Leveraging LLMs to Accelerate Drug Discovery for Life Sciences (Presented by Snowflake)
, Industry Field Chief Technology Officer, Life Sciences, Snowflake
Generative AI is accelerating our ability to understand all aspects of drug discovery, including predicting the 3D structures of proteins and visualizing how small molecules (ligands) bind to proteins, a crucial step to understanding the underlying causes for disease and developing cures.
We'll demonstrate how to run the protein folding model from BioNeMo by NVIDIA using enterprise-grade data in Snowflake with Snowpark Container Services. Discover how to leverage protein embedding models to perform similarity search to find similar proteins, compare their structures, and analyze whether the sequence similarity resulted in structural similarity using Uniprot RAW embeddings made available by EMBL and the protT5 model for obtaining protein embeddings. Finally, see how a ligand can dock with the protein by leveraging BioNeMo's stable diffusion model, DiffDock. The output will be presented in a Python-based Streamlit app inside Snowflake leveraging the Biopython libraries and PyMOL.