Le Song

Towards AI-Driven Digital Organism: A System of Multiscale Foundation Models for Biology

Summary

Biology lies at the core of vital fields such as medicine, pharmacy, public health, longevity, agriculture, environmental protection, and clean energy. What will be the foundational AI models for biology? What data can be used to build them? How to build them exactly?

I will tutorial and discuss an engineering viable approach to address these challenges by designing an AI-Driven Digital Organism (AIDO), a world model of biology, in a modular, connectable, and holistic fashion to reflect biological scales, connectedness, and complexities. A system with integrated multiscale foundation models like the AIDO opens up a safe, affordable and high-throughput alternative platform for predicting, simulating and programming biology at all levels from molecules to cells to individuals. An AIDO is poised to trigger a new wave of better-guided wet-lab experimentation and better-informed first-principle reasoning, which can eventually help us better decode and improve life.

Short bio

Le Song is the CTO of GenBio AI. He is also a full professor of Mohamed bin Zayed University of AI (MBZUAI), and was a tenured associate professor of Georgia Institute of Technology, and the conference program chair of ICML 2022. He is an expert in AI and AI for Science and has won many best paper awards in premium AI conferences such as NeurIPS, ICML and AISTATS. He has pioneered the virtual cell research by pretraining the large single cell models and has developed the largest protein language model in the world with 100-billion parameters. His work on using large language models for protein structure predictions has also been featured as the cover story in Nature Machine Intelligence. 

Google Scholar: https://scholar.google.co.uk/citations?user=Xl4E0CsAAAAJ&hl=en