gengeneeval 0.4.0__tar.gz → 0.4.1__tar.gz

{gengeneeval-0.4.0 → gengeneeval-0.4.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: gengeneeval
-Version: 0.4.0
+Version: 0.4.1
 Summary: Comprehensive evaluation of generated gene expression data. Computes metrics between real and generated datasets with support for condition matching, DEG-focused evaluation, per-context analysis, train/test splits, memory-efficient lazy loading, CPU parallelization, GPU acceleration, and publication-quality visualizations.
 License: MIT
 License-File: LICENSE
@@ -256,6 +256,8 @@ GenEval supports **Differentially Expressed Genes (DEG)-focused evaluation**, co
 #### Key Features
 
 - **Fast DEG detection**: Vectorized Welch's t-test, Student's t-test, or Wilcoxon rank-sum
+- **DEG vs all-genes comparison**: Compute metrics on both and compare
+- **Flexible DEG selection**: Top N by significance, or threshold-based filtering
 - **Per-context evaluation**: Automatically evaluates each (covariate × perturbation) combination
 - **GPU acceleration**: DEG detection and metrics on GPU for large datasets
 - **Comprehensive reporting**: Aggregated and expanded results with visualizations
@@ -266,7 +268,7 @@ GenEval supports **Differentially Expressed Genes (DEG)-focused evaluation**, co
 from geneval import evaluate_degs
 import pandas as pd
 
-# Evaluate with DEG-focused metrics
+# Evaluate with DEG-focused metrics (computes both DEG and all-genes by default)
 results = evaluate_degs(
     real_data=real_adata.X,           # (n_samples, n_genes)
     generated_data=gen_adata.X,
@@ -276,29 +278,62 @@ results = evaluate_degs(
     control_key="control",            # Value indicating control samples
     perturbation_column="perturbation",
     deg_method="welch",               # or "student", "wilcoxon", "logfc"
-    pval_threshold=0.05,
+    pval_threshold=0.05,              # Significance threshold
     lfc_threshold=0.5,                # log2 fold change threshold
+    compute_all_genes=True,           # Also compute metrics on all genes
     device="cuda",                    # GPU acceleration
 )
 
-# Access results
-print(results.aggregated_metrics)     # Summary across all contexts
-print(results.expanded_metrics)       # Per-context metrics
+# Compare DEG-only vs all-genes metrics
+print(results.comparison_summary)
+#        metric  deg_mean  all_mean  difference  ratio
+# wasserstein_1     5.34      0.69        4.65   7.74
+#           mmd     1.14      0.13        1.02   9.00
+
+# Access per-context results
+print(results.expanded_metrics)       # Has deg_* and all_* columns
 print(results.deg_summary)            # DEG counts per context
 
 # Save results with plots
 results.save("deg_evaluation/")
 ```
 
+#### DEG Selection Control
+
+```python
+# Option 1: Top N most significant DEGs
+results = evaluate_degs(
+    ...,
+    n_top_degs=50,      # Use only top 50 DEGs by adjusted p-value
+)
+
+# Option 2: Stricter thresholds
+results = evaluate_degs(
+    ...,
+    pval_threshold=0.01,    # More stringent p-value
+    lfc_threshold=1.0,      # 2-fold change minimum
+)
+
+# Option 3: DEGs only (skip all-genes metrics for speed)
+results = evaluate_degs(
+    ...,
+    compute_all_genes=False,
+)
+
+# Get DEG-only or all-genes metrics separately
+deg_only = results.get_deg_only_metrics()
+all_genes = results.get_all_genes_metrics()
+```
+
 #### Per-Context Evaluation
 
 When multiple condition columns are provided (e.g., `["cell_type", "perturbation"]`), GenEval evaluates **every combination** separately:
 
-| Context | n_DEGs | W1 (DEGs only) | MMD (DEGs only) |
-|---------|--------|----------------|-----------------|
-| TypeA_drug1 | 234 | 0.42 | 0.031 |
-| TypeA_drug2 | 189 | 0.38 | 0.027 |
-| TypeB_drug1 | 312 | 0.51 | 0.045 |
+| Context | n_DEGs | deg_W1 | all_W1 | deg_MMD | all_MMD |
+|---------|--------|--------|--------|---------|---------|
+| TypeA_drug1 | 234 | 5.42 | 0.69 | 1.03 | 0.13 |
+| TypeA_drug2 | 189 | 4.38 | 0.71 | 0.92 | 0.12 |
+| TypeB_drug1 | 312 | 6.51 | 0.68 | 1.21 | 0.14 |
 
 If only `perturbation` column is provided, evaluation is done per-perturbation.
 

{gengeneeval-0.4.0 → gengeneeval-0.4.1}/README.md

@@ -216,6 +216,8 @@ GenEval supports **Differentially Expressed Genes (DEG)-focused evaluation**, co
 #### Key Features
 
 - **Fast DEG detection**: Vectorized Welch's t-test, Student's t-test, or Wilcoxon rank-sum
+- **DEG vs all-genes comparison**: Compute metrics on both and compare
+- **Flexible DEG selection**: Top N by significance, or threshold-based filtering
 - **Per-context evaluation**: Automatically evaluates each (covariate × perturbation) combination
 - **GPU acceleration**: DEG detection and metrics on GPU for large datasets
 - **Comprehensive reporting**: Aggregated and expanded results with visualizations
@@ -226,7 +228,7 @@ GenEval supports **Differentially Expressed Genes (DEG)-focused evaluation**, co
 from geneval import evaluate_degs
 import pandas as pd
 
-# Evaluate with DEG-focused metrics
+# Evaluate with DEG-focused metrics (computes both DEG and all-genes by default)
 results = evaluate_degs(
     real_data=real_adata.X,           # (n_samples, n_genes)
     generated_data=gen_adata.X,
@@ -236,29 +238,62 @@ results = evaluate_degs(
     control_key="control",            # Value indicating control samples
     perturbation_column="perturbation",
     deg_method="welch",               # or "student", "wilcoxon", "logfc"
-    pval_threshold=0.05,
+    pval_threshold=0.05,              # Significance threshold
     lfc_threshold=0.5,                # log2 fold change threshold
+    compute_all_genes=True,           # Also compute metrics on all genes
     device="cuda",                    # GPU acceleration
 )
 
-# Access results
-print(results.aggregated_metrics)     # Summary across all contexts
-print(results.expanded_metrics)       # Per-context metrics
+# Compare DEG-only vs all-genes metrics
+print(results.comparison_summary)
+#        metric  deg_mean  all_mean  difference  ratio
+# wasserstein_1     5.34      0.69        4.65   7.74
+#           mmd     1.14      0.13        1.02   9.00
+
+# Access per-context results
+print(results.expanded_metrics)       # Has deg_* and all_* columns
 print(results.deg_summary)            # DEG counts per context
 
 # Save results with plots
 results.save("deg_evaluation/")
 ```
 
+#### DEG Selection Control
+
+```python
+# Option 1: Top N most significant DEGs
+results = evaluate_degs(
+    ...,
+    n_top_degs=50,      # Use only top 50 DEGs by adjusted p-value
+)
+
+# Option 2: Stricter thresholds
+results = evaluate_degs(
+    ...,
+    pval_threshold=0.01,    # More stringent p-value
+    lfc_threshold=1.0,      # 2-fold change minimum
+)
+
+# Option 3: DEGs only (skip all-genes metrics for speed)
+results = evaluate_degs(
+    ...,
+    compute_all_genes=False,
+)
+
+# Get DEG-only or all-genes metrics separately
+deg_only = results.get_deg_only_metrics()
+all_genes = results.get_all_genes_metrics()
+```
+
 #### Per-Context Evaluation
 
 When multiple condition columns are provided (e.g., `["cell_type", "perturbation"]`), GenEval evaluates **every combination** separately:
 
-| Context | n_DEGs | W1 (DEGs only) | MMD (DEGs only) |
-|---------|--------|----------------|-----------------|
-| TypeA_drug1 | 234 | 0.42 | 0.031 |
-| TypeA_drug2 | 189 | 0.38 | 0.027 |
-| TypeB_drug1 | 312 | 0.51 | 0.045 |
+| Context | n_DEGs | deg_W1 | all_W1 | deg_MMD | all_MMD |
+|---------|--------|--------|--------|---------|---------|
+| TypeA_drug1 | 234 | 5.42 | 0.69 | 1.03 | 0.13 |
+| TypeA_drug2 | 189 | 4.38 | 0.71 | 0.92 | 0.12 |
+| TypeB_drug1 | 312 | 6.51 | 0.68 | 1.21 | 0.14 |
 
 If only `perturbation` column is provided, evaluation is done per-perturbation.
 

{gengeneeval-0.4.0 → gengeneeval-0.4.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "gengeneeval"
-version = "0.4.0"
+version = "0.4.1"
 description = "Comprehensive evaluation of generated gene expression data. Computes metrics between real and generated datasets with support for condition matching, DEG-focused evaluation, per-context analysis, train/test splits, memory-efficient lazy loading, CPU parallelization, GPU acceleration, and publication-quality visualizations."
 authors = ["GenEval Team <geneval@example.com>"]
 license = "MIT"

{gengeneeval-0.4.0 → gengeneeval-0.4.1}/src/geneval/__init__.py

@@ -49,7 +49,7 @@ CLI Usage:
               --conditions perturbation cell_type --output results/
 """
 
-__version__ = "0.4.0"
+__version__ = "0.4.1"
 __author__ = "GenEval Team"
 
 # Main evaluation interface

{gengeneeval-0.4.0 → gengeneeval-0.4.1}/src/geneval/deg/__init__.py

@@ -31,6 +31,8 @@ from .context import (
 from .evaluator import (
     DEGEvaluator,
     DEGEvaluationResult,
+    DEGSettings,
+    ContextMetrics,
     evaluate_degs,
 )
 from .visualization import (
@@ -56,6 +58,8 @@ __all__ = [
     # Evaluator
     "DEGEvaluator",
     "DEGEvaluationResult",
+    "DEGSettings",
+    "ContextMetrics",
     "evaluate_degs",
     # Visualization
     "plot_deg_distributions",