Spaces:
Paused
Paused
Download app.py from Delower/dpp4-kd-webapp: direct link, hf CLI and curl.
- Browser
- Download file 4.89 kB
-
https://huggingface.co/spaces/Delower/dpp4-kd-webapp/resolve/main/app.py
- Command line
-
hf download hf://spaces/Delower/dpp4-kd-webapp/app.py
-
curl -L -o app.py https://huggingface.co/spaces/Delower/dpp4-kd-webapp/resolve/main/app.py
4.89 kB
| """DPP-4 Kd Predictor — DPP-4 Kd LTN. | |
| Transfer-learned LTN for DPP-4 binding affinity (Kd): stage 1 pre-trained | |
| on the all-target Kd corpus, stage 2 fine-tuned on DPP-4 Ki. On the fully | |
| held-out external set of 15 DPP-4 Kd compounds (never trained on): | |
| RMSE 1.604 · MAE 1.276 · class accuracy 0.867 (scores in pKd). | |
| Weights (ltn_stage2.pt) and the DPP-4 ESM-2 protein vector are bundled in | |
| this Space; the standalone model repo is Delower/dpp4-kd-ltn. | |
| """ | |
| import os | |
| import gradio as gr | |
| import pandas as pd | |
| import spaces | |
| from kd_inference import load_esm_vector, load_model, predict_smiles_list | |
| NET = load_model() | |
| ESM_VEC = load_esm_vector() | |
| def predict_frame(df, smiles_col): | |
| smiles = df[smiles_col].astype(str).tolist() | |
| rows = predict_smiles_list(NET, ESM_VEC, smiles) | |
| out = df.copy() | |
| out["predicted_pKd"] = [r["predicted_pKd"] for r in rows] | |
| out["predicted_Kd_nM"] = [r["predicted_Kd_nM"] for r in rows] | |
| out["predicted_deltaG_kcal_mol"] = [r["predicted_deltaG_kcal_mol"] for r in rows] | |
| out["predicted_class"] = [r["predicted_class"] for r in rows] | |
| out["status"] = [r["status"] for r in rows] | |
| return out | |
| def predict_single(smiles): | |
| smiles = (smiles or "").strip() | |
| if not smiles: | |
| return "—", "—", "—", "—" | |
| df = pd.DataFrame({"smiles": [smiles]}) | |
| out = predict_frame(df, "smiles") | |
| r = out.iloc[0] | |
| if r["status"] != "ok": | |
| raise gr.Error("Invalid SMILES — RDKit could not parse that structure. " | |
| "Please check the string and try again.") | |
| return (f"{r['predicted_pKd']:.3f}", | |
| f"{r['predicted_Kd_nM']:.2f}", | |
| f"{r['predicted_deltaG_kcal_mol']:.2f}", | |
| f"{r['predicted_class']}") | |
| def predict_batch(file): | |
| if file is None: | |
| return None, None | |
| df = pd.read_csv(file.name) | |
| col = next((c for c in df.columns | |
| if c.lower() in ("smiles", "canonical_smiles", "smile")), None) | |
| if col is None: | |
| raise gr.Error("CSV must contain a 'smiles' column.") | |
| out = predict_frame(df, col) | |
| path = "/tmp/kd_batch_predictions.csv" | |
| out.to_csv(path, index=False) | |
| return out, path | |
| ABOUT = """ | |
| ## Model | |
| **DPP-4 Kd LTN** — a tuned Logic Tensor Network (MLP trunk 768-384-192 with | |
| regression + band-classification heads trained under LTN axioms), the best | |
| model of the DPP-4 Kd transfer suite. | |
| - Target: human DPP-4 (UniProt **P27487** / ChEMBL **CHEMBL284**) | |
| - Features: Morgan fingerprint (r=2, 2048 bits) + ESM-2 650M embedding of | |
| DPP-4 (1280) = 3,328 | |
| - Transfer learning: **stage 1** pre-train on the all-target Kd corpus | |
| (86,569 compound-target rows) → **stage 2** fine-tune on DPP-4 Ki | |
| (555 compounds; Ki used as the pKd-scale fine-tune label) | |
| - Outputs: predicted **pKd**, **Kd (nM)** = 10^(9 − pKd), | |
| **ΔG (kcal/mol)** = −1.3642 × pKd, and potency class | |
| (potent pKd ≥ 7 · moderate 6–7 · weak < 6) | |
| ## Performance — external test, 15 DPP-4 Kd compounds (never trained on) | |
| | Metric | DPP-4 Kd LTN | | |
| |---|---| | |
| | RMSE (pKd) | 1.604 | | |
| | MAE (pKd) | 1.276 | | |
| | Class accuracy | 0.867 | | |
| Honest caveat: this is a Ki→Kd transfer model evaluated on only 15 | |
| compounds; an RMSE of ~1.6 log units means predictions are a ranking / | |
| triage signal, not a substitute for a measured Kd. The model systematically | |
| under-predicts the very tightest binders (e.g. linagliptin, experimental | |
| pKd 11.18, is predicted at 8.26). | |
| Part of an open UAB SPARC series: DPP-4 pIC50 predictor | |
| (Delower/dpp4-pic50-webapp), EGFR pIC50 predictor | |
| (Delower/egfr-pic50-webapp), MolGemma DPP-4 generator | |
| (Delower/dpp4-molgemma-generator). | |
| """ | |
| with gr.Blocks(title="DPP-4 Kd Predictor") as demo: | |
| gr.Markdown("# DPP-4 Kd Predictor — DPP-4 Kd LTN\n" | |
| "Stage-1 all-target Kd pre-train → stage-2 DPP-4 Ki fine-tune · " | |
| "external-15 RMSE 1.604 (pKd)") | |
| with gr.Tab("Single molecule"): | |
| smi = gr.Textbox(label="SMILES", placeholder="e.g. sitagliptin: N[C@@H](CC(=O)N1CCn2c(nnc2C(F)(F)F)C1)Cc1cc(F)c(F)cc1F") | |
| btn = gr.Button("Predict Kd", variant="primary") | |
| o1 = gr.Textbox(label="Predicted pKd") | |
| o2 = gr.Textbox(label="Predicted Kd (nM)") | |
| o3 = gr.Textbox(label="Predicted ΔG (kcal/mol)") | |
| o4 = gr.Textbox(label="Potency class") | |
| btn.click(predict_single, inputs=smi, outputs=[o1, o2, o3, o4]) | |
| with gr.Tab("Batch (CSV)"): | |
| f = gr.File(label="CSV with a 'smiles' column", file_types=[".csv"]) | |
| bbtn = gr.Button("Run batch prediction", variant="primary") | |
| table = gr.Dataframe(label="Predictions") | |
| dl = gr.File(label="Download predictions CSV") | |
| bbtn.click(predict_batch, inputs=f, outputs=[table, dl]) | |
| with gr.Tab("About"): | |
| gr.Markdown(ABOUT) | |
| if __name__ == "__main__": | |
| demo.launch(server_name="0.0.0.0", server_port=int(os.environ.get("PORT", 7860))) | |