Linux / amd64
MegaMolBART is a model that understands chemistry and can be used for a variety of cheminformatics applications in drug discovery. The embeddings from its encoder can be used as features for predictive models. Alternatively, the encoder and decoder can be used together to generate novel molecules by sampling the model's embedding space.
The "MegaMolBART Base" docker image contains all software prerequisites for training and inference models using NeMo for use in drug discovery.
For additional information on how to use this container for training, please see the Github repository
By pulling and using the container, you accept the terms and conditions of Apache 2.0 license