Transformer-based large language models (LLMs) have revolutionized the ways to understand and explore massive datasets and enable us to generate and augment relevant data efficiently. Initially applied for natural language processing tasks, LLMs have extended applicability in understanding languages of the molecules of life — DNA, RNA, proteins, and chemical compounds. Understanding and efficiently exploring such vast and intricate biochemical data spaces is crucial for drug discovery — from designing new molecules to predicting complex behaviors. BioNeMo enables researchers to train LLMs, fine-tune, and use them for inference for predictive and generative AI. BioNeMo Service allows researchers to perform inference at a scale using state-of-the-art LLMs for drug discovery.
We'll introduce BioNeMo — Framework and Service — and their applications, then take a deeper dive into running LLM training and inferencing using pre-trained models in BioNeMo for biomolecular property predictions.
Prerequisite(s):
Basic familiarity with Python, Docker, Machine learning concepts, Biomolecular data formats
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.
Ready to validate your skills? Get NVIDIA certified and distinguish yourself in the industry.