Advances in the deep learning-based large language model (LLM) architectures have shown their impact on various complex tasks, including image and text processing, data generation, etc. Understanding the vast data related to biomolecules such as DNA, proteins, and drug-like chemicals efficiently is crucial for expediting drug discovery. MegaMolBART is built on the NVIDIA NeMo framework developed for conversational AI models. It leverages the NeMo Megatron to curate the training data and train models with up to trillions of parameters. MegaMolBART and other models offer the capabilities of chemical space exploration and provide the learned embeddings useful for predictive tasks. In this course, you’ll get an introduction to LLM for cheminformatics applications, followed by a deeper dive into the features of MegaMolBART and our extended platform, with a hands-on walkthrough of chemical space exploration. This workshop will also provide an example of using the learned embeddings from the pre-trained model for physicochemical property prediction. Prerequisite(s): Basic familiarity with Python and Docker
*Please disregard any reference to "Event Code" for access to training materials. "Event Codes" are only valid during the original live session.
Explore more training options offered by the NVIDIA Deep Learning Institute (DLI). Choose from an extensive catalog of self-paced, online courses or instructor-led virtual workshops to help you develop key skills in AI, HPC, graphics & simulation, and more.