Paper Type
ERF
Abstract
Public transcriptomics repositories contain vast but fragmented gene expression data, making cross-database analysis difficult. Researchers must manually retrieve datasets, evaluate gene expression under specific conditions, and identify biologically related genes using multiple platforms such as NCBI’s Gene Expression Omnibus, Expression Atlas, and ArrayExpress. This paper proposes an LLM-enabled orchestration framework that automates transcriptomics data retrieval, expression evaluation, and gene relationship discovery. Given a set of genes associated with a biological process, the system retrieves relevant studies, evaluates differential expression across experiments, and identifies functionally related genes using pathway and ontology resources such as Gene Ontology. The LLM acts as an intelligent reasoning and integration layer that filters irrelevant results, normalizes experimental context, and synthesizes findings into structured outputs. This framework improves scalability, reproducibility, and efficiency in transcriptomics research while supporting automated biological hypothesis generation and evidence synthesis.
Paper Number
1965
Recommended Citation
Johnson-Hill, Brady K.; Sugumaran, Vijayan; and Battistuzzi, Fabia U., "From Data to Discovery: Agentic AI for Transcriptomics Research" (2026). AMCIS 2026 Proceedings. 38.
https://aisel.aisnet.org/amcis2026/conftheme/conftheme/38
From Data to Discovery: Agentic AI for Transcriptomics Research
Public transcriptomics repositories contain vast but fragmented gene expression data, making cross-database analysis difficult. Researchers must manually retrieve datasets, evaluate gene expression under specific conditions, and identify biologically related genes using multiple platforms such as NCBI’s Gene Expression Omnibus, Expression Atlas, and ArrayExpress. This paper proposes an LLM-enabled orchestration framework that automates transcriptomics data retrieval, expression evaluation, and gene relationship discovery. Given a set of genes associated with a biological process, the system retrieves relevant studies, evaluates differential expression across experiments, and identifies functionally related genes using pathway and ontology resources such as Gene Ontology. The LLM acts as an intelligent reasoning and integration layer that filters irrelevant results, normalizes experimental context, and synthesizes findings into structured outputs. This framework improves scalability, reproducibility, and efficiency in transcriptomics research while supporting automated biological hypothesis generation and evidence synthesis.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.
Comments
NEXTTRANS