BIOGEN: evidence-grounded multi-agent reasoning framework for transcriptomic interpretation in antimicrobial...

Interpreting gene clusters derived from RNA sequencing (RNA-seq) remains difficult in functional genomics, particularly in antimicrobial resistance studies where mechanistic context is needed for downstream hypothesis generation.

We present BIOGEN, an evidence-grounded multi-agent framework for post hoc interpretation of RNA-seq transcriptional modules that integrates biomedical retrieval, structured interpretation, and multi-critic verification. BIOGEN organizes knowledge from PubMed and UniProt into traceable cluster-level explanations with explicit evidence reporting and confidence tiering.

On the primary Salmonella enterica dataset, BIOGEN achieved strong grounding and biological coherence, with BERTScore 0.689, Semantic Alignment Score 0.715, KEGG Functional Similarity 0.342, and a non-verifiable identifier rate of 0.000, compared with 0.100 for the LLM-only baseline. Across four additional bacterial RNA-seq datasets, BIOGEN preserved zero ungrounded outputs under the identifier-based criterion. In a controlled multi-dataset comparison against representative open-source agentic AI baselines, BIOGEN was the only framework that consistently produced zero non-verifiable identifier outputs across all five datasets.

These results indicate that retrieval access alone is insufficient to ensure reliable biological interpretation. Evidence-grounded orchestration is essential for transparent, source-traceable transcriptomic reasoning under distribution shift.