What Is MegaMolBART v0.2?

This container deploys MegaMolBART model for inferencing. 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.

Software Requirements

The MegaMolBART container is assembled with the prerequisite software for training NeMo-MegaMolBART and performing inference using a pre-trained model.

Requirements:

• Linux OS
• Pascal, Volta, Turing, or an NVIDIA Ampere architecture-based GPU.
• Nvidia Driver
• Docker

Getting Started

MegaMolBART v0.2 container encloses all prerequisites for training and inference. Please follow these steps to start MegaMolBART container for inference.

• Start an instance of the Docker image using the following command:

# For Docker version 19.03 or later
docker run \
   --gpus all \
   --rm \
   -p 8888:8888 \
   nvcr.io/nvidia/clara/megamolbart:0.2.0


# For Docker version 19.02 or older
docker run \
   --runtime nvidia \
   --rm \
   -p 8888:8888 \
   nvcr.io/nvidia/clara/megamolbart:0.2.0

• In a browser open URL http://<<HOSTNAME/IP>>:8888

License

By pulling and using the container, you accept the terms and conditions of Apache 2.0 license