EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SVHunter: long-read-based structural variation detection through the transformer model

Runtian Gao iD, Heng Hu iD, Zhongjun Jiang, Shuqi Cao, Guohua Wang iD, Yuming Zhao iD, Tao Jiang

Briefings in Bioinformatics · 2025

DOI: 10.1093/bib/bbaf203 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2025. Verfasst von Runtian Gao und 6 weiteren Autor:innen. Beteiligte Einrichtung: College of Life Science, Northeast Forestry University, Harbin 150000, China. Hauptthemen laut MEDLINE: Genomic Structural Variation, Genome, Human, Software. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, National Science Foundation for Distinguished Young Scholars of China, National Key R&D Program of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Structural variations (SVs) are genomic rearrangements larger than 50 bp, that are widely present in the human genome and are associated with various complex diseases. Existing long-read-based SV detection tools often rely on fixed rules or heuristic algorithms, which can oversimplify the complexity of SV signatures. Therefore, these methods usually lack flexibility and cannot fully capture SV signals, leading to reduced accuracy and robustness. To address these issues, we propose SVHunter, a transformer-based method for long-read SV detection. SVHunter combines convolutional neural networks and transformers to capture both local and global SV signatures, enabling accurate identification of SVs. Additionally, SVHunter employs the mean shift clustering algorithm, which dynamically adjusts bandwidth parameters to accommodate different types of SVs without requiring a preset number of clusters, thus allowing precise breakpoint clustering. Validation across multiple sequencing platforms and datasets demonstrates that SVHunter excels at detecting various types of SVs, with a notable reduction in the false discovery rate. This highlights considerable strong potential for both research and clinical applications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Genomic Structural VariationGenome, HumanSoftwareHumansAlgorithmsNeural Networks, ComputerGenomicsComputational Biology

Stichwörter der Autor:innen

dynamical clusteringlong-read sequencingstructural variationtransformer model

Autor:innen und Institutionen

  • College of Life Science, Northeast Forestry University, Harbin 150000, China.
  • College of Computer and Control Engineering, Northeast Forestry University, Harbin 150000, China.
  • School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China.

ORCID-Profile: Runtian Gao, Heng Hu, Guohua Wang, Yuming Zhao

Förderung

  • National Natural Science Foundation of China
  • National Science Foundation for Distinguished Young Scholars of China
  • National Key R&D Program of China

Zitieren

APA

Gao, R., Hu, H., Jiang, Z., Cao, S., Wang, G., Zhao, Y., & Jiang, T. (2025). SVHunter: long-read-based structural variation detection through the transformer model. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbaf203

Vancouver

Gao R, Hu H, Jiang Z, Cao S, Wang G, Zhao Y, et al. SVHunter: long-read-based structural variation detection through the transformer model. Briefings in Bioinformatics. 2025. doi:10.1093/bib/bbaf203

BibTeX
@article{Gao2025,
  author = {Gao, Runtian and Hu, Heng and Jiang, Zhongjun and Cao, Shuqi and Wang, Guohua and Zhao, Yuming and Jiang, Tao},
  title = {SVHunter: long-read-based structural variation detection through the transformer model},
  journal = {Briefings in Bioinformatics},
  year = {2025},
  doi = {10.1093/bib/bbaf203}
}
Kostenlos starten →