pythonflex 0.1.5__tar.gz → 0.2__tar.gz

pythonflex-0.2/.vscode/settings.json

@@ -0,0 +1,5 @@
+{
+    "python-envs.defaultEnvManager": "ms-python.python:conda",
+    "python-envs.defaultPackageManager": "ms-python.python:conda",
+    "python-envs.pythonProjects": []
+}

{pythonflex-0.1.5 → pythonflex-0.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pythonflex
-Version: 0.1.5
+Version: 0.2
 Summary: pythonFLEX is a benchmarking toolkit for evaluating CRISPR screen results against biological gold standards. The toolkit computes gene-level and complex-level performance metrics, helping researchers systematically assess the biological relevance and resolution of their CRISPR screening data.
 Author-email: Yasir Demirtaş <tyasird@hotmail.com>
 Requires-Python: >=3.9

{pythonflex-0.1.5 → pythonflex-0.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "pythonflex"
-version = "0.1.5"
+version = "0.2"
 description = "pythonFLEX is a benchmarking toolkit for evaluating CRISPR screen results against biological gold standards. The toolkit computes gene-level and complex-level performance metrics, helping researchers systematically assess the biological relevance and resolution of their CRISPR screening data."
 readme = "README.md"
 authors = [

{pythonflex-0.1.5 → pythonflex-0.2}/src/pythonflex/__init__.py

@@ -2,7 +2,7 @@
 from .logging_config import log
 from .utils import dsave, dload
 from .preprocessing import get_example_data_path, load_datasets,  get_common_genes, filter_matrix_by_genes, load_gold_standard, filter_duplicate_terms
-from .analysis import initialize, pra, pra_percomplex, fast_corr, perform_corr, is_symmetric, binary, has_mirror_of_first_pair, convert_full_to_half_matrix, drop_mirror_pairs, quick_sort, complex_contributions, save_results_to_csv
+from .analysis import initialize, pra, pra_percomplex, fast_corr, perform_corr, is_symmetric, binary, has_mirror_of_first_pair, convert_full_to_half_matrix, drop_mirror_pairs, quick_sort, complex_contributions, save_results_to_csv, update_matploblib_config
 from .plotting import (
     adjust_text_positions, plot_precision_recall_curve, plot_percomplex_scatter,
     plot_percomplex_scatter_bysize, plot_complex_contributions, plot_significant_complexes, plot_auc_scores
@@ -14,5 +14,5 @@ __all__ = [ "log", "get_example_data_path", "fast_corr",
     "perform_corr", "is_symmetric", "binary", "has_mirror_of_first_pair", "convert_full_to_half_matrix",
     "drop_mirror_pairs", "quick_sort", "complex_contributions", "adjust_text_positions", "plot_precision_recall_curve",
     "plot_percomplex_scatter", "plot_percomplex_scatter_bysize", "plot_complex_contributions",
-    "plot_significant_complexes", "plot_auc_scores", "save_results_to_csv"
+    "plot_significant_complexes", "plot_auc_scores", "save_results_to_csv", "update_matploblib_config"
 ]

{pythonflex-0.1.5 → pythonflex-0.2}/src/pythonflex/analysis.py

@@ -23,7 +23,7 @@ from .logging_config import log
 from .preprocessing import filter_matrix_by_genes
 from .utils import dsave, dload, _sanitize
 
-
+import matplotlib as mpl
 
 def deep_update(source, overrides):
     """Recursively update the source dict with the overrides."""
@@ -40,7 +40,7 @@ def initialize(config={}):
 
     default_config = {
         "min_genes_in_complex": 3,
-        "min_genes_per_complex_analysis": 3,
+        "min_genes_per_complex_analysis": 2,
         "output_folder": "output",
         "gold_standard": "CORUM",
         "color_map": "RdYlBu",
@@ -48,7 +48,7 @@ def initialize(config={}):
         "plotting": {
             "save_plot": True,
             "show_plot": True,
-            "output_type": "png",
+            "output_type": "pdf",
         },
         "preprocessing": {
             "normalize": False,
@@ -95,31 +95,105 @@ def initialize(config={}):
 
 
 
-def update_matploblib_config(config={}):
-    log.progress("Updating matplotlib settings.")
-    plt.rcParams.update({
-        "font.family": "DejaVu Sans",        # ← change if you prefer Arial, etc.
-        "mathtext.fontset": "dejavusans",
-        'font.size': 7,                # General font size
-        'axes.titlesize': 10,          # Title size
-        'axes.labelsize': 7,           # Axis labels (xlabel/ylabel)
-        'legend.fontsize': 7,          # Legend text
-        'xtick.labelsize': 6,          # X-axis tick labels
-        'ytick.labelsize': 6,          # Y-axis tick labels
-        'lines.linewidth': 1.5,        # Line width for plots
-        'figure.dpi': 300,             # Figure resolution
-        'figure.figsize': (8, 6),      # Default figure size
-        'grid.linestyle': '--',        # Grid line style
-        'grid.linewidth': 0.5,         # Grid line width
-        'grid.alpha': 0.2,             # Grid transparency
-        'axes.spines.right': False,    # Hide right spine
-        'axes.spines.top': False,      # Hide top spine
-        'image.cmap': config['color_map'],        # Default colormap
-        'axes.edgecolor': 'black',                # Axis edge color
-        'axes.facecolor': 'none',                 # Transparent axes background
-        'text.usetex': False                # Ensure LaTeX is off
+
+
+def update_matploblib_config(config=None, font_family="Arial", layout="single"):
+    """
+    Configure matplotlib settings optimized for Nature journal figures:
+      - 7 pt fonts (labels, ticks, legend), 9 pt titles
+      - Thin spines (0.5 pt), ticks out (left/bottom only), no minor ticks
+      - No grid, clean minimalist look
+      - Colorblind-friendly Tableau 10 color cycle
+      - Illustrator-safe PDF export (Type 42)
+      - Figure sizes: "single" (~89 mm), "double" (~183 mm), or custom (width, height) in inches
+    
+    Args:
+        config (dict, optional): Configuration dict (e.g., {'color_map': 'RdYlBu'}).
+        font_family (str): Preferred font (e.g., 'Arial', falls back to 'Helvetica').
+        layout (str or tuple): 'single' (~89 mm), 'double' (~183 mm), or (width, height) in inches.
+    """
+    if config is None:
+        config = {}
+    # Fallback if chosen font missing
+    try:
+        from matplotlib.font_manager import findfont, FontProperties
+        findfont(FontProperties(family=font_family))
+    except Exception:
+        font_family = "Helvetica"  # Nature prefers Helvetica if Arial unavailable
+        print(f"Warning: '{font_family}' not found, falling back to 'Helvetica'.")
+    
+    # Figure size presets (Nature: single ≈ 89 mm, double ≈ 183 mm at 25.4 mm/inch)
+    if isinstance(layout, tuple):
+        fig_w, fig_h = layout
+    else:
+        if layout == "double":
+            fig_w = 7.2  # ~183 mm
+            fig_h = 5.4  # Adjusted aspect
+        else:  # "single"
+            fig_w = 4.0  # Increased from 3.5" for more space (~102 mm)
+            fig_h = 3.0  # Increased from 2.6" for better aspect (~76 mm)
+    # Colorblind-friendly cycle (Tableau 10 adapted)
+    cb_cycle = [
+        "#4E79A7", "#F28E2B", "#E15759", "#76B7B2", "#59A14F",
+        "#EDC948", "#B07AA1", "#FF9DA7", "#9C755F", "#BAB0AC"
+    ]
+    mpl.rcParams.update({
+        # --- Text & Fonts ---
+        "text.usetex": False,  # Avoid LaTeX
+        "font.family": [font_family],  # Explicit font
+        "mathtext.fontset": "dejavusans",  # Disable mathtext
+        "mathtext.default": "regular",  # Plain text
+        "axes.unicode_minus": True,  # Proper minus signs
+        # --- Sizes (7 pt baseline, adjusted for space) ---
+        "font.size": 7,  # Reduced from 8 pt
+        "axes.titlesize": 9,  # Reduced from 10 pt
+        "axes.labelsize": 7,
+        "legend.fontsize": 7,
+        "xtick.labelsize": 7,
+        "ytick.labelsize": 7,
+        # --- Lines & Markers ---
+        "lines.linewidth": 1.5,  # Kept for data visibility
+        "lines.markersize": 4.0,
+        "patch.linewidth": 0.5,
+        "errorbar.capsize": 2,
+        # --- Axes, Spines, Ticks ---
+        "axes.linewidth": 0.5,
+        "axes.edgecolor": "black",
+        "axes.facecolor": "none",
+        "axes.titlepad": 3.0,
+        "axes.labelpad": 2.0,
+        "axes.prop_cycle": mpl.cycler(color=cb_cycle),
+        "xtick.direction": "out",
+        "ytick.direction": "out",
+        "xtick.major.size": 2.5,
+        "ytick.major.size": 2.5,
+        "xtick.minor.visible": False,
+        "ytick.minor.visible": False,
+        "xtick.major.width": 0.5,
+        "ytick.major.width": 0.5,
+        "xtick.top": False,
+        "ytick.right": False,
+        # --- Grid ---
+        "axes.grid": False,
+        # --- Legend ---
+        "legend.frameon": False,
+        "legend.handlelength": 1.6,  # Slightly adjusted
+        "legend.handletextpad": 0.4,
+        "legend.borderaxespad": 0.3,
+        "legend.loc": "best",  # Dynamic placement to avoid overlap
+        # --- Figure & Save ---
+        "figure.dpi": 600,
+        "figure.figsize": (fig_w, fig_h),
+        "savefig.dpi": 600,
+        "savefig.bbox": "tight",
+        "savefig.pad_inches": 0.1,  # Increased for spacing
+        "savefig.transparent": False,  # White background
+        # --- PDF/SVG Export ---
+        "pdf.fonttype": 42,
+        "ps.fonttype": 42,
+        "pdf.use14corefonts": False,
+        "svg.fonttype": "none",
     })
-    log.done("Matplotlib settings updated.")
 
 
 
@@ -172,15 +246,14 @@ def pra(dataset_name, matrix, is_corr=False):
         pr_auc = metrics.auc(recall, precision)
         df["precision"] = precision
         df["recall"] = recall
-
+    
     log.info(f"PR-AUC: {pr_auc:.4f}, Number of true positives: {df['prediction'].sum()}")
     dsave(df, "pra", dataset_name)
     dsave(pr_auc, "pr_auc", dataset_name)
-    log.done(f"Global PRA completed for {dataset_name}")
-    return df, pr_auc
-
-
+    dsave( _corrected_auc(df) , "corrected_pr_auc", dataset_name)
 
+    log.done(f"Global PRA completed for {dataset_name}")
+    return df
 
 
 
@@ -189,6 +262,9 @@ def pra(dataset_name, matrix, is_corr=False):
 # helper functions for PRA per-complex analysis
 # --------------------------------------------------------------------------
 
+def _corrected_auc(df: pd.DataFrame) -> float:
+    return np.trapz(df["precision"], df["recall"]) - df["precision"].iloc[-1]
+
 def _build_gene_to_pair_indices(pairwise_df):
     indices = pairwise_df.index.values
     genes = pd.concat([pairwise_df['gene1'], pairwise_df['gene2']], ignore_index=True)
@@ -240,10 +316,15 @@ def _dump_pairwise_memmap(df: pd.DataFrame, tag: str) -> Path:
 
 
 
-def _init_worker(memmap_path, gene_to_pair_indices):
+# Global variables for worker processes (compatible with older joblib)
+PAIRWISE_DF = None
+GENE2IDX = None
+
+def _init_worker_globals(memmap_path, gene_to_pair_indices):
+    """Initialize global variables for worker processes"""
     global PAIRWISE_DF, GENE2IDX
     PAIRWISE_DF = load(memmap_path)        
-    GENE2IDX    = gene_to_pair_indices                   
+    GENE2IDX = gene_to_pair_indices
 
 
 
@@ -263,42 +344,52 @@ def delete_memmap(memmap_path, log, wait_seconds=0.1):
 # --------------------------------------------------------------------------
 # Process each chunk of terms
 # --------------------------------------------------------------------------
-def _process_chunk(chunk_terms, min_genes):
-    pairwise_df = PAIRWISE_DF
-    gene_to_pair_indices = GENE2IDX
-    local_auc_scores = {}
-
-    for idx, row in chunk_terms.iterrows():
-        gene_set = set(row.used_genes)
-        if len(gene_set) < min_genes:
-            continue
+def _process_chunk(chunk_terms, min_genes, memmap_path, gene_to_pair_indices):
+    """Process a chunk of terms - compatible with older joblib versions"""
+    try:
+        # Load data in each worker (compatible with older joblib)
+        pairwise_df = load(memmap_path)
+        local_auc_scores = {}
+        local_corrected_auc_scores = {}
+
+        for idx, row in chunk_terms.iterrows():
+            gene_set = set(row.used_genes)
+            if len(gene_set) < min_genes:
+                continue
 
-        candidate_indices = bitarray(len(pairwise_df))
-        for g in gene_set:
-            if g in gene_to_pair_indices:
-                candidate_indices[gene_to_pair_indices[g]] = True
-        if not candidate_indices.any():
-            continue
+            candidate_indices = bitarray(len(pairwise_df))
+            for g in gene_set:
+                if g in gene_to_pair_indices:
+                    candidate_indices[gene_to_pair_indices[g]] = True
+            if not candidate_indices.any():
+                continue
 
-        selected = np.unpackbits(candidate_indices).view(bool)[:len(pairwise_df)]
-        sub_df   = pairwise_df.iloc[selected]
+            selected = np.unpackbits(candidate_indices).view(bool)[:len(pairwise_df)]
+            sub_df   = pairwise_df.iloc[selected]
 
-        complex_id = str(idx)
-        pattern    = r'(?:^|;)' + re.escape(complex_id) + r'(?:;|$)'
-        true_label = sub_df["complex_ids"].str.contains(pattern, regex=True).astype(int)
-        mask       = (sub_df["complex_ids"] == "") | (true_label == 1)
-        preds      = true_label[mask]
+            complex_id = str(idx)
+            pattern    = r'(?:^|;)' + re.escape(complex_id) + r'(?:;|$)'
+            true_label = sub_df["complex_ids"].str.contains(pattern, regex=True).astype(int)
+            mask       = (sub_df["complex_ids"] == "") | (true_label == 1)
+            preds      = true_label[mask]
 
-        if preds.sum() == 0:
-            continue
+            if preds.sum() == 0:
+                continue
 
-        tp_cum   = preds.cumsum()
-        precision = tp_cum / (np.arange(len(preds)) + 1)
-        recall    = tp_cum / tp_cum.iloc[-1]
-        if len(recall) >= 2 and recall.iloc[-1] != 0:
-            local_auc_scores[idx] = metrics.auc(recall, precision)
+            tp_cum   = preds.cumsum()
+            precision = tp_cum / (np.arange(len(preds)) + 1)
+            recall    = tp_cum / tp_cum.iloc[-1]
+            if len(recall) >= 2 and recall.iloc[-1] != 0:
+                # Compute regular AUC
+                local_auc_scores[idx] = metrics.auc(recall, precision)
+                # Compute corrected AUC using the same logic as _corrected_auc function
+                local_corrected_auc_scores[idx] = np.trapz(precision, recall) - precision.iloc[-1]
 
-    return local_auc_scores
+        return {'auc': local_auc_scores, 'corrected_auc': local_corrected_auc_scores}
+    
+    except Exception as e:
+        # Return error info for debugging
+        return {'error': str(e), 'chunk_size': len(chunk_terms)}
 
 
 
@@ -345,26 +436,23 @@ def pra_percomplex(dataset_name, matrix, is_corr=False, chunk_size=200):
     results = None
     
     try:
-        # Simplified parallel execution without progress callback interference
+        # Compatible parallel execution for older joblib versions
         log.started("Processing chunks in parallel")
-        with tqdm(total=len(chunks), desc="Per-complex PRA") as pbar:
-            results = Parallel(
-                n_jobs=8,
-                temp_folder=os.path.dirname(memmap_path),     
-                max_nbytes=None,                              
-                mmap_mode="r",
-                initializer=_init_worker,
-                initargs=(memmap_path, gene_to_pair_indices),
-                verbose=0  # Reduce joblib verbosity
-            )(delayed(_process_chunk)(chunk, min_genes) for chunk in chunks)
-            
-            # Update progress bar once all tasks are complete
-            pbar.update(len(chunks))
+        
+        # Use a more conservative approach with older joblib
+        results = Parallel(
+            n_jobs=min(4, len(chunks)),  # Limit to 4 workers or number of chunks
+            temp_folder=os.path.dirname(memmap_path),     
+            max_nbytes='100M',  # Set memory limit
+            verbose=1  # Show progress
+        )(delayed(_process_chunk)(chunk, min_genes, memmap_path, gene_to_pair_indices) 
+          for chunk in tqdm(chunks, desc="Per-complex PRA"))
         
         log.done("Processing chunks in parallel")
         
     except Exception as e:
         log.error(f"Error during parallel processing: {e}")
+        log.error(f"Error type: {type(e).__name__}")
         # Still try to clean up the memmap file
         try:
             if os.path.exists(memmap_path):
@@ -383,19 +471,29 @@ def pra_percomplex(dataset_name, matrix, is_corr=False, chunk_size=200):
         except OSError as e:
             log.warning(f"Failed to remove memmap file {memmap_path}: {e}")
 
-    # Merge results with error handling
+    # Merge results with enhanced error handling
     auc_scores = {}
+    corrected_auc_scores = {}
     if results:
-        for res in results:
+        for i, res in enumerate(results):
             if isinstance(res, dict):
-                auc_scores.update(res)
-            elif isinstance(res, tuple) and res[0] is None:
-                log.error(res[1])  # Log the error message from the chunk
+                if 'error' in res:
+                    log.error(f"Error in chunk {i}: {res['error']}")
+                elif 'auc' in res and 'corrected_auc' in res:
+                    # New format with both AUC types
+                    auc_scores.update(res['auc'])
+                    corrected_auc_scores.update(res['corrected_auc'])
+                else:
+                    # Fallback for old format (backward compatibility)
+                    auc_scores.update(res)
+            elif isinstance(res, tuple) and len(res) >= 2 and res[0] is None:
+                log.error(f"Chunk {i} error: {res[1]}")
             else:
-                log.error(f"Ignoring unexpected chunk result: {res}")
+                log.warning(f"Unexpected result type from chunk {i}: {type(res)} - {res}")
     
     # Add the computed AUC scores to the terms DataFrame.
     terms["auc_score"] = pd.Series(auc_scores)
+    terms["corrected_auc_score"] = pd.Series(corrected_auc_scores)
     terms.drop(columns=["hash"], inplace=True)
     dsave(terms, "pra_percomplex", dataset_name)
     log.done(f"Per-complex PRA completed.")
@@ -1296,4 +1394,3 @@ def save_results_to_csv(categories = ["complex_contributions", "pr_auc", "pra_pe
 #     dsave(pr_auc, "pr_auc", dataset_name)
 #     log.done(f"Global PRA completed for {dataset_name}")
 #     return df, pr_auc
-

{pythonflex-0.1.5 → pythonflex-0.2}/src/pythonflex/examples/basic_usage.py

@@ -6,18 +6,22 @@ Demonstrates initialization, data loading, analysis, and plotting.
 import pythonflex as flex
 
 inputs = {
-    "SNF": {
-        "path":  "C:/Users/yd/Desktop/projects/datasets/fused_similarity_network.csv",
+    "Melanoma (63 Screens)": {
+        "path": flex.get_example_data_path("melanoma_cell_lines_500_genes.csv"), 
         "sort": "high"
     },
-    "miss_SNF": {
-        "path":  "C:/Users/yd/Desktop/projects/datasets/miss_snf_fused_similarity_network.csv",
+    "Liver (24 Screens)": {
+        "path": flex.get_example_data_path("liver_cell_lines_500_genes.csv"), 
         "sort": "high"
-    }
+    },
+    "Neuroblastoma (37 Screens)": {
+        "path": flex.get_example_data_path("neuroblastoma_cell_lines_500_genes.csv"), 
+        "sort": "high"
+    },
 }
 
-#%%
 
+#%%
 default_config = {
     "min_genes_in_complex": 0,
     "min_genes_per_complex_analysis": 3,
@@ -27,7 +31,7 @@ default_config = {
     "jaccard": True,
     "plotting": {
         "save_plot": True,
-        "output_type": "PNG",
+        "output_type": "pdf",
     },
     "preprocessing": {
         "fill_na": True,
@@ -43,7 +47,6 @@ default_config = {
 flex.initialize(default_config)
 
 # Load datasets and gold standard terms
-
 data, _ = flex.load_datasets(inputs)
 terms, genes_in_terms = flex.load_gold_standard()
 
@@ -51,16 +54,17 @@ terms, genes_in_terms = flex.load_gold_standard()
 #%%
 # Run analysis
 for name, dataset in data.items():
-    df, pr_auc = flex.pra(name, dataset, is_corr=True)
-    fpc = flex.pra_percomplex(name, dataset, is_corr=True) 
+    pra = flex.pra(name, dataset, is_corr=False)
+    fpc = flex.pra_percomplex(name, dataset, is_corr=False) 
     cc = flex.complex_contributions(name)
+    
 
 
 #%%
 # Generate plots
 flex.plot_auc_scores()
 flex.plot_precision_recall_curve()
-flex.plot_percomplex_scatter()
+flex.plot_percomplex_scatter(n_top=20)
 flex.plot_percomplex_scatter_bysize()
 flex.plot_significant_complexes()
 flex.plot_complex_contributions()
@@ -82,27 +86,3 @@ flex.save_results_to_csv()
 
 
 
-# %%
-import os
-import glob
-
-inputs = {
-    "depmap all": {
-        "path":  "../../../../datasets/depmap/24Q4/depmap_geneeffect_all_cellines.csv",
-        "sort": "high"
-    }
-}
-
-# Now auto-discover the rest of the CSVs in the folder
-DATA_DIR = "../../../../datasets/depmap/24Q4/subset/"
-for path in glob.glob(os.path.join(DATA_DIR, "*.csv")):
-
-    # Derive the key name from filename (without extension)
-    key = os.path.splitext(os.path.basename(path))[0]
-    inputs[key] = {
-        "path": path,
-        "sort": "high"
-    }
-
-# inputs now has "depmap all" first, then one entry per CSV in DATA_DIR
-print(inputs)

{pythonflex-0.1.5 → pythonflex-0.2}/src/pythonflex/examples/dataset_filtering.py

@@ -8,6 +8,8 @@ model = pd.read_csv("../../../../datasets/depmap/24Q4/Model.csv",index_col=0)
 df.columns = df.columns.str.split(" \\(").str[0]
 df = df.T
 
+#%%
+
 # %%
 # get ModelID of selected disease for example OncotreePrimaryDisease==Melanoma
 melanoma = model[model.OncotreePrimaryDisease=="Melanoma"].index.unique().values

pythonflex-0.2/src/pythonflex/examples/test.py

@@ -0,0 +1,104 @@
+#%%
+import pythonflex as flex
+import os
+
+# # Define specific cell line types you're interested in
+DATA_DIR = "C:/Users/yd/Desktop/projects/_datasets/depmap/25Q2/subset/"
+
+# Specific cell lines of interest with "_cell_lines" suffix removed
+cell_line_files = [
+    "soft_tissue_cell_lines.csv",
+    "skin_cell_lines.csv", 
+    # "lung_cell_lines.csv",
+    # "head_and_neck_cell_lines.csv",
+    # "esophagus_stomach_cell_lines.csv",
+]
+
+inputs = {}
+
+# Create inputs dict with shortened names (removing "_cell_lines" suffix)
+for filename in cell_line_files:
+    # Remove .csv extension and _cell_lines suffix
+    key = filename.replace("_cell_lines.csv", "")
+    full_path = os.path.join(DATA_DIR, filename)
+    
+    inputs[key] = {
+        "path": full_path,
+        "sort": "high"
+    }
+
+inputs['depmap'] = {
+    "path": "C:/Users/yd/Desktop/projects/_datasets/depmap/25Q2/gene_effect.csv",
+    "sort": "high"
+}
+
+# Print the resulting inputs dictionary
+print("Configured inputs:")
+for key, value in inputs.items():
+    print(f"  {key}: {value['path']}")
+
+
+
+default_config = {
+    "min_genes_in_complex": 2,
+    "min_genes_per_complex_analysis": 2,
+    "output_folder": "25q2_min_genes_2",
+    "gold_standard": "CORUM",
+    "color_map": "RdYlBu",
+    "jaccard": True,
+    "plotting": {
+        "save_plot": True,
+        "output_type": "pdf",
+    },
+    "preprocessing": {
+        "fill_na": True,
+        "normalize": False,
+    },
+    "corr_function": "numpy",
+    "logging": {  
+        "visible_levels": ["DONE","STARTED"]  # "PROGRESS", "STARTED", ,"INFO","WARNING"
+    }
+}
+
+# Initialize logger, config, and output folder
+flex.initialize(default_config)
+
+# Load datasets and gold standard terms
+data, _ = flex.load_datasets(inputs)
+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) 
+    cc = flex.complex_contributions(name)
+    
+
+
+#%%
+# Generate plots
+flex.plot_auc_scores()
+flex.plot_precision_recall_curve()
+flex.plot_percomplex_scatter()
+flex.plot_percomplex_scatter_bysize()
+flex.plot_significant_complexes()
+flex.plot_complex_contributions()
+
+
+#%%
+# Save results to CSV
+flex.save_results_to_csv()
+
+
+
+
+
+
+
+
+
+#%%
+
+