herg-xgboost / config.json
Delower's picture
Upload config.json with huggingface_hub
b71656b verified
Raw History Blame Contribute Delete
3.61 kB
{
"project": "hERG toxicity prediction - Phase 5 XGBoost (Approach A finals)",
"version": "phase5-locked-pool-finals-2026-11-13",
"models": {
"cls_scaffold": {
"file": "models/xgboostA_cls_base+physchem_extra+morgan_counts+ecfp6+fcfp4+herg+pharm+morgan1024+morgan1024_counts_scaffold.pkl",
"task": "classification",
"protocol": "scaffold",
"headline": true
},
"cls_random": {
"file": "models/xgboostA_cls_base+physchem_extra+morgan_counts+ecfp6+fcfp4+herg+pharm+morgan1024+morgan1024_counts_random.pkl",
"task": "classification",
"protocol": "random"
},
"reg_scaffold": {
"file": "models/xgboostA_reg_base+morgan_counts+ecfp6+fcfp4+herg+pharm_scaffold.pkl",
"task": "regression",
"protocol": "scaffold",
"headline": true
},
"reg_random": {
"file": "models/xgboostA_reg_base+morgan_counts+ecfp6+fcfp4+herg+pharm_random.pkl",
"task": "regression",
"protocol": "random"
}
},
"feature_blocks": {
"classification": [
"morgan",
"maccs",
"desc",
"physchem_extra",
"morgan_counts",
"ecfp6",
"fcfp4",
"herg",
"pharm",
"morgan1024",
"morgan1024_counts"
],
"regression": [
"morgan",
"desc",
"morgan_counts",
"ecfp6",
"fcfp4",
"herg",
"pharm"
],
"excluded": "CDK/PaDEL block - dropped after the PaDEL build stalled; identical for all four models",
"block_kinds": {
"bits_raw": [
"morgan",
"maccs",
"ecfp6",
"fcfp4",
"morgan1024"
],
"continuous_prepped": [
"desc",
"physchem_extra",
"herg"
],
"counts_log1p_prepped": [
"morgan_counts",
"pharm",
"morgan1024_counts (classification only)"
]
},
"block_definitions": "feature_extraction.py (RDKit only, end-to-end from SMILES)"
},
"xgboost_params": {
"n_estimators": 900,
"learning_rate": 0.03,
"max_depth": 8,
"subsample": 0.8,
"colsample_bytree": 0.8,
"tree_method": "hist",
"n_jobs": 2,
"random_state": 42
},
"preprocessing": "Per continuous/count block, a ContPrep fitted on the protocol train+val keys ONLY: drop columns with variance <=1e-12 or >=5% NaN (judged on the fit fold), median-impute with fit-fold medians, standardise with fit-fold mean/SD (+1e-9). Count blocks are log1p-transformed (after clipping negatives to 0) before the same steps. Fitted states are stored inside each model pickle under 'preps'; predict_herg.py applies them exactly.",
"thresholds": {
"primary_cutoff_uM": 10,
"primary_rule": "blocker if IC50 < 10 uM, i.e. pIC50 >= 5.0",
"cls_call_rule": "prob_blocker >= 0.5",
"reg_derived_call_rule": "pred_pIC50 >= 5.0",
"secondary_cutoff_uM": 1
},
"training_data": {
"classification_pool_compounds": 12702,
"regression_pool_compounds": 8657,
"sources": "ChEMBL + BindingDB + PubChem functional hERG IC50 (regression: functional IC50 only; Ki never pooled into the primary regression), canonical-deduplicated",
"lockout": "1,738 unique compounds of every evaluation set (internal test splits, hERG-70, hERG-60, new-compounds slice, FDA 36 panel, regulatory-failure set) removed by InChIKey connectivity block before training; post-lock overlap verified = 0",
"fit": "headline finals refit on protocol train+val; preprocessing fit on the same keys only"
},
"pickle_format": "dict {model: XGBClassifier/XGBRegressor, task, blocks, params, preps, protocol, trained_on}"
}