Enrich.AI: An Agentic AI Platform for Interactive GeneSet Enrichment Analysis and Biological Interpretation
- 1Bioinformatics and Human Electrophysiology Laboratory, Department of Informatics, Ionian University, 49084, Corfu, Greece
Abstract
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 multiple resources to identify biologically relevant findings. Integrating AI into this process can help to bridge these gaps. Results: We present Enrich.AI, a conversational biology assistant that integrates statistical enrichment analysis with automated biological interpretation. The agent operates on an LLM-based ReAct architecture and dynamically selects among the tools for enrichment (220+ gene set libraries), literature search (40+ million publications via Europe PMC), gene annotation, and database retrieval. Given a gene list and a short description of the biological context, Enrich.AI produces a written interpretation grounded in the retrieved literature and six interactive, configurable visualizations. A conversational interface enables human-in-the-loop refinement, letting researchers without programming experience explore results iteratively. The reliability of these interpretations was validated through a systematic evaluation on 50 gene sets, demonstrating high faithfulness to retrieved evidence and a low hallucination rate.
Related
- Interactive effects of Nutrient Enrichment and Water Scarcity on Floral signaling and visitation
- StainAI-Web: An Interactive Platform for Whole-Slide Microglial Morphology Analysis
- iGEX: an interactive Gene EXpression exploration platform for the analysis of transcriptomic and proteomic datasets
- SENgEAR: an interactive visualization platform for comparative analysis of senescence signatures and cellular communication
- EMAP-SSN: An Embedding- and Multiple-Alignment-Integrated Sequence Similarity Network Platform for Interactive Exploration of Protein Sequence Space
BibTeX
@misc{koumadorakis2026enrichai,
title = {{Enrich.AI: An Agentic AI Platform for Interactive GeneSet Enrichment Analysis and Biological Interpretation}},
author = {D. E. Koumadorakis and T. P. Exarchos and P. Vlamos and A. G. Vrahatis},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.29.755561},
url = {https://www.biorxiv.org/content/10.64898/2026.09.29.755561v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Enrich.AI: An Agentic AI Platform for Interactive GeneSet Enrichment Analysis and Biological Interpretation
AU - D. E. Koumadorakis
AU - T. P. Exarchos
AU - P. Vlamos
AU - A. G. Vrahatis
PY - 2026
DA - 2026/09/29
PB - bioRxiv
DO - 10.64898/2026.09.29.755561
UR - https://www.biorxiv.org/content/10.64898/2026.09.29.755561v1
AB - 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 multiple resources to identify biologically relevant findings. Integrating AI into this process can help to bridge these gaps. Results: We present Enrich.AI, a conversational biology assistant that integrates statistical enrichment analysis with automated biological interpretation. The agent operates on an LLM-based ReAct architecture and dynamically selects among the tools for enrichment (220+ gene set libraries), literature search (40+ million publications via Europe PMC), gene annotation, and database retrieval. Given a gene list and a short description of the biological context, Enrich.AI produces a written interpretation grounded in the retrieved literature and six interactive, configurable visualizations. A conversational interface enables human-in-the-loop refinement, letting researchers without programming experience explore results iteratively. The reliability of these interpretations was validated through a systematic evaluation on 50 gene sets, demonstrating high faithfulness to retrieved evidence and a low hallucination rate.
ER -