Enrich.AI: An Agentic AI Platform for Interactive GeneSet Enrichment Analysis and Biological Interpretation
Motivation: Enrichment analysis is widely used to extract biological meanings from gene lists. However, the large number of available tools and reference libraries often make the interpretation of results challenging. Inexperienced users lack clear guidance on which datasets and terms are most relevant to their data, whereas experienced researchers must navigate large result sets and consult…
Enrich.AI is an innovative agentic AI platform designed for interactive gene set enrichment analysis and biological interpretation. The platform aims to simplify the process of interpreting gene lists, which can often be overwhelming for both novice and experienced researchers due to the vast array of available tools and reference libraries.
Enrich.AI employs a conversational biology assistant, utilizing an LLM-based ReAct architecture to dynamically select among 220+ gene set libraries, 40+ million publications from Europe PMC for literature search, gene annotation, and database retrieval. The platform is given a gene list and a brief biological context, and it generates a written interpretation supported by literature and six interactive visualizations.
A distinguishing feature of Enrich.AI is its conversational interface, which allows for human-in-the-loop refinement. This means that researchers, even those without programming experience, can explore results iteratively, making it more accessible and user-friendly. The platform's reliability was evaluated in a systematic assessment of 50 gene sets, showing high faithfulness to retrieved evidence and a low hallucination rate.
Written by urgent.news from bioRxiv's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
