Member Spotlight: Sriram Chandrasekaran

Feature Stories

Member Spotlight: Sriram Chandrasekaran

Sriram Chandrasekaran is an assistant professor of biomedical engineering, and a recipient of a 2018 Precision Health Investigators Award. His lab develops computer models to understand how complex networks in a cell—spanning metabolism, gene regulation, and signaling—interact with each other, how these networks break down in disease, and how they can be targeted for therapy using drug combinations.

What are your research interests, broadly? What are your most recent projects and/or publications?

My lab’s focus is on drug discovery and precision health using AI. Notably, we have developed AI algorithms to combat the spread of drug-resistant infections like Tuberculosis (TB). TB is the world’s deadliest bacterial infectious, disease killing 1.8 million people each year. Due to the alarming spread of drug resistance, there is an urgent need for new drug regimens.

We have developed a computational model called INDIGO (INferring Drug Interactions using chemoGenomics and Orthology), which searches through millions of possible drug combinations to identify the most synergistic drug regimens to treat TB. Predictions from INDIGO correlated significantly with experimental testing of new leads. Predictions were also significantly predictive of drug regimen efficacy from past clinical trials.

Results from INDIGO were featured in the news article How an AI solution can design new tuberculosis drug regimens.

Some recent papers include:

  • Ma S, Jaipalli J, Larkins-Ford J, Lohmiller J, Aldridge B, Sherman D+, and Chandrasekaran S+, Transcriptomic signatures predict regulators of drug synergy and clinical regimen efficacy against Tuberculosis, mBio, 2019.
  • Cicchese J, Sambarey A, Kirschner DE+, Linderman JJ+, and Chandrasekaran S+. “A multi-scale pipeline linking drug transcriptomics with pharmacokinetics predicts in vivo interactions of tuberculosis drugs.” Scientific Reports, 2021.
  • Chung, CH, & Chandrasekaran S+. An interpretable flux-based machine learning model of drug interactions across metabolic space and time. bioRxiv. 2021

How has your Precision Health Investigators Award helped advance your research?

We have developed a computational pipeline for personalized treatment of TB using pilot funds from Precision Health. In addition to predicting drug regimen potency using chemogenomics and AI, our  pipeline also incorporates drug pharmacokinetics and host immune dynamics. This study was done in collaboration between various labs in three different schools at U-M – Engineering (Linderman), Medicine (Kirschner) and Public Health (Yang).

We are now mining health records to create a comprehensive AI model that takes into account over 200 different features for each patient to design personalized treatments for TB. This will eventually allow clinicians to match drug regimens for each patient based on the type of infection and their health status.

We have received the following grants based on the precision health funding:

  • NIH NIAID R01, A multifactorial pipeline to dissect combinatorial drug efficacy in Tuberculosis (2021-2025)
  • NIH NIGMS R35, Linking metabolic activity with drug sensitivity using metabolic influence networks (2020-2025)

More info on the grants is on Michigan Experts.