Add two distance metrics, three-way comparison and bootstrapping

pertpy/tools/__init__.py

@@ -3,18 +3,31 @@
 from pertpy.tools._coda._sccoda import Sccoda
 from pertpy.tools._coda._tasccoda import Tasccoda
 from pertpy.tools._dialogue import Dialogue
-from pertpy.tools._differential_gene_expression import EdgeR, PyDESeq2, Statsmodels, TTest, WilcoxonTest
+from pertpy.tools._differential_gene_expression import (
+ DGEEVAL,
+ EdgeR,
+ PyDESeq2,
+ Statsmodels,
+ TTest,
+ WilcoxonTest,
+)
 from pertpy.tools._distances._distance_tests import DistanceTest
 from pertpy.tools._distances._distances import Distance
 from pertpy.tools._enrichment import Enrichment
 from pertpy.tools._milo import Milo
 from pertpy.tools._mixscape import Mixscape
 from pertpy.tools._perturbation_space._clustering import ClusteringSpace
+from pertpy.tools._perturbation_space._comparison import PerturbationComparison
 from pertpy.tools._perturbation_space._discriminator_classifiers import (
  LRClassifierSpace,
  MLPClassifierSpace,
 )
-from pertpy.tools._perturbation_space._simple import CentroidSpace, DBSCANSpace, KMeansSpace, PseudobulkSpace
+from pertpy.tools._perturbation_space._simple import (
+ CentroidSpace,
+ DBSCANSpace,
+ KMeansSpace,
+ PseudobulkSpace,
+)
 from pertpy.tools._scgen import Scgen
 
 __all__ = [

pertpy/tools/_differential_gene_expression/__init__.py

@@ -1,4 +1,5 @@
 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

pertpy/tools/_differential_gene_expression/_dge_comparison.py

@@ -0,0 +1,86 @@
+import numpy as np
+import pandas as pd
+from anndata import AnnData
+
+
+class DGEEVAL:
+ def compare(
+ self,
+ adata: AnnData | None = None,
+ de_key1: str = None,
+ de_key2: str = None,
+ de_df1: pd.DataFrame | None = None,
+ de_df2: pd.DataFrame | None = None,
+ shared_top: int = 100,
+ ) -> dict[str, float]:
+ """Compare two differential expression analyses.
+
+ Compare two sets of DE results and evaluate the similarity by the overlap of top DEG and
+ the correlation of their scores and adjusted p-values.
+
+ Args:
+ adata: AnnData object containing DE results in `uns`. Required if `de_key1` and `de_key2` are used.
+ de_key1: Key for DE results in `adata.uns`, e.g., output of `tl.rank_genes_groups`.
+ de_key2: Another key for DE results in `adata.uns`, e.g., output of `tl.rank_genes_groups`.
+ de_df1: DataFrame containing DE results, e.g. output from pertpy differential gene expression interface.
+ de_df2: DataFrame containing DE results, e.g. output from pertpy differential gene expression interface.
+ shared_top: The number of top DEG to compute the proportion of their intersection.
+
+ """
+ if (de_key1 or de_key2) and (de_df1 is not None or de_df2 is not None):
+ raise ValueError(
+ "Please provide either both `de_key1` and `de_key2` with `adata`, or `de_df1` and `de_df2`, but not both."
+ )
+
+ if de_df1 is None and de_df2 is None: # use keys
+ if not de_key1 or not de_key2:
+ raise ValueError("Both `de_key1` and `de_key2` must be provided together if using `adata`.")
+
+ else: # use dfs
+ if de_df1 is None or de_df2 is None:
+ raise ValueError("Both `de_df1` and `de_df2` must be provided together if using DataFrames.")
+
+ if de_key1:
+ if not adata:
+ raise ValueError("`adata` should be provided with `de_key1` and `de_key2`. ")
+ assert all(
+ k in adata.uns for k in [de_key1, de_key2]
+ ), "Provided `de_key1` and `de_key2` must exist in `adata.uns`."
+ vars = adata.var_names
+
+ if de_df1 is not None:
+ for df in (de_df1, de_df2):
+ if not {"variable", "log_fc", "adj_p_value"}.issubset(df.columns):
+ raise ValueError("Each DataFrame must contain columns: 'variable', 'log_fc', and 'adj_p_value'.")
+
+ assert set(de_df1["variable"]) == set(de_df2["variable"]), "Variables in both dataframes must match."
+ vars = de_df1["variable"].sort_values()
+
+ shared_top = min(shared_top, len(vars))
+ vars_ranks = np.arange(1, len(vars) + 1)
+ results = pd.DataFrame(index=vars)
+ top_names = []
+
+ if de_key1 and de_key2:
+ for i, k in enumerate([de_key1, de_key2]):
+ label = adata.uns[k]["names"].dtype.names[0]
+ srt_idx = np.argsort(adata.uns[k]["names"][label])
+ results[f"scores_{i}"] = adata.uns[k]["scores"][label][srt_idx]
+ results[f"pvals_adj_{i}"] = adata.uns[k]["pvals_adj"][label][srt_idx]
+ results[f"ranks_{i}"] = vars_ranks[srt_idx]
+ top_names.append(adata.uns[k]["names"][label][:shared_top])
+ else:
+ for i, df in enumerate([de_df1, de_df2]):
+ srt_idx = np.argsort(df["variable"])
+ results[f"scores_{i}"] = df["log_fc"].values[srt_idx]
+ results[f"pvals_adj_{i}"] = df["adj_p_value"].values[srt_idx]
+ results[f"ranks_{i}"] = vars_ranks[srt_idx]
+ top_names.append(df["variable"][:shared_top])
+
+ metrics = {}
+ metrics["shared_top_genes"] = len(set(top_names[0]).intersection(top_names[1])) / shared_top
+ metrics["scores_corr"] = results["scores_0"].corr(results["scores_1"], method="pearson")
+ metrics["pvals_adj_corr"] = results["pvals_adj_0"].corr(results["pvals_adj_1"], method="pearson")
+ metrics["scores_ranks_corr"] = results["ranks_0"].corr(results["ranks_1"], method="spearman")
+
+ return metrics

pertpy/tools/_distances/_distance_tests.py

@@ -66,11 +66,14 @@ def __init__(
  self.alpha = alpha
  self.correction = correction
  self.cell_wise_metric = (
- cell_wise_metric if cell_wise_metric else Distance(self.metric, self.obsm_key).cell_wise_metric
+ cell_wise_metric if cell_wise_metric else Distance(self.metric, obsm_key=self.obsm_key).cell_wise_metric
  )
 
  self.distance = Distance(
- self.metric, layer_key=self.layer_key, obsm_key=self.obsm_key, cell_wise_metric=self.cell_wise_metric
+ self.metric,
+ layer_key=self.layer_key,
+ obsm_key=self.obsm_key,
+ cell_wise_metric=self.cell_wise_metric,
  )
 
  def __call__(
@@ -176,7 +179,8 @@ def test_xy(self, adata: AnnData, groupby: str, contrast: str, show_progressbar:
  # Evaluate the test
  # count times shuffling resulted in larger distance
  comparison_results = np.array(
- pd.concat([r["distance"] - df["distance"] for r in results], axis=1) > 0, dtype=int
+ pd.concat([r["distance"] - df["distance"] for r in results], axis=1) > 0,
+ dtype=int,
  )
  n_failures = pd.Series(np.clip(np.sum(comparison_results, axis=1), 1, np.inf), index=df.index)
  pvalues = n_failures / self.n_perms
@@ -284,7 +288,8 @@ def test_precomputed(self, adata: AnnData, groupby: str, contrast: str, verbose:
  # Evaluate the test
  # count times shuffling resulted in larger distance
  comparison_results = np.array(
- pd.concat([r["distance"] - df["distance"] for r in results], axis=1) > 0, dtype=int
+ pd.concat([r["distance"] - df["distance"] for r in results], axis=1) > 0,
+ dtype=int,
  )
  n_failures = pd.Series(np.clip(np.sum(comparison_results, axis=1), 1, np.inf), index=df.index)
  pvalues = n_failures / self.n_perms