BIOGEN: Evidence-Grounded Multi-Agent Reasoning Framework for Transcriptomic Interpretation in Antimicrobial Resistance
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911563333500928 |
|---|---|
| author | Hossain, Elias Shoeibi, Mehrdad Garibay, Ivan Yousefi, Niloofar |
| author_facet | Hossain, Elias Shoeibi, Mehrdad Garibay, Ivan Yousefi, Niloofar |
| contents | Interpreting gene clusters from RNA sequencing (RNA-seq) remains challenging, especially in antimicrobial resistance studies where mechanistic insight is important for hypothesis generation. Existing pathway enrichment methods can summarize co-expressed modules, but they often provide limited cluster-specific explanations and weak connections to supporting literature. We present BIOGEN, an evidence-grounded multi-agent framework for post hoc interpretation of RNA-seq transcriptional modules. BIOGEN combines biomedical retrieval, structured reasoning, and multi-critic verification to generate traceable cluster-level explanations with explicit evidence and confidence labels. On a primary Salmonella enterica dataset, BIOGEN achieved strong biological grounding, including BERTScore 0.689, Semantic Alignment Score 0.715, KEGG Functional Similarity 0.342, and a hallucination rate of 0.000, compared with 0.100 for an LLM-only baseline. Across four additional bacterial RNA-seq datasets, BIOGEN also maintained zero hallucination under the same fixed pipeline. In comparisons with representative open-source agentic AI baselines, BIOGEN was the only framework that consistently preserved zero hallucination across all five datasets. These findings suggest that retrieval alone is not enough for reliable biological interpretation, and that evidence-grounded orchestration is important for transparent and source-traceable transcriptomic reasoning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_16082 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | BIOGEN: Evidence-Grounded Multi-Agent Reasoning Framework for Transcriptomic Interpretation in Antimicrobial Resistance Hossain, Elias Shoeibi, Mehrdad Garibay, Ivan Yousefi, Niloofar Quantitative Methods Artificial Intelligence Machine Learning Interpreting gene clusters from RNA sequencing (RNA-seq) remains challenging, especially in antimicrobial resistance studies where mechanistic insight is important for hypothesis generation. Existing pathway enrichment methods can summarize co-expressed modules, but they often provide limited cluster-specific explanations and weak connections to supporting literature. We present BIOGEN, an evidence-grounded multi-agent framework for post hoc interpretation of RNA-seq transcriptional modules. BIOGEN combines biomedical retrieval, structured reasoning, and multi-critic verification to generate traceable cluster-level explanations with explicit evidence and confidence labels. On a primary Salmonella enterica dataset, BIOGEN achieved strong biological grounding, including BERTScore 0.689, Semantic Alignment Score 0.715, KEGG Functional Similarity 0.342, and a hallucination rate of 0.000, compared with 0.100 for an LLM-only baseline. Across four additional bacterial RNA-seq datasets, BIOGEN also maintained zero hallucination under the same fixed pipeline. In comparisons with representative open-source agentic AI baselines, BIOGEN was the only framework that consistently preserved zero hallucination across all five datasets. These findings suggest that retrieval alone is not enough for reliable biological interpretation, and that evidence-grounded orchestration is important for transparent and source-traceable transcriptomic reasoning. |
| title | BIOGEN: Evidence-Grounded Multi-Agent Reasoning Framework for Transcriptomic Interpretation in Antimicrobial Resistance |
| topic | Quantitative Methods Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2510.16082 |