SVision: a deep learning approach to resolve complex structural variants

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 characterize CSVs from long-read sequencing data. SVision outperforms current callers...

Full description

Saved in:
Bibliographic Details
Published inNature methods Vol. 19; no. 10; pp. 1230 - 1233
Main Authors Lin, Jiadong, Wang, Songbo, Audano, Peter A., Meng, Deyu, Flores, Jacob I., Kosters, Walter, Yang, Xiaofei, Jia, Peng, Marschall, Tobias, Beck, Christine R., Ye, Kai
Format Journal Article
LanguageEnglish
Published New York Nature Publishing Group US 01.10.2022
Nature Publishing Group
Subjects
631/114/1305
631/114/2785
631/1647/794
631/208/212
Automation
Bioinformatics
Biological Microscopy
Biological Techniques
Biomedical and Life Sciences
Biomedical Engineering/Biotechnology
Breakpoints
Brief Communication
Computer science
Deep Learning
Engineering
Genome
Genomes
Graph representations
High-Throughput Nucleotide Sequencing
Illustrators
Image coding
Life Sciences
Neural networks
Object recognition
Proteomics
Sequence Analysis, DNA
Online AccessGet full text
ISSN1548-7091
1548-7105
1548-7105
DOI10.1038/s41592-022-01609-w

Cover

More Information
Summary: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 characterize 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 is a deep-learning-based method that can sensitively and accurately detect and characterize complex structural variants using long-read sequencing data.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
These authors contributed equally.
K.Y designed and supervised research; J.L and S.W developed the algorithm and software; D.M contributed to the assessment and analysis of deep learning model; W.K, T.M and P.A provided constructive suggestions for the algorithm; J.L performed the algorithm benchmarking on real data and complex structural variants analysis; S.W performed algorithm benchmarking on the simulated data. P.A.A, J.I.F, and C.R.B contributed to the analysis and experimental validation of complex structural variants; P.J and X.Y contributed to the sequencing data processing; J.L, W.K, P.A.A, C.R.B and K.Y wrote the paper with input from all other authors. All authors read and approved the final manuscript.
Author contributions
ISSN:1548-7091
1548-7105
1548-7105
DOI:10.1038/s41592-022-01609-w