if multiple biological replicates exist to calculate
                     the perturbation signature for every replicate separately.
             pval_cutoff: P-value cut-off for selection of significantly DE genes.
-            perturbation_type: specify type of CRISPR perturbation expected for labeling mixscape classifications. Defaults to KO.
+            perturbation_type: specify type of CRISPR perturbation expected for labeling mixscape classifications.
             copy: Determines whether a copy of the `adata` is returned.
 
         Returns:
@@ -227,7 +227,7 @@ class Mixscape:
                 X = adata_comp.layers["X_pert"]
             except KeyError:
                 raise KeyError(
-                    "No 'X_pert' found in .layers! Please run pert_sign first to calculate perturbation signature!"
+                    "No 'X_pert' found in .layers! Please run perturbation_signature first to calculate perturbation signature!"
                 ) from None
         # initialize return variables
         adata.obs[f"{new_class_name}_p_{perturbation_type.lower()}"] = 0
@@ -315,7 +315,9 @@ class Mixscape:
                     )
 
                 adata.obs[f"{new_class_name}_global"] = [a.split(" ")[-1] for a in adata.obs[new_class_name]]
-                adata.obs.loc[orig_guide_cells_index, f"{new_class_name}_p_{perturbation_type.lower()}"] = post_prob
+                adata.obs.loc[orig_guide_cells_index, f"{new_class_name}_p_{perturbation_type.lower()}"] = np.round(
+                    post_prob
+                ).astype("int64")
         adata.uns["mixscape"] = gv_list
 
         if copy:
@@ -344,15 +346,13 @@ class Mixscape:
             control: Control category from the `pert_key` column.
             mixscape_class_global: The column of `.obs` with mixscape global classification result (perturbed, NP or NT).
             layer: Key from `adata.layers` whose value will be used to perform tests on.
-            control: Control category from the `pert_key` column. Defaults to 'NT'.
-            n_comps: Number of principal components to use. Defaults to 10.
+            control: Control category from the `pert_key` column.
+            n_comps: Number of principal components to use.
             min_de_genes: Required number of genes that are differentially expressed for method to separate perturbed and non-perturbed cells.
             logfc_threshold: Limit testing to genes which show, on average, at least X-fold difference (log-scale) between the two groups of cells.
-                             Defaults to 0.25.
             split_by: Provide the column `.obs` if multiple biological replicates exist to calculate
             pval_cutoff: P-value cut-off for selection of significantly DE genes.
             perturbation_type: Specify type of CRISPR perturbation expected for labeling mixscape classifications.
-                               Defaults to KO.
             copy: Determines whether a copy of the `adata` is returned.
 
         Returns:
@@ -461,7 +461,13 @@ class Mixscape:
             adata_split = adata[split_mask].copy()
             # find top DE genes between cells with targeting and non-targeting gRNAs
             sc.tl.rank_genes_groups(
-                adata_split, layer=layer, groupby=labels, groups=genes, reference=control, method="t-test"
+                adata_split,
+                layer=layer,
+                groupby=labels,
+                groups=genes,
+                reference=control,
+                method="t-test",
+                use_raw=False,
             )
             # get DE genes for each gene
             for gene in genes:
@@ -704,7 +710,6 @@ class Mixscape:
             before_mixscape: Option to split densities based on mixscape classification (default) or original target gene classification.
                              Default is set to NULL and plots cells by original class ID.
             perturbation_type: Specify type of CRISPR perturbation expected for labeling mixscape classifications.
-                               Defaults to `KO`.
 
         Examples:
             Visualizing the perturbation scores for the cells in a dataset:
@@ -881,7 +886,7 @@ class Mixscape:
             keys: Keys for accessing variables of `.var_names` or fields of `.obs`. Default is 'mixscape_class_p_ko'.
             groupby: The key of the observation grouping to consider. Default is 'mixscape_class'.
             log: Plot on logarithmic axis.
-            use_raw: Whether to use `raw` attribute of `adata`. Defaults to `True` if `.raw` is present.
+            use_raw: Whether to use `raw` attribute of `adata`.
             stripplot: Add a stripplot on top of the violin plot.
             order: Order in which to show the categories.
             xlabel: Label of the x-axis. Defaults to `groupby` if `rotation` is `None`, otherwise, no label is shown.
@@ -1075,7 +1080,6 @@ class Mixscape:
             mixscape_class: The column of `.obs` with the mixscape classification result.
             mixscape_class_global: The column of `.obs` with mixscape global classification result (perturbed, NP or NT).
             perturbation_type: Specify type of CRISPR perturbation expected for labeling mixscape classifications.
-                               Defaults to 'KO'.
             lda_key: If not specified, lda looks .uns["mixscape_lda"] for the LDA results.
             n_components: The number of dimensions of the embedding.
             show: Show the plot, do not return axis.

pertpy/tools/_perturbation_space/_clustering.py

@@ -7,6 +7,8 @@ from sklearn.metrics import pairwise_distances
 from pertpy.tools._perturbation_space._perturbation_space import PerturbationSpace
 
 if TYPE_CHECKING:
+    from collections.abc import Iterable
+
     from anndata import AnnData
 
 
@@ -14,6 +16,7 @@ class ClusteringSpace(PerturbationSpace):
     """Applies various clustering techniques to an embedding."""
 
     def __init__(self):
+        super().__init__()
         self.X = None
 
     def evaluate_clustering(
@@ -21,7 +24,7 @@ class ClusteringSpace(PerturbationSpace):
         adata: AnnData,
         true_label_col: str,
         cluster_col: str,
-        metrics: list[str] = None,
+        metrics: Iterable[str] = None,
         **kwargs,
     ):
         """Evaluation of previously computed clustering against ground truth labels.
@@ -30,7 +33,7 @@ class ClusteringSpace(PerturbationSpace):
             adata: AnnData object that contains the clustered data and the cluster labels.
             true_label_col: ground truth labels.
             cluster_col: cluster computed labels.
-            metrics: Metrics to compute. Defaults to ['nmi', 'ari', 'asw'].
+            metrics: Metrics to compute. If `None` it defaults to ["nmi", "ari", "asw"].
             **kwargs: Additional arguments to pass to the metrics. For nmi, average_method can be passed.
                 For asw, metric, distances, sample_size, and random_state can be passed.