June 6, 10:00am
Location: Santa Clara I

Can Self-supervised Models Make a Difference in Real-world Drug Discovery?

When starting a drug discovery project, there often isn’t much data available. How can we bootstrap machine learning approaches to drug discovery in the presence of limited data? Self-supervised approaches provide a systematic methodology to solve the low data problem in real world drug discovery. I will explore a variety of different self-supervised strategies to learn in the absence of experimental data, including some very recent work leveraging large language models such as GPT3 for chemistry. I will share some results from past and on-going work at Deep Forest Sciences working to extend self-supervision to real-world drug discovery.

Bharath is the founder and CEO of Deep Forest Sciences, a startup building an AI platform, Chiron, that brings cutting edge AI tools to real world discovery teams. He is also the founder and lead developer of the DeepChem open source project, one of the most popular open source frameworks for deep learning in drug discovery. Bharath founded DeepChem while doing his PhD at Stanford university, where he was supported by a Hertz Fellowship. Bharath received his BA and BS from UC Berkeley in EECS and Mathematics and was valedictorian of his graduating class in mathematics. Bharath is the lead author of “TensorFlow for Deep Learning: From Linear Regression to Reinforcement Learning”, and “Deep Learning for the Life Sciences” with O’Reilly Media.