Modeling cellular response: Application to precision medicine
Associate Professor and Director of Computational Sciences (CSci) graduate program
Department of Mathematics University of Massachusetts Boston
The abundance of many RNA transcripts changes significantly in response to a variety of molecular and environmental perturbations. A key question in this setting is as follows: what intermediate molecular perturbations gave rise to the observed transcriptional changes? As changes beyond transcriptional level are rarely measured, direct inference of causal regulatory mechanisms is difficult and remains a central challenge in computational biology. In this talk, we present statistical and Bayesian approaches to query causal networks of bio-molecular interactions and identify intermediate molecular causes of transcriptional response. Additionally, we present a weighted group-lasso regularized model to predict diagnostic markers for precision medicine application. Using nested cross-validation as well as independent clinical datasets, we demonstrate that our approach leads to increased accuracy and generalizable results.
Research Interests: I am interested in the application of mathematics and computational algorithms in biological systems. In particular, I study machine learning models for biomarker discovery, precision medicine, and patient stratification; causal reasoning models for inference of stimuli-induced active biological pathways; and models of transcriptional and post-transcriptional gene regulation. Specialties: Applied mathematics, Machine learning, Bioinformatics, Statistics, and Software development for biological applications.
Date and time:
Saturday, November 27, 2021
12:45 PM—2:30 PM
Zoom Meeting Link: