NPSV-deep: a deep learning method for genotyping structural variants in short read genome sequencing data.

Journal: Bioinformatics (Oxford, England)
PMID:

Abstract

MOTIVATION: Structural variants (SVs) play a causal role in numerous diseases but can be difficult to detect and accurately genotype (determine zygosity) with short-read genome sequencing data (SRS). Improving SV genotyping accuracy in SRS data, particularly for the many SVs first detected with long-read sequencing, will improve our understanding of genetic variation.

Authors

  • Michael D Linderman
    Department of Computer Science, Middlebury College, Middlebury, VT 05753, United States.
  • Jacob Wallace
    Department of Computer Science, Middlebury College, Middlebury, VT 05753, United States.
  • Alderik van der Heyde
    Department of Computer Science, Middlebury College, Middlebury, VT 05753, United States.
  • Eliza Wieman
    Department of Computer Science, Middlebury College, Middlebury, VT 05753, United States.
  • Daniel Brey
    Department of Computer Science, Middlebury College, Middlebury, VT 05753, United States.
  • Yiran Shi
    Department of Computer Science, Middlebury College, Middlebury, VT 05753, United States.
  • Peter Hansen
    Department of Computer Science, Middlebury College, Middlebury, VT 05753, United States.
  • Zahra Shamsi
    Google, Mountain View, CA 94043, United States.
  • Jeremiah Liu
    Google, Mountain View, CA 94043, United States.
  • Bruce D Gelb
    Mindich Child Health and Development Institute, Departments of Pediatrics and Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, NY, USA.
  • Ali Bashir
    Google Research, Mountain View, CA, USA.