pythonflex 0.3.4__py3-none-any.whl → 0.4__py3-none-any.whl

pythonflex/examples/basic_usage.py

@@ -7,33 +7,32 @@ import pythonflex as flex
 
 inputs = {
     "Melanoma (63 Screens)": {
-        "path": flex.get_example_data_path("melanoma_cell_lines_500_genes.csv"), 
+        "path": flex.get_example_data_path("melanoma_cell_lines_500_genes.csv"),
         "sort": "high",
-        "color": "#FF0000"
+        "color": "#4E79A7",
     },
     "Liver (24 Screens)": {
-        "path": flex.get_example_data_path("liver_cell_lines_500_genes.csv"), 
+        "path": flex.get_example_data_path("liver_cell_lines_500_genes.csv"),
         "sort": "high",
-        "color": "#FFDD00"
+        "color": "#F28E2B",
     },
     "Neuroblastoma (37 Screens)": {
-        "path": flex.get_example_data_path("neuroblastoma_cell_lines_500_genes.csv"), 
+        "path": flex.get_example_data_path("neuroblastoma_cell_lines_500_genes.csv"),
         "sort": "high",
-        "color": "#FFDDDD"
+        "color": "#59A14F",
     },
 }
 
 
 
 default_config = {
-    "min_genes_in_complex": 0,
-    "min_genes_per_complex_analysis": 3,
-    "output_folder": "CORUM",
-    "gold_standard": "CORUM",
-    "color_map": "BuGn",
+    "min_genes_in_complex": 2,
+    "min_genes_per_complex_analysis": 2,
+    "output_folder": "output_test",
+    "gold_standard": "GOBP",
+    "color_map": "RdYlBu",
     "jaccard": True,
-    "jaccard_threshold": 1,
-    "use_common_genes": False,  # Set to False for individual dataset-gold standard intersections
+    "analysis_genes": "shared",  # or "dataset_specific" (genes present per dataset)
     "plotting": {
         "save_plot": True,
         "output_type": "png",
@@ -42,9 +41,14 @@ default_config = {
         "fill_na": True,
         "normalize": False,
     },
-    "corr_function": "numpy",
+    "corr_function": "numpy_without_mask",
+    "per_complex": {
+        "n_jobs": 8,
+        "chunk_size": 400,
+        "max_nbytes": "100M",
+    },
     "logging": {  
-        "visible_levels": ["DONE"]  
+        "visible_levels": ["DONE", "INFO", "WARNING"]
         # "PROGRESS", "STARTED", ,"INFO","WARNING"
     }
 }
@@ -58,30 +62,34 @@ terms, genes_in_terms = flex.load_gold_standard()
 
 # Run analysis
 for name, dataset in data.items():
-    pra = flex.pra(name, dataset, is_corr=False)
-    fpc = flex.pra_percomplex(name, dataset, is_corr=False) 
+    # Calculate correlation once and reuse it for global and per-complex PRA.
+    corr = flex.perform_corr(dataset, default_config["corr_function"])
+    pra = flex.pra(name, corr, is_corr=True)
+    fpc = flex.pra_percomplex(name, corr, is_corr=True)
     cc = flex.complex_contributions(name)
-    flex.mpr_prepare(name)  
-    
-
 
+    # Optional mPR analysis. This can be slow on large datasets.
+    # flex.mpr_prepare(name)
+    
 
 
 #%%
 # Generate plots
-# flex.plot_precision_recall_curve()
-# flex.plot_auc_scores()
-# flex.plot_significant_complexes()
-# flex.plot_percomplex_scatter(n_top=20)
-# flex.plot_percomplex_scatter_bysize()
-# flex.plot_complex_contributions()
-# flex.plot_mpr_tp_multi(show_filters="all")
-# flex.plot_mpr_complexes_multi(show_filters="all")
-# flex.plot_mpr_complexes_auc_scores("all")
-
+flex.plot_precision_recall_curve()
+flex.plot_auc_scores()
+flex.plot_significant_complexes()
+#%%
+flex.plot_percomplex_scatter(n_top=10)
+flex.plot_percomplex_scatter_bysize(n_top=10)
+#flex.plot_complex_contributions()
 
+# Optional mPR summary plot. Requires flex.mpr_prepare(name) above.
+# flex.plot_mpr_summary(variants="unfiltered")
 
 #%%
 # Save results to CSV
 # flex.save_results_to_csv()
 
+#how many cpu I have?
+import multiprocessing
+print(f"Number of CPU cores available: {multiprocessing.cpu_count()}")

pythonflex/examples/manuscript.py

@@ -12,54 +12,43 @@ skin = pd.read_csv('C:/Users/yd/Desktop/projects/_datasets/depmap/25Q2/subset/sk
 
 soft = pd.read_csv('C:/Users/yd/Desktop/projects/_datasets/depmap/25Q2/subset/soft_tissue_cell_lines.csv', index_col=0)
 
-
 cholesky = pd.read_csv('C:/Users/yd/Desktop/projects/_datasets/depmap/25Q2/25Q2_chronos_whitened_Cholesky.csv', index_col=0).T
 
-# inputs = {
-#     "All Screens": {
-#         "path": gene_effect, 
-#         "sort": "high",
-#         "color": "#000000"
-#     },
-#     "Skin": {
-#         "path": skin, 
-#         "sort": "high",
-#         "color": "#FF0000"
-#     },
-#     "Soft Tissue": {
-#         "path": soft, 
-#         "sort": "high",
-#         "color": "#FFFF00"
-#     },
-# }
-
-
 inputs = {
-    "DM All Screens": {
+    "depmap": {
         "path": gene_effect, 
         "sort": "high",
         "color": "#000000"
     },
-    "DM Cholesky Whitening": {
-        "path": cholesky, 
+    # "cholesky": {
+    #     "path": cholesky, 
+    #     "sort": "high",
+    #     "color": "#000CF4"
+    # },
+    "Skin": {
+        "path": skin, 
         "sort": "high",
-        "color": "#FF0000"
+        "color": "#2E7D32"
+    },
+    "Soft Tissue": {
+        "path": soft, 
+        "sort": "high",
+        "color": "#7A8B00"
     },
-   
 }
 
 
 
 
+
 default_config = {
     "min_genes_in_complex": 2,
-    "min_genes_per_complex_analysis": 3,
-    "output_folder": "CORUM_DMvsCholesky",
+    "min_genes_per_complex_analysis": 2,
+    "output_folder": "for_paper_output_01062026_CORUM_dm_skin_soft",
     "gold_standard": "CORUM",
-    "color_map": "BuGn",
-    "jaccard": False,
-        "jaccard_threshold": 1.0,
-    "use_common_genes": False,  # Set to False for individual dataset-gold standard intersections
+    "color_map": "RdYlBu",
+    "jaccard": True,
+    "analysis_genes": "shared",  # or "dataset_specific" (genes present per dataset)
     "plotting": {
         "save_plot": True,
         "output_type": "pdf",
@@ -69,8 +58,13 @@ default_config = {
         "normalize": False,
     },
     "corr_function": "numpy",
+    "per_complex": {
+        "n_jobs": 8,
+        "chunk_size": 400,
+        "max_nbytes": "100M",
+    },
     "logging": {  
-        "visible_levels": ["DONE"]  
+        "visible_levels": ["DONE", "INFO", "WARNING"]
         # "PROGRESS", "STARTED", ,"INFO","WARNING"
     }
 }
@@ -84,12 +78,14 @@ terms, genes_in_terms = flex.load_gold_standard()
 
 # Run analysis
 for name, dataset in data.items():
-    pra = flex.pra(name, dataset, is_corr=False)
-    fpc = flex.pra_percomplex(name, dataset, is_corr=False) 
+    # Calculate correlation once and reuse it for global and per-complex PRA.
+    corr = flex.perform_corr(dataset, default_config["corr_function"])
+    pra = flex.pra(name, corr, is_corr=True)
+    fpc = flex.pra_percomplex(name, corr, is_corr=True)
     cc = flex.complex_contributions(name)
-    flex.mpr_prepare(name)  
-
-
+    # Optional mPR analysis. This can be slow on large datasets.
+    flex.mpr_prepare(name)
+    
 
 
 #%%
@@ -100,13 +96,11 @@ flex.plot_significant_complexes()
 flex.plot_percomplex_scatter(n_top=20)
 flex.plot_percomplex_scatter_bysize()
 flex.plot_complex_contributions()
-##
-#%%
-flex.plot_mpr_tp_multi(show_filters="all")
-flex.plot_mpr_complexes_multi(show_filters="all")
-
+# Optional mPR summary plot. Requires flex.mpr_prepare(name) above.
+flex.plot_mpr_summary(variants="unfiltered")
 # Save results to CSV
 flex.save_results_to_csv()
 
-# %%
+
+
 # %%

pythonflex/examples/runtime/runtime_benchmark.py

@@ -0,0 +1,218 @@
+"""Benchmark the manuscript workflow against each bundled gold standard.
+
+Run from any directory with:
+    python path/to/src/pythonflex/examples/runtime_benchmark.py
+"""
+
+from __future__ import annotations
+
+import os
+import sys
+from pathlib import Path
+from time import perf_counter
+from typing import Any, Callable
+
+import pandas as pd
+
+
+PROJECT_ROOT = Path(__file__).resolve().parents[3]
+SRC_ROOT = PROJECT_ROOT / "src"
+if str(SRC_ROOT) not in sys.path:
+    sys.path.insert(0, str(SRC_ROOT))
+
+# Plot generation is benchmarked and saved without opening interactive windows.
+os.environ.setdefault("MPLBACKEND", "Agg")
+
+import pythonflex as flex  # noqa: E402
+
+
+GENE_EFFECT_PATH = Path(
+    "C:/Users/yd/Desktop/projects/_datasets/depmap/25Q2/gene_effect.csv"
+)
+BENCHMARK_ROOT = PROJECT_ROOT / "output" / "runtime_benchmark"
+GOLD_STANDARDS = ("CORUM", "PATHWAY", "GOBP")
+
+
+def build_config(gold_standard: str, output_folder: Path) -> dict[str, Any]:
+    return {
+        "min_genes_in_complex": 2,
+        "min_genes_per_complex_analysis": 3,
+        "output_folder": str(output_folder),
+        "gold_standard": gold_standard,
+        "color_map": "RdYlBu",
+        "jaccard": True,
+        "analysis_genes": "common",
+        "plotting": {
+            "save_plot": True,
+            "show_plot": False,
+            "output_type": "png",
+        },
+        "preprocessing": {
+            "fill_na": True,
+            "normalize": False,
+        },
+        "corr_function": "numpy",
+        "logging": {
+            "visible_levels": ["DONE", "INFO", "WARNING"],
+        },
+    }
+
+
+def timed_call(
+    timings: list[dict[str, Any]],
+    gold_standard: str,
+    step: str,
+    operation: Callable[[], Any],
+) -> Any:
+    start = perf_counter()
+    result = operation()
+    timings.append(
+        {
+            "gold_standard": gold_standard,
+            "step": step,
+            "seconds": perf_counter() - start,
+        }
+    )
+    return result
+
+
+def run_gold_standard(gold_standard: str) -> list[dict[str, Any]]:
+    output_folder = BENCHMARK_ROOT / gold_standard
+    timings: list[dict[str, Any]] = []
+    workflow_start = perf_counter()
+
+    timed_call(
+        timings,
+        gold_standard,
+        "initialize",
+        lambda: flex.initialize(build_config(gold_standard, output_folder)),
+    )
+    gene_effect = timed_call(
+        timings,
+        gold_standard,
+        "read_gene_effect",
+        lambda: pd.read_csv(GENE_EFFECT_PATH, index_col=0),
+    )
+    inputs = {
+        "All screens": {
+            "path": gene_effect,
+            "sort": "high",
+            "color": "#000000",
+        },
+    }
+    data, _ = timed_call(
+        timings,
+        gold_standard,
+        "load_datasets",
+        lambda: flex.load_datasets(inputs),
+    )
+    timed_call(
+        timings,
+        gold_standard,
+        "load_gold_standard",
+        flex.load_gold_standard,
+    )
+
+    name, dataset = next(iter(data.items()))
+    timed_call(
+        timings,
+        gold_standard,
+        "pra",
+        lambda: flex.pra(name, dataset, is_corr=False),
+    )
+    timed_call(
+        timings,
+        gold_standard,
+        "pra_percomplex",
+        lambda: flex.pra_percomplex(name, dataset, is_corr=False),
+    )
+    timed_call(
+        timings,
+        gold_standard,
+        "complex_contributions",
+        lambda: flex.complex_contributions(name),
+    )
+    timed_call(
+        timings,
+        gold_standard,
+        "mpr_prepare",
+        lambda: flex.mpr_prepare(name),
+    )
+
+    timed_call(
+        timings,
+        gold_standard,
+        "plot_precision_recall_curve",
+        flex.plot_precision_recall_curve,
+    )
+    timed_call(timings, gold_standard, "plot_auc_scores", flex.plot_auc_scores)
+    timed_call(
+        timings,
+        gold_standard,
+        "plot_significant_complexes",
+        flex.plot_significant_complexes,
+    )
+    timed_call(
+        timings,
+        gold_standard,
+        "plot_percomplex_scatter",
+        lambda: flex.plot_percomplex_scatter(n_top=20),
+    )
+    timed_call(
+        timings,
+        gold_standard,
+        "plot_percomplex_scatter_bysize",
+        flex.plot_percomplex_scatter_bysize,
+    )
+    timed_call(
+        timings,
+        gold_standard,
+        "plot_complex_contributions",
+        flex.plot_complex_contributions,
+    )
+
+    timings.append(
+        {
+            "gold_standard": gold_standard,
+            "step": "total_runtime",
+            "seconds": perf_counter() - workflow_start,
+        }
+    )
+    output_folder.mkdir(parents=True, exist_ok=True)
+    pd.DataFrame(timings).to_csv(
+        output_folder / "benchmark_results.csv",
+        index=False,
+    )
+    return timings
+
+
+def main() -> None:
+    if not GENE_EFFECT_PATH.exists():
+        raise FileNotFoundError(f"Input dataset was not found: {GENE_EFFECT_PATH}")
+
+    all_timings: list[dict[str, Any]] = []
+    for gold_standard in GOLD_STANDARDS:
+        print(f"Running runtime benchmark: {gold_standard}")
+        all_timings.extend(run_gold_standard(gold_standard))
+
+    total_seconds = sum(
+        timing["seconds"]
+        for timing in all_timings
+        if timing["step"] == "total_runtime"
+    )
+    all_timings.append(
+        {
+            "gold_standard": "ALL",
+            "step": "grand_total_runtime",
+            "seconds": total_seconds,
+        }
+    )
+    BENCHMARK_ROOT.mkdir(parents=True, exist_ok=True)
+    combined_path = BENCHMARK_ROOT / "benchmark_results_all_gold_standards.csv"
+    pd.DataFrame(all_timings).to_csv(combined_path, index=False)
+    print(f"Benchmark results saved to: {combined_path}")
+    print(f"Grand total workflow runtime: {total_seconds:.3f} seconds")
+
+
+if __name__ == "__main__":
+    main()