A playground for applying graph convolutional networks to molecules, with a focus on learning continuous “atom-type” embeddings and from these classical molecule force field parameters.
OpenFF recommends using Conda virtual environments for all scientific Python work. NAGL can be installed into a new Conda environment named
nagl with the
mamba create -n nagl -c conda-forge openff-nagl conda activate nagl
For more information on installing NAGL, see Installation.
NAGL can then be imported from the
Or executed from the command line:
from openff.nagl import GNNModel model = GNNModel.load("trained_model.pt")
from openff.toolkit import Molecule ethanol = Molecule.from_smiles("CCO") model.compute_property(ethanol)
A toolkit for the generation of neural network models for predicting molecule properties.