Our lab develops foundational AI models that leverage large-scale biological data to gain a fundamental understanding of gene network dynamics to accelerate the discovery of key regulators and therapeutic targets. We take an innovative network-level approach to uncovering how layers of regulation in the cell from genomic sequence to transcriptional networks to cell-cell interactions across tissues coordinate human development and maintenance and how this regulatory circuitry is disrupted in human disease. We employ a closed-loop approach to computationally prioritize downstream experiments and feed back the results to rapidly evolve AI models towards a generalized understanding of biological systems. We apply these AI models to discover network-correcting therapeutics for cardiovascular disease to accelerate the development of much-needed treatments for patients.
Our lab leverages machine learning and experimental genomics to map the gene regulatory networks driving cardiovascular disease to develop network-correcting therapies. We develop novel machine learning models that can be pretrained on large-scale biological data to gain a fundamental understanding of network dynamics that can then improve predictions in a multitude of downstream applications through transfer learning. We apply these approaches to advance our understanding of the regulatory circuitry governing human development and tissue maintenance and to determine how network rewiring drives the progression of cardiovascular disease. We then design innovative network-based screens to identify molecules that correct these disrupted networks back to the normal state, thereby accelerating the development of much-needed treatments for patients.
Statistical Analysis of Genetic Association Studies
Understanding how eQTLs work
