VirProtRAG: Literature-grounded viral protein function annotation with retrieval-augmented generation

VirProtRAG is a viral protein function annotation framework that reformulates the task as an integrated process of information retrieval and evidence‑grounded knowledge generation. VirProtRAG introduces three task-adapted components: (i) a hybrid retrieval module combining keyword‑based and semantic dense retrieval to maximize literature coverage, (ii) synonym‑expanded, rank‑aware retrieval with reciprocal rank fusion for improved search effectiveness, and (iii) literature quality and evidence‑oriented re‑ranking to enhance reliability and interpretability.