Interpretable RNA-Seq Clustering with an LLM-Based Agentic Evidence-Grounded Framework
This addresses the need for more reliable and interpretable AI in biomedicine by improving RNA-seq analysis transparency, though it is incremental as it builds on existing LLM and retrieval methods.
The paper tackled the problem of interpreting RNA-seq clusters by proposing CITE V.1, a framework that uses LLMs with evidence grounding to provide transparent explanations, resulting in biologically meaningful insights for Salmonella enterica data while reducing speculative results and false citations compared to an LLM-only baseline.
We propose CITE V.1, an agentic, evidence-grounded framework that leverages Large Language Models (LLMs) to provide transparent and reproducible interpretations of RNA-seq clusters. Unlike existing enrichment-based approaches that reduce results to broad statistical associations and LLM-only models that risk unsupported claims or fabricated citations, CITE V.1 transforms cluster interpretation by producing biologically coherent explanations explicitly anchored in the biomedical literature. The framework orchestrates three specialized agents: a Retriever that gathers domain knowledge from PubMed and UniProt, an Interpreter that formulates functional hypotheses, and Critics that evaluate claims, enforce evidence grounding, and qualify uncertainty through confidence and reliability indicators. Applied to Salmonella enterica RNA-seq data, CITE V.1 generated biologically meaningful insights supported by the literature, while an LLM-only Gemini baseline frequently produced speculative results with false citations. By moving RNA-seq analysis from surface-level enrichment to auditable, interpretable, and evidence-based hypothesis generation, CITE V.1 advances the transparency and reliability of AI in biomedicine.