Next generation drug discovery using mechanistic AI

Speaker: Associate Professor. Sriram Chandrasekaran, Who is an Associate Professor of Biomedical Engineering at the University of Michigan-Ann Arbor, and he leads the Systems Biology & Drug Discovery lab. He received his PhD in Biophysics from the University of Illinois at Urbana-Champaign and worked at Harvard University and MIT as a Harvard Junior Fellow. He has developed over 10 different systems biology algorithms for drug discovery and bioengineering. A key focus of his lab is the development of mechanistic AI methods that use both engineering models and machine learning. He teaches a new course called AI in BME that introduces students to AI algorithms and their biomedical applications.

Sriram is the recipient of the Howard Hughes Medical Institute (HHMI) Predoctoral Fellowship, Harvard Junior Fellowship, MIT Technology Review’s Top Innovators Under 35 (TR35) award, a Distinguished Young Investigator Award from the AICHE COBRA society, EBS Outstanding Teaching Award, NIH R35 MIRA award, the Machine Learning in the Chemical Sciences Award from the Camille & Henry Dreyfus Foundation and was a invited speaker for the 2022 US National Academy of Medicine (NAM) Emerging Leaders Forum.
Abstract: By 2050, we may lose 10 million people a year to drug-resistant infections. Unfortunately, the pace of drug discovery has not kept up with the rapid emergence of these pathogens. Drug combinations are increasingly used to tackle drug resistance in cancer and infectious diseases. Yet we lack a rational basis to design such multimodal treatments. Current drug-discovery approaches are unable to screen an astronomical number of drug combinations and do not account for pathogen heterogeneity or the complex in vivo environment. We have developed hybrid AI tools - INDIGO, MAGENTA, and CARAMeL, which predict the efficacy of millions of drug regimens based on the properties of the drugs, the pathogen, and the immune and infection environment. Our hybrid AI methods combine engineering models with machine learning, which provides both predictive power and mechanistic insights. Using these methods, we have identified highly synergistic drugs to treat drug resistant infections including Tuberculosis, the world’s deadliest bacterial infection. Our approach also accurately predicts the outcome of past clinical trials of multi-drug regimens. Our ultimate goal is to create a personalized approach to treat infections using AI.