ailab-bio/mlp_synth

PROTAC Synthesizability — MLP

A PyTorch MLP 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 = 0.598.

Files

• mlp_v3_final.pt — network weights + architecture
• mlp_v3_final.skops — fitted preprocessor + target transformer
• mlp_v3_hparams.yaml — hyperparameters

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

Usage

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

from mlp.model import TorchMLPRegressor
from mol_utils import compute_fingerprints, compute_descriptors

model  = TorchMLPRegressor.load("mlp_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, torch, numpy.

License

MIT