Symphonizing pileup and full-alignment for deep learning-based long-read variant calling

Deep learning-based variant callers are becoming the standard and have achieved superior single nucleotide polymorphisms calling performance using long reads. Here we present Clair3, which leverages two major method categories: pileup calling handles most variant candidates with speed, and full-alig...

Full description

Saved in:
Bibliographic Details
Published inNature Computational Science Vol. 2; no. 12; pp. 797 - 803
Main Authors Zheng, Zhenxian, Li, Shumin, Su, Junhao, Leung, Amy Wing-Sze, Lam, Tak-Wah, Luo, Ruibang
Format Journal Article
LanguageEnglish
Published United States Nature Publishing Group 01.12.2022
Subjects
Algorithms
Alignment
Deep learning
Genomes
Neural networks
Nucleotides
Online AccessGet full text
ISSN2662-8457
DOI10.1038/s43588-022-00387-x

Cover

More Information
Summary:Deep learning-based variant callers are becoming the standard and have achieved superior single nucleotide polymorphisms calling performance using long reads. Here we present Clair3, which leverages two major method categories: pileup calling handles most variant candidates with speed, and full-alignment tackles complicated candidates to maximize precision and recall. Clair3 runs faster than any of the other state-of-the-art variant callers and demonstrates improved performance, especially at lower coverage.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2662-8457
DOI:10.1038/s43588-022-00387-x