schrodinger.seam.examples.active_learning_weigher module¶

A workflow for generating a “model” that predicts the molecular weight of a molecule based on the number of atoms and types of atoms in the molecule.

Basic usage:

$SCHRODINGER/run seam_example.py active_learning_weigher

class schrodinger.seam.examples.active_learning_weigher.PredWeight(seen_count: int, prediction: float, element: str)¶

Bases: object

seen_count: int¶

prediction: float¶

element: str¶

__init__(seen_count: int, prediction: float, element: str) → None¶

class schrodinger.seam.examples.active_learning_weigher.MolWtModel(predict_weights: Dict[str, float])¶

Bases: object

predict_weights: Dict[str, float]¶

classmethod initialize()¶

toText() → str¶

__init__(predict_weights: Dict[str, float]) → None¶

schrodinger.seam.examples.active_learning_weigher.predict(model: schrodinger.seam.examples.active_learning_weigher.MolWtModel, mol: rdkit.Chem.rdchem.Mol) → float¶

schrodinger.seam.examples.active_learning_weigher.train(model: schrodinger.seam.examples.active_learning_weigher.MolWtModel, mols_with_wts: Iterable[Tuple[rdkit.Chem.rdchem.Mol, float]]) → schrodinger.seam.examples.active_learning_weigher.MolWtModel¶: Train the model by updating the weights based on the actual weights of the input molecules.

schrodinger.seam.examples.active_learning_weigher.to_mols(smiles: str) → List[rdkit.Chem.rdchem.Mol]¶

schrodinger.seam.examples.active_learning_weigher.main(args=None)¶