Dual-SVF: a robust knowledge-guided multimodal method for structural variant filtering in long-read sequencing
Briefings in Bioinformatics · 2026
DOI: 10.1093/bib/bbag448 ↗Kurz gefasst
Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2026. Verfasst von Chunxiao Lai und 4 weiteren Autor:innen. Beteiligte Einrichtung: Sanya Science and Education Innovation Park, Wuhan University of Technology, Building 9, Yonyou Industrial Park, Yazhou Bay Science and Technology Ci…. Hauptthemen laut MEDLINE: High-Throughput Nucleotide Sequencing, Sequence Analysis, DNA, Genomics, Software. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key R&D Program of China.
Abstract (Originalsprache)
Structural variants (SVs) are key drivers of genomic diversity and disease, yet their accurate detection from long-read sequencing remains challenged by high false-positive rates caused by sequencing errors and alignment artifacts. Current filtering approaches predominantly rely on alignment structure, often overlooking sequence content and genomic context knowledge, which undermines the robustness of SV detection. To address these issues, we present Dual-SVF, a robust knowledge-guided multimodal method for SV filtering that jointly models genomic semantics (from raw sequence content) and syntactics (from sequence alignment topology). Dual-SVF integrates genomic prior knowledge, including sequence entropy, GC content, and mapping quality, through a confidence-gated cross-attention mechanism that dynamically weights modality reliability and enables mutual error correction. Validation across diverse sequencing platforms and multiple species demonstrates that Dual-SVF consistently achieves superior performance compared with state-of-the-art methods. Dual-SVF is an open-source, VCF-compatible tool, which seamlessly complements existing pipelines to ensure reliable SV filtering across noisy genomic data.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Sanya Science and Education Innovation Park, Wuhan University of Technology, Building 9, Yonyou Industrial Park, Yazhou Bay Science and Technology City, Sanya, Hainan 572024, China.
- School of Computer Science and Artificial Intelligence, Wuhan University of Technology, No. 21 Gongda Road, Hongshan District, Wuhan, Hubei 430070, China.
- Wuhan Second Ship Design and Research Institute, No. 450 Zhongshan Road, Wuchang District, Wuhan, Hubei 430064, China.
- Engineering Research Centre of Chinese Ministry of Education for Edible and Medicinal Fungi, Jilin Agricultural University, No. 2888 Xincheng Street, Jingyue District, Changchun, Jilin 130118, China.
- Yazhouwan National Laboratory, No. 8 Huanjin Road, Yazhou Bay Science and Technology City, Sanya, Hainan 572024, China.
ORCID-Profile: Chunxiao Lai
Förderung
- National Key R&D Program of China
Zitieren
APA
Lai, C., Zhang, H., Cheng, C., Peng, J., & Yuan, X. (2026). Dual-SVF: a robust knowledge-guided multimodal method for structural variant filtering in long-read sequencing. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbag448
Vancouver
Lai C, Zhang H, Cheng C, Peng J, Yuan X. Dual-SVF: a robust knowledge-guided multimodal method for structural variant filtering in long-read sequencing. Briefings in Bioinformatics. 2026. doi:10.1093/bib/bbag448
BibTeX
@article{Lai2026,
author = {Lai, Chunxiao and Zhang, Haohao and Cheng, Chong and Peng, Jing and Yuan, Xiaohui},
title = {Dual-SVF: a robust knowledge-guided multimodal method for structural variant filtering in long-read sequencing},
journal = {Briefings in Bioinformatics},
year = {2026},
doi = {10.1093/bib/bbag448}
}
EUVIMED