Title: An efficient framework for accelerating Needleman-Wunsch algorithm using GPU

Authors: Hamza Nadim; Mohamed Assal; Abdelfatah A. Hegazy

Addresses: College of Computing and Information Technology, Arab Academy for Science and Technology, Cairo, 11799, Egypt ' Faculty of Computer Science, Modern University for Technology and Information, Cairo, 11799, Egypt ' College of Computing and Information Technology, Arab Academy for Science and Technology and Maritime Transport for Information Technology and Community Service Affairs, Cairo, 11799, Egypt

Abstract: The Needleman-Wunsch algorithm is considered the benchmark for global alignment, this work proposes a new implementation for the parallel NW algorithm over the graphical processing unit (GPU). Focusing on enhancing the second phase of the algorithm (The Fill) the most time demanding phase. The idea of filling a percentage of the matrix is presented which guarantees a decrease in execution time, the key was to find the minimum needed percentage to be filled while ensuring the same result as filling the whole matrix of the algorithm. Experiments show the effectiveness of the proposed model in execution time when compared with the sequential algorithm.

Keywords: Needleman-Wunsch; GPU; graphical processing unit; CUDA; compute unified device architecture; sequence alignment; partial matrix filling.

DOI: 10.1504/IJBRA.2021.114412

International Journal of Bioinformatics Research and Applications, 2021 Vol.17 No.2, pp.101 - 110

Received: 19 Dec 2017
Accepted: 23 Jun 2018

Published online: 18 Apr 2021 *

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