SVision: a deep learning approach to resolve complex structural variants.

Journal: Nature methods
Published Date: Sep 16, 2022

Abstract

Complex structural variants (CSVs) encompass multiple breakpoints and are often missed or misinterpreted. We developed SVision, a deep-learning-based multi-object-recognition framework, to automatically detect and haracterize CSVs from long-read sequencing data. SVision outperforms current callers at identifying the internal structure of complex events and has revealed 80 high-quality CSVs with 25 distinct structures from an individual genome. SVision directly detects CSVs without matching known structures, allowing sensitive detection of both common and previously uncharacterized complex rearrangements.

Authors

  • Jiadong Lin
    MOE Key Lab for Intelligent Networks & Networks Security, Faculty of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an, China.
  • Songbo Wang
    MOE Key Lab for Intelligent Networks & Networks Security, Faculty of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an, China.
  • Peter A Audano
    The Jackson Laboratory for Genomic Medicine, Farmington, CT, USA.
  • Deyu Meng
  • Jacob I Flores
    The Jackson Laboratory for Genomic Medicine, Farmington, CT, USA.
  • Walter Kosters
    Leiden Institute of Advanced Computer Science, Faculty of Science, Leiden University, Leiden, the Netherlands.
  • Xiaofei Yang
    Guizhou University, Guiyang, China Guizhou University Guiyang China.
  • Peng Jia
    GeoHealth Initiative, Faculty of Geo-information Science and Earth Observation (ITC), University of Twente, Enschede, 7500, the Netherlands; International Initiative on Spatial Lifecourse Epidemiology (ISLE), the Netherlands. Electronic address: p.jia@utwente.nl.
  • Tobias Marschall
    Heinrich Heine University, Medical Faculty, Institute for Medical Biometry and Bioinformatics, Dusseldorf, Germany.
  • Christine R Beck
    The Jackson Laboratory for Genomic Medicine, Farmington, CT, USA.
  • Kai Ye
    MandalaT Software Corporation, F5, Wuxi, China.

Keywords

External Resources

Popular Topics
Recent Journals