Shashank Jatav

DeepGEOSearch improves biomedical dataset discovery by using an LLM-powered schema-less retrieval system that matches natural-language queries to datasets with high precision and recall.

This paper evaluates GPT-4's performance in automated cell type annotation on single-cell RNA-seq data, identifies its limitations, and introduces an improved approach using RAG and new evaluation metrics.

This paper introduces scMetNet, a method to analyze metabolic rewiring in single-cell data, applied to murine embryonic neural development to identify key metabolic pathways and sub-networks involved in stem cell differentiation.