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

Journal: Nature computational science
Published Date:

Abstract

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.

Authors

  • Zhenxian Zheng
    Department of Computer Science, The University of Hong Kong, Hong Kong, China.
  • Shumin Li
    School of Computer Science and Technology, Harbin Institute of Technology Shenzhen Graduate School, Shenzhen, Guangdong 518055, China.
  • Junhao Su
    School of Civil and Transportation Engineering, Guangdong University of Technology, Guangzhou 510006, PR China.
  • Amy Wing-Sze Leung
    Department of Computer Science, The University of Hong Kong, Hong Kong, China.
  • Tak-Wah Lam
    Department of Computer Science, The University of Hong Kong, Hong Kong, 999077, China.
  • Ruibang Luo
    Department of Computer Science, The University of Hong Kong, Hong Kong, 999077, China. rbluo@cs.hku.hk.