ViroBioTree: A Tree-Structured Biological Evidence Retrieval Framework for Viral Protein Function Annotation
Viruses · 09.06.2026 · 18 (6) · 656
DOI: 10.3390/v18060656 ↗Kurz gefasst
Fachartikel in der Zeitschrift Viruses, online erschienen am 09.06.2026. Verfasst von Tinglian Lai und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Mathematics and Computational Science, Guilin University of Electronic Technology, Guilin 541004, China. Hauptthemen laut MEDLINE: Viral Proteins, Molecular Sequence Annotation, Computational Biology, Software. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Guangxi province, the Science and Technology Project of Guangxi, Natural Science Foundation of Guangxi province of Guodong Li.
Abstract (Originalsprache)
Accurate viral protein function annotation is essential for genomic surveillance, yet conventional retrieval-augmented generation (RAG) pipelines often fragment biological evidence into fixed-length text chunks, disrupting relationships among ORFs, annotations, structural domains, sequence motifs, residue mappings, and model-derived attention evidence. We propose ViroBioTree, a tree-structured biological evidence retrieval framework for downstream viral protein evidence review rather than a new primary annotation classifier. Built as an evidence organization layer on ViralMultiNet-derived ORF-level predictions and annotations, ViroBioTree converts sequence, annotation, structure, and attention evidence into typed biological nodes and traceable edges, then performs deterministic multi-channel recall, evidence-aware reranking, balanced TopK selection, rule-based verification, and node-cited report generation. In a demo benchmark, ViroBioTree achieved its strongest deterministic proxy performance on structure-explanation tasks, with Precision@K = 1.0, Recall@K = 1.0, and diversity = 0.52; these values reflect expected node-type and tag agreement rather than independent biological correctness. A bounded full-scale SARS-CoV-2 index contained 39,800 ORF rows, 80,000 attention records, 199,418 nodes, and 495,886 edges. In a stratified full20k diagnostic evaluation, ViroBioTree showed task-dependent advantages over LlamaIndex vector retrieval for conflict detection, evidence retrieval, and structure explanation, while LlamaIndex remained competitive or stronger for annotation-rich function annotation. A cross-family Influenza A Virus (IAV) diagnostic audit showed that the schema can represent IAV evidence namespaces while explicitly exposing missing formal ORF inputs, missing attention evidence, and unavailable residue/PDB assertions. Supplementary robustness, external sanity-check, diversity-risk, expert-evaluation, domain-tool positioning, and cross-family audit analyses supported traceability, report quality, and conservative evidence handling, but also showed that stable Precision@K under query perturbation does not necessarily imply stable retrieved evidence sets. ViroBioTree operates offline and deterministically, but does not address raw-read assembly, base calling, primary ORF prediction, or wet-lab validation. Its results should be interpreted as proxy and expert-reviewed evidence for traceable viral protein evidence retrieval and report generation rather than as direct validation of biological function annotation.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- School of Mathematics and Computational Science, Guilin University of Electronic Technology, Guilin 541004, China.
- School of Mathematics and Data Science, Changji University, Changji 831100, China.
- Guangxi Colleges and Universities Key Laboratory of Data Analysis and Computation, School of Mathematics and Computing Science, Guilin University of Electronic Technology, Guilin 541002, China.
- Center for Applied Mathematics of Guangxi, Guilin University of Electronic Technology, Guilin 541002, China.
- Academy of Excellent Engineers, Guangxi Artificial Intelligence College, Nanning 530201, China.
ORCID-Profile: Guodong Li
Förderung
- Natural Science Foundation of Guangxi province
- the Science and Technology Project of Guangxi
- Natural Science Foundation of Guangxi province of Guodong Li
- Guangxi Center for Applied Mathematics
- Guangxi Academy of Artificial Intelligence
- Innovation Project of GUET Graduate Education
Zitieren
APA
Lai, T., Liu, F., Li, G., & Hua, L. (2026). ViroBioTree: A Tree-Structured Biological Evidence Retrieval Framework for Viral Protein Function Annotation. Viruses, 18(6), 656. https://doi.org/10.3390/v18060656
Vancouver
Lai T, Liu F, Li G, Hua L. ViroBioTree: A Tree-Structured Biological Evidence Retrieval Framework for Viral Protein Function Annotation. Viruses. 2026;18(6):656. doi:10.3390/v18060656
BibTeX
@article{Lai2026,
author = {Lai, Tinglian and Liu, Fuguo and Li, Guodong and Hua, Liyan},
title = {ViroBioTree: A Tree-Structured Biological Evidence Retrieval Framework for Viral Protein Function Annotation},
journal = {Viruses},
year = {2026},
volume = {18},
number = {6},
pages = {656},
doi = {10.3390/v18060656}
}
EUVIMED