aiqbench analysis
This research applies Large Language Model-based Retrieval-Augmented Generation (RAG) to solve a specific bottleneck in computational biology: predicting gene functions in non-model organisms where traditional homology methods fail. By integrating biological orthology data into the retrieval process and using an Evidence Confidence Score, the Homo-RAG framework significantly improves the accuracy of functional annotation for understudied species. The study demonstrates that combining semantic relevance with domain-specific biological relationships creates a robust pipeline for evidence-grounded gene prediction.
Homo-RAG: Homology-Guided Retrieval-Augmented Generation for Cross-Species Gene Function Prediction
arXiv:2608.25466v1 Announce Type: cross Abstract: The functional annotation of genes in non-model organisms remains a significant challenge in computational biology, with 20-70% of sequenced genes lacking characterized functions. Traditional homology-based methods are often costly and strongly dependent on high sequence similarity. This study presents Homo-RAG, a framework for large language model-based gene function prediction that integrates homology-guided multi-hop retrieval with evidence-aware ranking. The framework exploits biological relationships between zebrafish and human orthologs to guide evidence acquisition from ZFIN, UniProt, and PubMed through hybrid dense and lexical retrieval. An Evidence Confidence Score (ECS) integrates semantic relevance, entity matching, orthology information, source reliability, and literature association signals to refine the ranking of retrieved evidence. Extensive evaluation across 150 queries and 7,200 retrieved documents shows that evidence weighting parameter of lambda=0.50 improves NDCG@10 to 0.9879 and MRR to 0.99, while retrieving relevant evidence for 99.33% of queries. Furthermore, 80% of the retrieved documents are query-exclusive, indicating that evidence quality complements rather than replaces retrieval relevance. These findings establish Homo-RAG as a practical and robust framework for reliable, evidence-grounded gene function prediction in understudied organisms. The study addresses important limitations of conventional annotation pipelines while identifying opportunities for future improvements in evidence features and attribution mechanisms.
Abstract:The functional annotation of genes in non-model organisms remains a significant challenge in computational biology, with 20-70% of sequenced genes lacking characterized functions. Traditional homology-based methods are often costly and strongly dependent on high sequence similarity. This study presents Homo-RAG, a framework for large language model-based gene function prediction that integrates homology-guided multi-hop retrieval with evidence-aware ranking. The framework exploits biological relationships between zebrafish and human orthologs to guide evidence acquisition from ZFIN, UniProt, and PubMed through hybrid dense and lexical retrieval. An Evidence Confidence Score (ECS) integrates semantic relevance, entity matching, orthology information, source reliability, and literature association signals to refine the ranking of retrieved evidence. Extensive evaluation across 150 queries and 7,200 retrieved documents shows that evidence weighting parameter of lambda=0.50 improves NDCG@10 to 0.9879 and MRR to 0.99, while retrieving relevant evidence for 99.33% of queries. Furthermore, 80% of the retrieved documents are query-exclusive, indicating that evidence quality complements rather than replaces retrieval relevance. These findings establish Homo-RAG as a practical and robust framework for reliable, evidence-grounded gene function prediction in understudied organisms. The study addresses important limitations of conventional annotation pipelines while identifying opportunities for future improvements in evidence features and attribution mechanisms.
Neural and Evolutionary Computing (cs.NE); Artificial Intelligence (cs.AI)
arXiv:2608.25466 [cs.NE]
(or arXiv:2608.25466v1 [cs.NE] for this version)
https://doi.org/10.48550/arXiv.2608.25466 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 294 words
Related coverage
Graph2Idea:Retrieval-Augmented Scientific Idea Generation with Graph-Structured Contexts
arXiv · Jun 10, 2026
Graph2Idea:Retrieval-Augmented Scientific Idea Generation with Graph-Structured Contexts
arXiv · Jun 9, 2026
VisRAG2.0: Mitigating Visual Hallucinations via Evidence-Guided Multi-Image Reasoning in Visual Retrieval-Augmented Generation
arXiv · Jul 29, 2026
CrossModalQA: A Cross-modal and Multi-hop Benchmark for Multimodal Retrieval-augmented Generation
arXiv · Sep 9, 2026