Doctoral Thesis: Untangling the complexity of nature: Machine-learning for accelerated life-sciences

Adam U. Yaari

Abstract: 

Biological mechanisms are convoluted and stochastic systems that remain largely misunderstood despite centuries of rigorous scientific work. Machine-learning (ML) is a powerful framework to augment investigate such systems. Yet, its impact remain limited in the broad context of life-sciences. This thesis presents a number of approaches to optimize ML utility to accelerate biological research. First, we propose a paradigm shift from siloed data curation to multi-purpose cohorts at scale, even in the most restrictive case of human experimentation. The potential of this approach is revealed through the Brain-TreeBank, a multi-modal dataset of naturalistic language aligned to intracranial neural recordings. Second, we argue for the importance of ML interpretability to accelerate the understanding of biology. We develop an explainable general-purpose tool for modeling discrete stochastic processes at multiple resolutions. We demonstrate the utility of the method by identifying sets of mutations that likely drive cancer growth across the entire genome. 

Details

• Date: Tuesday, December 13
• Time: 1:00 pm - 2:30 pm
• Category: Thesis Defense
• Location: 32-G449 (Patil/Kiva)

Additional Location Details:

Thesis Supervisor(s): Drs. Boris Katz and Bonnie Berger