HELLO: improved neural network architectures and methodologies for small variant calling.

Journal: BMC bioinformatics
PMID: 34391391

Abstract

BACKGROUND: Modern Next Generation- and Third Generation- Sequencing methods such as Illumina and PacBio Circular Consensus Sequencing platforms provide accurate sequencing data. Parallel developments in Deep Learning have enabled the application of Deep Neural Networks to variant calling, surpassing the accuracy of classical approaches in many settings. DeepVariant, arguably the most popular among such methods, transforms the problem of variant calling into one of image recognition where a Deep Neural Network analyzes sequencing data that is formatted as images, achieving high accuracy. In this paper, we explore an alternative approach to designing Deep Neural Networks for variant calling, where we use meticulously designed Deep Neural Network architectures and customized variant inference functions that account for the underlying nature of sequencing data instead of converting the problem to one of image recognition.

Authors

  • Anand Ramachandran
    Department of Electrical and Computer Engineering, University of Illinois At Urbana-Champaign, Urbana, IL, 61801, USA.
  • Steven S Lumetta
    Department of Electrical and Computer Engineering, University of Illinois At Urbana-Champaign, Urbana, IL, 61801, USA.
  • Eric W Klee
    Biomedical Statistics and Informatics, Department of Quantitative Health Sciences, Mayo Clinic, Rochester, MN, USA.
  • Deming Chen
    Department of Electrical and Computer Engineering, University of Illinois At Urbana-Champaign, Urbana, IL, 61801, USA. dchen@illinois.edu.

Keywords

External Resources

Popular Topics
Recent Journals