Title: A GPU-CPU heterogeneous algorithm for NGS read alignment

Authors: Ahmad Al Kawam; Sunil Khatri; Aniruddha Datta

Addresses: Department of Electrical and Computer Engineering, Texas A&M University, College Station, Texas 77840, USA ' Department of Electrical and Computer Engineering, Texas A&M University, College Station, Texas 77840, USA ' Department of Electrical and Computer Engineering, Texas A&M University, College Station, Texas 77840, USA

Abstract: In the next generation sequencing (NGS) read alignment problem, millions of deoxyribonucleic acid (DNA) fragments, called reads, are mapped to a reference genome. Read alignment is typically carried out using traditional computing platforms, which have become a limiting factor in the speed of the process. The massive scale of the problem makes it an attractive target for acceleration. In this paper, we design a read alignment algorithm designed to run on a heterogeneous system composed of a graphics processing unity (GPU) and a multicore central processing unit (CPU). We introduce novel techniques for the alignment process and construct a computational pipeline of overlapped CPU and GPU stages. We compare our tool with the BWA-mem alignment tool, and the results show substantial speedups.

Keywords: NGS; next generation sequencing; read alignment; GPU acceleration.

DOI: 10.1504/IJCBDD.2018.090840

International Journal of Computational Biology and Drug Design, 2018 Vol.11 No.1/2, pp.52 - 66

Received: 11 Mar 2017
Accepted: 16 Sep 2017
Published online: 28 Mar 2018 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article