Swaraj Thorat

About Swaraj Thorat

I currently work with the Research and Development team at Eli Lilly and Company, where I am involved in building organ-specific biological aging clocks using large-scale plasma proteomics data. The goal of this work is to better understand how different organs age and how those changes relate to disease risk. It combines machine learning, statistical modeling, and systems biology to study aging at the molecular level.|Alongside this, a big part of my work focuses on building reproducible bioinformatics pipelines and integrating different types of biological datasets to support data-driven research.I have been working on developing and productionizing Nextflow pipelines for multi-omics biomarker discovery. This involves integrating datasets such as GTEx transcriptomics, Human Protein Atlas proteomics, and metabolomics data. I focus on creating workflows that are reproducible and scalable, and that can run across cloud environments like AWS and DNAnexus. A lot of this work includes handling data ingestion, harmonization, quality control, and preparing standardized outputs for downstream analysis.I am also contributing to the development of a centralized Genetics Hub platform within the organization. The goal of this platform is to support genetic data ingestion, standardized analysis pipelines, and large-scale querying of genomic datasets across teams.Areas that particularly interest me include:• Genomics and multi-omics data integration• Reproducible workflow development using Nextflow• Large-scale data pipelines and cloud computing• Biomarker discovery and genetic association studiesI completed my Master’s in Bioinformatics from Indiana University, where I previously worked as a Graduate Research and Teaching Assistant. During that time, I worked on projects including developing a BERT-based NLP model for genomic sequence classification and improving single-cell RNA-seq analysis pipelines.I enjoy working at the intersection of biology, data, and computation, and I’m particularly interested in building tools and systems that make complex biological data easier to analyze and interpret.

Experience

1. Computational Biologist

   Eli Lilly and Company

   Aug 2025 — Present · Indianapolis, IN, US

   I develop organ-specific biological aging clocks using large-scale plasma proteomics data to study molecular aging and its relationship with disease risk.I apply machine learning, statistical modeling, and systems biology approaches to estimate biological aging across multiple organs including heart, liver, kidney, and adipose tissue independent of chronological age.In parallel, I build reproducible Nextflow pipelines for multi-omics data integration, combining datasets such as GTEx transcriptomics, Human Protein Atlas proteomics, and metabolomics. These workflows automate data ingestion, harmonization, and quality control to support scalable biomarker discovery and downstream analysis.

Education

• Indiana University Indianapolis

  Master's degree, Bioinformatics

• Dwarkadas J. Sanghvi College of Engineering

  Bachelor of Engineering - BE, Biomedical/Medical Engineering