BBE Informal Seminar - Jishnu Das

"Studying immunomodulation using interpretable machine learning and
network approaches"

Our lab integrates multi-scale, multi-modal datasets using interpretable machine learning and network approaches that move beyond biomarkers to the inference of possible immunomodulatory mechanisms. Significant Latent Factor Interaction Discovery and Exploration (SLIDE) is a first-in-class interpretable machine learning technique that has been applied to a wide range of infectious, autoimmune and alloimmune diseases to gain corresponding mechanistic insights. We developed SpaceTravLR, a novel framework to advance spatial biology at single cell resolution from descriptive mapping to causal modeling by uncovering spatial functional microniches underlying a range of immune phenotypes. I will also describe Sliding Window Interaction Grammar (SWING), a novel interaction language model for quantifying the impact of genetic variation on protein and peptide interactions. Finally, I will go over frameworks for uncovering regulatory and signaling circuits underlying immune (B and Tfh) cell fate decision making.

Host: Ellen Rothenberg