Development of an Agentic AI Model for NGS Downstream Analysis Targeting Researchers with Limited Biological Background

TL;DR

This paper presents an AI-powered tool that automates and interprets NGS downstream analysis for researchers with limited biological expertise, integrating literature-backed insights and advanced methods within an accessible web app.

Contribution

The study introduces a novel agentic AI model built on Llama 3 and RAG that automates NGS analysis, provides literature-based interpretations, and recommends advanced techniques for non-expert users.

Findings

Successfully identified significant DEGs in a cancer dataset.

Generated biological insights linking mutations to prognosis.

Enabled advanced survival analysis through an interactive interface.

Abstract

Next-Generation Sequencing (NGS) has become a cornerstone of genomic research, yet the complexity of downstream analysis-ranging from differential expression gene (DEG) identification to biological interpretations-remains a significant barrier for researchers lacking specialized computational and biological expertise. While recent studies have introduced AI agents for RNA-seq analysis, most focus on general workflows without offering tailored interpretations or guidance for novices. To address this gap, we developed an Agentic AI model designed to automate NGS downstream analysis, provide literature-backed interpretations, and autonomously recommend advanced analytical methods. Built on the Llama 3 70B Large Language Model (LLM) and a Retrieval-Augmented Generation (RAG) framework, the model is deployed as an interactive Streamlit web application. The system integrates standard bioinformatics tools (Biopython, GSEApy, gProfiler) to execute core analyses, including DEG identification, clustering, and pathway enrichment. Uniquely, the agent utilizes RAG to query PubMed via Entrez, synthesizing biological insights and validating hypotheses with current literature. In a case study using cancer-related dataset, the model successfully identified significant DEGs, visualized clinical correlations, and derived evidence-based insights (e.g., linking BRAF mutations to prognosis), subsequently executing advanced survival modeling upon user selection. This framework democratizes bioinformatics by enabling researchers with limited backgrounds to seamlessly transition from basic data processing to advanced hypothesis testing and validation.