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

pertpy/tools/_coda/_tasccoda.py

@@ -10,9 +10,9 @@ import numpyro.distributions as npd
 import toytree as tt
 from anndata import AnnData
 from jax import config, random
+from lamin_utils import logger
 from mudata import MuData
 from numpyro.infer import Predictive
-from rich import print
 
 from pertpy.tools._coda._base_coda import (
     CompositionalModel2,
@@ -85,18 +85,18 @@ class Tasccoda(CompositionalModel2):
         Args:
             adata: AnnData object.
             type: Specify the input adata type, which could be either a cell-level AnnData or an aggregated sample-level AnnData.
-            cell_type_identifier: If type is "cell_level", specify column name in adata.obs that specifies the cell types. Defaults to None.
-            sample_identifier: If type is "cell_level", specify column name in adata.obs that specifies the sample. Defaults to None.
-            covariate_uns: If type is "cell_level", specify key for adata.uns, where covariate values are stored. Defaults to None.
-            covariate_obs: If type is "cell_level", specify list of keys for adata.obs, where covariate values are stored. Defaults to None.
-            covariate_df: If type is "cell_level", specify dataFrame with covariates. Defaults to None.
-            dendrogram_key: Key to the scanpy.tl.dendrogram result in `.uns` of original cell level anndata object. Defaults to None.
-            levels_orig: List that indicates which columns in `.obs` of the original data correspond to tree levels. The list must begin with the root level, and end with the leaf level. Defaults to None.
-            levels_agg: List that indicates which columns in `.var` of the aggregated data correspond to tree levels. The list must begin with the root level, and end with the leaf level. Defaults to None.
-            add_level_name: If True, internal nodes in the tree will be named as "{level_name}_{node_name}" instead of just {level_name}. Defaults to False.
-            key_added: If not specified, the tree is stored in .uns[‘tree’]. If `data` is AnnData, save tree in `data`. If `data` is MuData, save tree in data[modality_2]. Defaults to "tree".
-            modality_key_1: Key to the cell-level AnnData in the MuData object. Defaults to "rna".
-            modality_key_2: Key to the aggregated sample-level AnnData object in the MuData object. Defaults to "coda".
+            cell_type_identifier: If type is "cell_level", specify column name in adata.obs that specifies the cell types.
+            sample_identifier: If type is "cell_level", specify column name in adata.obs that specifies the sample.
+            covariate_uns: If type is "cell_level", specify key for adata.uns, where covariate values are stored.
+            covariate_obs: If type is "cell_level", specify list of keys for adata.obs, where covariate values are stored.
+            covariate_df: If type is "cell_level", specify dataFrame with covariates.
+            dendrogram_key: Key to the scanpy.tl.dendrogram result in `.uns` of original cell level anndata object.
+            levels_orig: List that indicates which columns in `.obs` of the original data correspond to tree levels. The list must begin with the root level, and end with the leaf level.
+            levels_agg: List that indicates which columns in `.var` of the aggregated data correspond to tree levels. The list must begin with the root level, and end with the leaf level.
+            add_level_name: If True, internal nodes in the tree will be named as "{level_name}_{node_name}" instead of just {level_name}.
+            key_added: If not specified, the tree is stored in .uns[‘tree’]. If `data` is AnnData, save tree in `data`. If `data` is MuData, save tree in data[modality_2].
+            modality_key_1: Key to the cell-level AnnData in the MuData object.
+            modality_key_2: Key to the aggregated sample-level AnnData object in the MuData object.
 
         Returns:
             MuData: MuData object with cell-level AnnData (`mudata[modality_key_1]`) and aggregated sample-level AnnData (`mudata[modality_key_2]`).
@@ -155,14 +155,13 @@ class Tasccoda(CompositionalModel2):
                      To set a different level as the base category for a categorical covariate, use "C(<CovariateName>, Treatment('<ReferenceLevelName>'))"
             reference_cell_type: Column name that sets the reference cell type.
                                  If "automatic", the cell type with the lowest dispersion in relative abundance that is present in at least 90% of samlpes will be chosen.
-                                 Defaults to "automatic".
             automatic_reference_absence_threshold: If using reference_cell_type = "automatic",
                                                    determine the maximum fraction of zero entries for a cell type
-                                                   to be considered as a possible reference cell type. Defaults to 0.05.
+                                                   to be considered as a possible reference cell type.
             tree_key: Key in `adata.uns` that contains the tree structure
             pen_args: Dictionary with penalty arguments. With `reg="scaled_3"`, the parameters phi (aggregation bias), lambda_1, lambda_0 can be set here.
                 See the tascCODA paper for an explanation of these parameters. Default: lambda_0 = 50, lambda_1 = 5, phi = 0.
-            modality_key: If data is a MuData object, specify key to the aggregated sample-level AnnData object in the MuData object. Defaults to "coda".
+            modality_key: If data is a MuData object, specify key to the aggregated sample-level AnnData object in the MuData object.
 
         Returns:
             Return an AnnData (if input data is an AnnData object) or return a MuData (if input data is a MuData object)
@@ -208,7 +207,7 @@ class Tasccoda(CompositionalModel2):
             ) from None
 
         # toytree tree - only for legacy reasons, can be removed in the final version
-        if isinstance(adata.uns[tree_key], tt.tree):
+        if isinstance(adata.uns[tree_key], tt.core.ToyTree):
             # Collapse singularities in the tree
             phy_tree = collapse_singularities(adata.uns[tree_key])
 
@@ -477,10 +476,10 @@ class Tasccoda(CompositionalModel2):
 
         Args:
             data: AnnData object or MuData object.
-            modality_key: If data is a MuData object, specify which modality to use. Defaults to "coda".
-            rng_key: The rng state used for the prior simulation. If None, a random state will be selected. Defaults to None.
-            num_prior_samples: Number of prior samples calculated. Defaults to 500.
-            use_posterior_predictive: If True, the posterior predictive will be calculated. Defaults to True.
+            modality_key: If data is a MuData object, specify which modality to use.
+            rng_key: The rng state used for the prior simulation. If None, a random state will be selected.
+            num_prior_samples: Number of prior samples calculated.
+            use_posterior_predictive: If True, the posterior predictive will be calculated.
 
         Returns:
             arviz.InferenceData: arviz_data
@@ -504,7 +503,7 @@ class Tasccoda(CompositionalModel2):
             try:
                 sample_adata = data[modality_key]
             except IndexError:
-                print("When data is a MuData object, modality_key must be specified!")
+                logger.error("When data is a MuData object, modality_key must be specified!")
                 raise
         if isinstance(data, AnnData):
             sample_adata = data

pertpy/tools/_dialogue.py

@@ -13,8 +13,8 @@ import seaborn as sns
 import statsmodels.formula.api as smf
 import statsmodels.stats.multitest as ssm
 from anndata import AnnData
+from lamin_utils import logger
 from pandas import DataFrame
-from rich import print
 from rich.console import Group
 from rich.live import Live
 from rich.progress import BarColumn, Progress, SpinnerColumn, TaskProgressColumn, TextColumn
@@ -291,7 +291,7 @@ class Dialogue:
             mcp_name: Name of mcp which was used for calculation of column value.
             max_length: Value needed to later decide at what index the threshold value should be extracted from column.
             min_threshold: Minimal threshold to select final scores by if it is smaller than calculated threshold.
-            index: Column index to use eto calculate the significant genes. Defaults to `z_score`.
+            index: Column index to use eto calculate the significant genes.
 
         Returns:
             According to the values in a df column (default: zscore) the significant up and downregulated gene names
@@ -377,12 +377,6 @@ class Dialogue:
 
             `argmin|Ax - y|`
 
-        Args:
-            A_orig:
-            y_orig:
-            feature_ranks:
-            n_iter: Passed to scipy.optimize.nnls. Defaults to 1000.
-
         Returns:
             Returns the aggregated coefficients from nnls.
         """
@@ -572,8 +566,8 @@ class Dialogue:
         Args:
             adata: AnnData object generate celltype objects for
             ct_order: The order of cell types
-            agg_pca: Whether to aggregate pseudobulks with PCA or not. Defaults to True.
-            normalize: Whether to mimic DIALOGUE behavior or not. Defaults to True.
+            agg_pca: Whether to aggregate pseudobulks with PCA or not.
+            normalize: Whether to mimic DIALOGUE behavior or not.
 
         Returns:
             A celltype_label:array dictionary.
@@ -613,7 +607,6 @@ class Dialogue:
             agg_pca: Whether to calculate cell-averaged PCA components.
             solver: Which solver to use for PMD. Must be one of "lp" (linear programming) or "bs" (binary search).
                     For differences between these to please refer to https://github.com/theislab/sparsecca/blob/main/examples/linear_programming_multicca.ipynb
-                    Defaults to 'bs'.
             normalize: Whether to mimic DIALOGUE as close as possible
 
         Returns:
@@ -640,9 +633,15 @@ class Dialogue:
 
         n_samples = mcca_in[0].shape[1]
         if penalties is None:
-            penalties = multicca_permute(
-                mcca_in, penalties=np.sqrt(n_samples) / 2, nperms=10, niter=50, standardize=True
-            )["bestpenalties"]
+            try:
+                penalties = multicca_permute(
+                    mcca_in, penalties=np.sqrt(n_samples) / 2, nperms=10, niter=50, standardize=True
+                )["bestpenalties"]
+            except ValueError as e:
+                if "matmul: input operand 1 has a mismatch in its core dimension" in str(e):
+                    raise ValueError("Please ensure that every cell type is represented in every sample.") from e
+                else:
+                    raise
         else:
             penalties = penalties
 
@@ -756,10 +755,10 @@ class Dialogue:
                         mcps.append(mcp)
 
                 if len(mcps) == 0:
-                    print(f"[bold red]No shared MCPs between {cell_type_1} and {cell_type_2}.")
+                    logger.warning(f"No shared MCPs between {cell_type_1} and {cell_type_2}.")
                     continue
 
-                print(f"[bold blue]{len(mcps)} MCPs identified for {cell_type_1} and {cell_type_2}.")
+                logger.info(f"{len(mcps)} MCPs identified for {cell_type_1} and {cell_type_2}.")
 
                 new_mcp_scores: dict[Any, list[Any]]
                 cca_sig, new_mcp_scores = self._calculate_cca_sig(
@@ -912,9 +911,7 @@ class Dialogue:
             results: dl.MultilevelModeling result object.
             MCP: MCP key of the result object.
             threshold: Number between [0,1]. The fraction of cell types compared against which must have the associated MCP gene.
-                        Defaults to 0.70.
             focal_celltypes: None (compare against all cell types) or a list of other cell types which you want to compare against.
-                             Defaults to None.
 
         Returns:
             Dict with keys 'up_genes' and 'down_genes' and values of lists of genes
@@ -993,10 +990,8 @@ class Dialogue:
         Args:
             ct_subs: Dialogue output ct_subs dictionary
             mcp: The name of the marker gene expression column.
-                 Defaults to "mcp_0".
             fraction: Fraction of extreme cells to consider for gene ranking.
                       Should be between 0 and 1.
-                      Defaults to 0.1.
 
         Returns:
             Dictionary where keys are subpopulation names and values are Anndata
@@ -1035,7 +1030,7 @@ class Dialogue:
         Args:
             ct_subs: Dialogue output ct_subs dictionary
             fraction: Fraction of extreme cells to consider for gene ranking.
-                      Should be between 0 and 1. Defaults to 0.1.
+                      Should be between 0 and 1.
 
         Returns:
             Nested dictionary where keys of the first level are MCPs (of the form "mcp_0" etc)
@@ -1085,7 +1080,7 @@ class Dialogue:
             split_key: Variable in adata.obs used to split the data.
             celltype_key: Key for cell type annotations.
             split_which: Which values of split_key to plot. Required if more than 2 values in split_key.
-            mcp: Key for MCP data. Defaults to "mcp_0".
+            mcp: Key for MCP data.
 
         Returns:
             A :class:`~matplotlib.axes.Axes` object
@@ -1144,7 +1139,7 @@ class Dialogue:
             celltype_key: Key in `adata.obs` containing cell type annotations.
             color: Key in `adata.obs` for color annotations. This parameter is used as the hue
             sample_id: Key in `adata.obs` for the sample annotations.
-            mcp: Key in `adata.obs` for MCP feature values. Defaults to `"mcp_0"`.
+            mcp: Key in `adata.obs` for MCP feature values.
 
         Returns:
             Seaborn Pairgrid object.

pertpy/tools/_differential_gene_expression/__init__.py

@@ -0,0 +1,20 @@
+from ._base import ContrastType, LinearModelBase, MethodBase
+from ._dge_comparison import DGEEVAL
+from ._edger import EdgeR
+from ._pydeseq2 import PyDESeq2
+from ._simple_tests import SimpleComparisonBase, TTest, WilcoxonTest
+from ._statsmodels import Statsmodels
+
+__all__ = [
+    "MethodBase",
+    "LinearModelBase",
+    "EdgeR",
+    "PyDESeq2",
+    "Statsmodels",
+    "SimpleComparisonBase",
+    "WilcoxonTest",
+    "TTest",
+    "ContrastType",
+]
+
+AVAILABLE_METHODS = [Statsmodels, EdgeR, PyDESeq2, WilcoxonTest, TTest]