SVision: a deep learning approach to resolve complex structural variants

Jiadong Lin; Songbo Wang; Peter A Audano; Deyu Meng; Jacob I Flores; Walter Kosters; Xiaofei Yang; Peng Jia; Tobias Marschall; Christine R Beck; Kai Ye

doi:10.1038/s41592-022-01609-w

SVision: a deep learning approach to resolve complex structural variants

Nat Methods. 2022 Oct;19(10):1230-1233. doi: 10.1038/s41592-022-01609-w. Epub 2022 Sep 16.

Authors

Jiadong Lin^#^{1

2

3

4}, Songbo Wang^#^{1

2

3}, Peter A Audano⁵, Deyu Meng^{1

6

7}, Jacob I Flores⁵, Walter Kosters⁴, Xiaofei Yang^{1

8}, Peng Jia^{1

2

3}, Tobias Marschall⁹, Christine R Beck^{5

10}, Kai Ye^{11

12

13

14

15}

Affiliations

¹ MOE Key Lab for Intelligent Networks & Networks Security, Faculty of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an, China.
² School of Automation Science and Engineering, Faculty of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an, China.
³ Genome Institute, the First Affiliated Hospital of Xi'an Jiaotong University, Xi'an, China.
⁴ Leiden Institute of Advanced Computer Science, Faculty of Science, Leiden University, Leiden, the Netherlands.
⁵ The Jackson Laboratory for Genomic Medicine, Farmington, CT, USA.
⁶ School of Mathematics and Statistics, Xi'an Jiaotong University, Xi'an, China.
⁷ Macau Institute of Systems Engineering, Macau University of Science and Technology, Taipa, Macau.
⁸ School of Computer Science and Technology, Faculty of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an, China.
⁹ Heinrich Heine University, Medical Faculty, Institute for Medical Biometry and Bioinformatics, Dusseldorf, Germany.
¹⁰ Department of Genetics and Genome Sciences, Institute for Systems Genomics, University of Connecticut Health Center, Farmington, CT, USA.
¹¹ MOE Key Lab for Intelligent Networks & Networks Security, Faculty of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an, China. kaiye@xjtu.edu.cn.
¹² School of Automation Science and Engineering, Faculty of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an, China. kaiye@xjtu.edu.cn.
¹³ Genome Institute, the First Affiliated Hospital of Xi'an Jiaotong University, Xi'an, China. kaiye@xjtu.edu.cn.
¹⁴ The School of Life Science and Technology, Xi'an Jiaotong University, Xi'an, China. kaiye@xjtu.edu.cn.
¹⁵ Faculty of Science, Leiden University, Leident, the Netherlands. kaiye@xjtu.edu.cn.

^# Contributed equally.

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.

SVision: a deep learning approach to resolve complex structural variants

Authors

Affiliations

Abstract

Publication types

MeSH terms

Grants and funding