ailab-bio/xgb_synth

PROTAC Synthesizability — XGBoost

An XGBoost regressor that predicts the heavy-atom-count weighted synthesizability score (hac_weighted_score) of PROTAC molecules from SMILES.

Nested 5×5 scaffold cross-validation, Optuna tuning. Mean CV R² = 0.565.

Files

• xgb_v3_final.ubj — XGBoost booster
• xgb_v3_final.skops — fitted preprocessor + target transformer
• xgb_v3_hparams.yaml — hyperparameters

(.ubj and .skops are both required to load the model.)

Usage

Requires the project code: https://github.com/ribesstefano/PROTAC-Synthesizability

from xgb.model import XGBoostRegressor
from mol_utils import compute_fingerprints, compute_descriptors

model  = XGBoostRegressor.load("xgb_v3_final")   # base path, no extension
smiles = ["O=C(O)c1ccccc1"]
preds  = model.predict(smiles,
                       X_fp=compute_fingerprints(smiles, 512, 2),
                       X_desc=compute_descriptors(smiles))

Dependencies

Pin these for reproducible loading (.skops and RDKit are version-sensitive): rdkit, scikit-learn, skops, xgboost, numpy.

License

MIT