Accelerating Biotechnology Using Machine Learning

We focus on developing AI frameworks that enable rapid protein discovery and engineering. We are an interdisciplinary team of computer scientists, biologists, and chemists who create advanced machine learning models trained on specially curated protein datasets. We build on recent developments in both NLP and computer vision to create protein-specific AI techniques. Our resulting evolution-inspired models accurately predict both the function of complex protein structures and the effect of point mutations without the need for time consuming and expensive wet-lab experiments. Applications include rapid prototyping of new vaccines, therapeutics, and enzymes for use in both medical and biomanufacturing domains.

Featured

Alzheimer’s Drug Fermented With Help From AI and Bacteria Moves Closer to Reality
UT News, CNS, March 14, 2024

Stability Oracle: a structure-based graph-transformer framework for identifying stabilizing mutations
Nature Communications, July 23, 2024 

Biosensor and machine learning-aided engineering of an amaryllidaceae enzyme
Nature Communications, March 7, 2024 

Predicting a Protein's Stability Under a Million Mutations
NeurIPS 2023, Poster