| """Inference helper for models uploaded by hf_upload_universal.py. |
| |
| Usage: |
| from infer import predict_smiles |
| predict_smiles(model, ["CCO", "CC(=O)O"]) |
| |
| The model was trained on the features listed in config.json |
| (e.g. Morgan fingerprint 1024 + physicochemical descriptors). |
| This model is a sklearn Pipeline (ColumnTransformer + |
| ExtraTreesRegressor). LazyPredict pipelines select columns by STRING |
| name, so features must be passed as a pandas DataFrame with columns |
| feature_0..feature_1029. |
| Feature order: Morgan fingerprint 1024 (radius 2) first, then 6 physchem |
| descriptors in this order: MolWt, MolLogP, TPSA, NumHDonors, |
| NumHAcceptors, NumRotatableBonds. |
| Unpickling model.pkl requires lazypredict (see requirements.txt). |
| """ |
| import pickle |
|
|
| import numpy as np |
| import pandas as pd |
| from rdkit import Chem |
| from rdkit.Chem import AllChem, Descriptors |
|
|
|
|
| def featurize(smiles_list, features): |
| rows = [] |
| for smi in smiles_list: |
| mol = Chem.MolFromSmiles(smi) |
| if mol is None: |
| raise ValueError(f"Invalid SMILES: {smi}") |
| parts = [] |
| if "morgan1024" in features: |
| fp = AllChem.GetMorganFingerprintAsBitVect(mol, 2, nBits=1024) |
| parts.append(np.asarray(fp, dtype=float)) |
| if "physchem" in features: |
| parts.append(np.array([ |
| Descriptors.MolWt(mol), Descriptors.MolLogP(mol), |
| Descriptors.TPSA(mol), Descriptors.NumHDonors(mol), |
| Descriptors.NumHAcceptors(mol), |
| Descriptors.NumRotatableBonds(mol), |
| ], dtype=float)) |
| rows.append(np.concatenate(parts) if parts else np.array([])) |
| X = np.vstack(rows) |
| return pd.DataFrame(X, columns=[f"feature_{i}" for i in range(X.shape[1])]) |
|
|
|
|
| def load_model(path="model.pkl"): |
| with open(path, "rb") as f: |
| return pickle.load(f) |
|
|
|
|
| def predict_smiles(model, smiles_list, features=("morgan1024", "physchem")): |
| X = featurize(smiles_list, features) |
| return model.predict(X) |
|
|
