IAN is a gene expression interpretation system released by the research team at the National Eye Institute, under the U.S. National Institutes of Health (NIH), on June 17, 2026. When researchers input gene expression analysis results and a list of Differentially Expressed Genes (DEG), multiple specialized AI agents cross-analyze various biological databases such as KEGG, Reactome, Gene Ontology, and STRING. The system then integrates key regulators, biological pathways, protein interactions, and pathway networks into a single interpretation, compiling the findings into an auditable HTML report. This process effectively simulates within software the workflow of domain-expert researchers reviewing experimental results through their respective expertise to produce a collaborative report. Conventional DEG analysis requires running separate tools for each database, aligning disparate identifiers and significance metrics, and manually interpreting overlapping or conflicting pathways. In this traditional approach, even when a statistically significant list of genes is obtained, it remains difficult to explain which upstream regulators drove the changes or how individual pathways connect to form a coherent biological phenomenon. IAN’s key differentiator lies in deploying specialized agents for each database rather than relying on a single general-purpose model, thereby linking individual analysis results into an integrated biological explanation. Much like GPT synthesizes core arguments by reading multiple documents, IAN reconstructs scattered omics evidence into explanations centered on pathways and interactions. Researchers can provide gene expression results and DEG lists generated from RNA-seq pipelines to IAN to compare potentially activated pathways in KEGG and Reactome, while supplementing related biological processes and molecular functions via Gene Ontology. By combining protein interaction data from STRING with key regulator analysis, a simple ranked list of genes can be evolved into a candidate mechanism network. The generated HTML report can serve as a starting point for selecting follow-up experimental candidates, comparing transcriptomic responses across different conditions, or enabling collaborative research teams to review the analytical basis. IAN holds particular value in studies interpreting gene expression differences between conditions, such as disease versus control groups or drug-treated versus untreated cohorts. Based on the regulator and pathway networks connected by IAN, researchers can establish validation priorities and design additional expression measurements or functional assays for candidate genes. However, input formats, supported parameters, execution environments, model configurations, evidence tracing methods, and the reproducibility scope of reports could not be confirmed solely from the provided discovery information. Furthermore, since the license distinguishes between non-commercial use and other usage conditions, it is essential to verify the repository’s official terms and obtain separate permission from the development team before applying IAN to corporate research or product development.

IAN is a gene expression interpretation system released by the research team at the National Eye Institute under the U.S. National Institutes of Health (NIH) on June 17, 2026. When researchers input gene expression analysis results and a list of differentially expressed genes (DEGs), multiple specialized AI agents cross-analyze data across various biological databases such as KEGG, Reactome, Gene Ontology, and STRING. It then identifies key regulators and biological pathways

Transcriptomic Pathway Analysis: Input gene expression results and DEG lists obtained from RNA-seq analysis, and cross-reference KEGG and Reactome pathway analyses with Gene Ontology annotations. Summarize key regulators and associated pathways in an HTML report to prioritize targets for downstream functional validation.