Computational Biology · Agentic AI · Translational Medicine

Rohit Jadhav PhD

Senior Computational Biologist · Immuno-Oncology · Fremont, CA

I build systems that turn large-scale omics data into drug targets, biomarkers, and clinical insights — and increasingly, I build the AI agents that run those systems autonomously. 15+ years at the intersection of computational biology and translational medicine, spanning epigenomics, immuno-oncology, and multi-agent AI for drug discovery.

15+
Years Experience
1,500+
Citations
4
Therapeutic Domains
10+
Peer-Reviewed Publications

Bridging Biology and AI
at Scale

My work sits at a rare intersection: I understand the biology deeply enough to ask the right questions, and I build the computational infrastructure to answer them at scale. Over 15 years, that has meant everything from ATAC-seq pipelines for T-cell exhaustion to multi-agent LLM systems that evaluate thousands of drug targets in days.

At Juvena Therapeutics, I lead informatics and ML applications across the platform — establishing cloud-native NGS infrastructure on GCP, building agentic AI workflows in partnership with Eli Lilly, and identifying multi-omics biomarkers that advanced a lead molecule into a Phase 1 clinical trial.

I publish in Nature, PNAS, and Cancer Research, serve as a reviewer for Bioinformatics and Scientific Reports, and maintain active open-source pipelines used across the field.

🤖

Agentic AI for Drug Discovery

Multi-agent LLM workflows, RAG, vector DBs, knowledge graphs — built for target prioritization at scale

🧬

Multi-Omics Biomarker Discovery

RNA-seq, scRNA-seq, proteomics, ATAC-seq, CRISPR screening — integrated for clinical translation

☁️

Cloud-Scale Infrastructure

Nextflow pipelines on GCP (Cloud Run, BigQuery, Vertex AI), Docker, GitHub Actions

Technical Stack

Python R TypeScript Nextflow Docker GCP Vertex AI BigQuery LLMs / RAG Vector DBs Supabase GitHub Actions Bioconductor Seurat Scanpy HOMER

Areas of Deep Focus

Where biology, computation, and AI intersect to drive translational impact.

🤖

Agentic AI for Drug Discovery

Building multi-agent LLM systems that autonomously synthesize literature, score pathway evidence, and prioritize drug targets at scales impossible for human teams alone. RAG pipelines, vector databases, knowledge graphs, and tool-using agents — designed for production deployment in biopharma.

LLMs RAG Knowledge Graphs Vector DBs MCP n8n
🧬

Multi-Omics Integration

Integrating RNA-seq, scRNA-seq, proteomics, ATAC-seq, and CRISPR screening data to identify biomarkers, therapeutic targets, and mechanisms of disease. End-to-end: QC, alignment, differential analysis, pathway enrichment, visualization, and clinical reporting.

RNA-seq scRNA-seq ATAC-seq Proteomics CRISPR Seurat
🎯

Immuno-Oncology & T-Cell Biology

Deep expertise in T-cell exhaustion, PD-1 blockade response, epigenetic regulation of immune aging, and tumor-immune interactions. Computational work directly tied to published clinical and preclinical discoveries in checkpoint immunotherapy.

T-cell Exhaustion PD-1 Blockade Epigenomics TCR-seq ChIP-seq
☁️

Cloud-Native Bioinformatics

Designing and operating production-grade bioinformatics infrastructure: Nextflow pipelines on GCP, containerized workflows, CI/CD with GitHub Actions, cost-optimized cloud compute, and scalable data management with BigQuery and Cloud Storage.

GCP Nextflow Docker Cloud Run BigQuery GitHub Actions

What I've Built

Selected projects that demonstrate the intersection of AI, biology, and translational impact.

01 / AGENTIC AI

Large-Scale Gene Target Evaluation Platform

Eli Lilly Partnership · Juvena Therapeutics

Built a multi-agent LLM system to evaluate thousands of gene targets for therapeutic relevance in aging and metabolic disease. The system autonomously synthesized literature, scored pathway evidence across multiple data modalities, and ranked candidates — compressing a multi-year manual effort into days.

Multi-agent architecture: literature RAG + pathway scoring + evidence synthesis
Knowledge graph integration for cross-disease target contextualization
Production deployment supporting active Eli Lilly partnership
AI · Production
02 / TRANSLATIONAL

Multi-Omics Biomarker Discovery → Phase 1 Trial

Juvena Therapeutics · Internal Pipeline

Integrated plasma proteomics, bulk RNA-seq, and CRISPR functional screening to identify pharmacodynamic and efficacy biomarkers for a lead therapeutic candidate. Biomarkers are now in active clinical use supporting patient stratification and dose optimization.

Multi-modal integration: proteomics + transcriptomics + CRISPR functional data
Statistical pipeline: mixed models, FDR correction, clinical subgroup analysis
Biomarkers advancing an active Phase 1 clinical trial
Phase 1 · Clinical
03 / EPIGENOMICS

Epigenetic Characterization of CD8 T-Cell Exhaustion

Stanford University · Rafi Ahmed Lab (Emory) Collaboration

Defined chromatin accessibility signatures distinguishing progenitor-exhausted from terminally exhausted CD8 T cells in chronic infection — and showed these populations respond differentially to PD-1 blockade. This ATAC-seq work provided mechanistic insight into why checkpoint immunotherapy works in some patients and not others.

ATAC-seq + ChIP-seq in virus-specific CD8 T cells from chronic LCMV infection
Identified TCF1+ progenitor population as primary responder to PD-1 blockade
Published PNAS 2019 · 248+ citations
PNAS · 248+ Citations

Writing

Thoughts on agentic AI, computational biology methods, and the future of AI-driven drug discovery.

Posts coming soon — writing in progress.

Let's Talk

Open to conversations about computational biology, agentic AI in drug discovery, and collaboration opportunities. Based in Fremont, CA — available for Bay Area and remote roles.