Spaces:
Sleeping
Sleeping
Download app.py from rahafahmad89/PathoPred: direct link, hf CLI and curl.
- Browser
- Download file 8.07 kB
-
https://huggingface.co/spaces/rahafahmad89/PathoPred/resolve/main/app.py
- Command line
-
hf download hf://spaces/rahafahmad89/PathoPred/app.py
-
curl -L -o app.py https://huggingface.co/spaces/rahafahmad89/PathoPred/resolve/main/app.py
8.07 kB
| import os | |
| import json | |
| import traceback | |
| import joblib | |
| import numpy as np | |
| import pandas as pd | |
| import matplotlib | |
| matplotlib.use("Agg") | |
| import matplotlib.pyplot as plt | |
| import shap | |
| import gradio as gr | |
| # ============================================================ | |
| # PATCH: Fix gradio_client boolean JSON-schema crash | |
| # ============================================================ | |
| try: | |
| import gradio_client.utils as _gcu | |
| if hasattr(_gcu, "_json_schema_to_python_type"): | |
| _orig = _gcu._json_schema_to_python_type | |
| def _patched(schema, defs=None): | |
| # JSON Schema allows boolean schemas (True / False) | |
| if isinstance(schema, bool): | |
| return "Any" | |
| return _orig(schema, defs) | |
| _gcu._json_schema_to_python_type = _patched | |
| except Exception: | |
| pass | |
| # ============================================================ | |
| # Artifacts | |
| # ============================================================ | |
| MODEL_PATH = "model_extratrees_ds4.joblib" | |
| FEATS_PATH = "feature_names.json" | |
| model = joblib.load(MODEL_PATH) | |
| with open(FEATS_PATH) as f: | |
| FEATURES = json.load(f) | |
| LABEL_NAME = {0: "Benign", 1: "Pathogenic"} | |
| THRESHOLD = 0.7 | |
| ID_CANDIDATES = [ | |
| "#Uploaded_Variation", "#Uploaded_variation", "uploaded_variation", | |
| "Uploaded_Variation", "Uploaded_variation", "variant_id", | |
| "Variant_ID", "variation_id", "Variant", "ID", "HGVSc", "HGVSp" | |
| ] | |
| # ============================================================ | |
| # Helpers | |
| # ============================================================ | |
| def _clean_headers(df): | |
| df.columns = ( | |
| df.columns.astype(str) | |
| .str.replace(r"[\u200b\ufeff]", "", regex=True) | |
| .str.strip() | |
| ) | |
| return df | |
| def _read_table(file): | |
| name = getattr(file, "name", str(file)) | |
| if name.lower().endswith((".xlsx", ".xls")): | |
| df = pd.read_excel(name, engine="openpyxl") | |
| else: | |
| df = pd.read_csv( | |
| name, | |
| engine="python", | |
| sep=None, | |
| dtype=str, | |
| na_values=["", "NA", "N/A"], | |
| quoting=3, | |
| on_bad_lines="skip", | |
| encoding_errors="ignore", | |
| ) | |
| return _clean_headers(df) | |
| def _coerce_numeric(df): | |
| for c in df.columns: | |
| df[c] = pd.to_numeric(df[c], errors="coerce") | |
| return df | |
| def _prepare(df): | |
| for c in FEATURES: | |
| if c not in df.columns: | |
| df[c] = np.nan | |
| return _coerce_numeric(df[FEATURES].copy()) | |
| def _validate_columns(df): | |
| return [c for c in FEATURES if c not in df.columns] | |
| def _pick_id_series(df): | |
| norm = {c.lower(): c for c in df.columns} | |
| for cand in ID_CANDIDATES: | |
| if cand.lower() in norm: | |
| col = norm[cand.lower()] | |
| return df[col].astype(str) | |
| return pd.Series(df.index, name="row_index") | |
| # ============================================================ | |
| # Prediction | |
| # ============================================================ | |
| def predict_csv(file): | |
| try: | |
| if file is None: | |
| return None, "โ No file uploaded." | |
| df = _read_table(file) | |
| missing = _validate_columns(df) | |
| if missing: | |
| return None, f"โ Missing {len(missing)} features. Example: {missing[:10]}" | |
| X = _prepare(df) | |
| proba = model.predict_proba(X)[:, 1] | |
| pred = (proba > THRESHOLD).astype(int) | |
| ids = _pick_id_series(df) | |
| out = pd.DataFrame({ | |
| "Variant ID": ids, | |
| "Predicted probability (pathogenic)": proba, | |
| "Predicted class": np.where( | |
| pred == 1, "๐ด Pathogenic", "๐ข Benign" | |
| ), | |
| }) | |
| summary = ( | |
| f"โ Processed {len(out)} variants \n" | |
| f"๐ด Pathogenic: {(pred == 1).sum()} | " | |
| f"๐ข Benign: {(pred == 0).sum()} \n" | |
| f"Threshold = {THRESHOLD}" | |
| ) | |
| return out, summary | |
| except Exception: | |
| return None, "โ ERROR:\n```" + traceback.format_exc() + "```" | |
| # ============================================================ | |
| # SHAP Explanation | |
| # ============================================================ | |
| def explain_first_row(file): | |
| try: | |
| if file is None: | |
| return None, "โ No file uploaded." | |
| df = _read_table(file) | |
| missing = _validate_columns(df) | |
| if missing: | |
| return None, "โ Missing required features for explanation." | |
| X = _prepare(df) | |
| if len(X) == 0: | |
| return None, "โ No rows found." | |
| explainer = shap.Explainer(model.predict_proba, X) | |
| shap_values = explainer(X.iloc[[0]]) | |
| vals = shap_values.values[0, :, 1] | |
| s = pd.Series(vals, index=FEATURES).sort_values( | |
| key=np.abs, ascending=False | |
| ).head(15) | |
| fig = plt.figure(figsize=(7, 5)) | |
| s.iloc[::-1].plot(kind="barh") | |
| plt.title("Top feature contributions (Sample #1)") | |
| plt.tight_layout() | |
| return fig, ( | |
| "๐ **Why this prediction?** \n" | |
| "Positive bars increase the probability of pathogenicity; " | |
| "negative bars decrease it. \n" | |
| "These signals are *supportive only* and must be interpreted " | |
| "within ACMG/AMP guidelines." | |
| ) | |
| except Exception: | |
| return None, "โ ERROR:\n```" + traceback.format_exc() + "```" | |
| # ============================================================ | |
| # UI | |
| # ============================================================ | |
| with gr.Blocks( | |
| title="Pathogenicity Predictor", | |
| theme=gr.themes.Soft(primary_hue="rose", secondary_hue="slate"), | |
| ) as demo: | |
| gr.Markdown(""" | |
| # ๐งฌ Pathogenicity Predictor | |
| **Research prototype for variant pathogenicity assessment** | |
| Upload a CSV or Excel file containing the trained feature columns. | |
| This tool provides *supportive* predictions and explanations. | |
| """) | |
| with gr.Row(): | |
| with gr.Column(scale=1): | |
| gr.Markdown("### ๐ Input") | |
| inp = gr.File( | |
| label="Upload CSV / XLSX", | |
| file_types=[".csv", ".xlsx", ".xls"] | |
| ) | |
| gr.Markdown(""" | |
| **Requirements** | |
| - One row = one variant | |
| - Must include all trained feature columns | |
| - Results are **not** clinical diagnoses | |
| """) | |
| with gr.Column(scale=2): | |
| gr.Markdown("### ๐ Results") | |
| with gr.Row(): | |
| btn_pred = gr.Button("๐ฎ Predict", variant="primary") | |
| btn_expl = gr.Button("๐ Explain first variant") | |
| out_df = gr.Dataframe( | |
| label="Predictions", | |
| interactive=False, | |
| wrap=True, | |
| ) | |
| out_txt = gr.Markdown() | |
| gr.Markdown("### ๐ฌ Why this prediction?") | |
| out_plot = gr.Plot(label="Feature contribution (SHAP)") | |
| btn_pred.click(predict_csv, inp, [out_df, out_txt], show_progress=True) | |
| btn_expl.click(explain_first_row, inp, [out_plot, out_txt]) | |
| # ======================================================== | |
| # Feedback section (email) | |
| # ======================================================== | |
| gr.Markdown(""" | |
| --- | |
| ### ๐ฌ Feedback | |
| We would love to hear your thoughts, suggestions, or bug reports. | |
| ๐ง **[Send feedback via email](mailto:dr.rahafahmad@gmail.com?subject=Pathogenicity%20Predictor%20Feedback)** | |
| Click on the link or email us directly at **dr.rahafahmad@gmail.com, 700039113@uaeu.ac.ae, bassam.ali@uaeu.ac.ae** | |
| """) | |
| gr.Markdown(""" | |
| --- | |
| โ ๏ธ **Research prototype** | |
| This tool is for research and educational use only. | |
| Not intended for clinical diagnosis or medical decision-making. | |
| ยฉ 2026 | |
| """) | |
| # ============================================================ | |
| # Launch (Spaces-safe) | |
| # ============================================================ | |
| if __name__ == "__main__": | |
| port = int(os.environ.get("PORT", 7860)) | |
| demo.queue() | |
| demo.launch(server_name="0.0.0.0", server_port=port, debug=True) | |