In search of clusters: the coming battle in lowly parallel computing
In search of clusters: the coming battle in lowly parallel computing
Algorithms on strings, trees, and sequences: computer science and computational biology
Algorithms on strings, trees, and sequences: computer science and computational biology
A linear space algorithm for computing maximal common subsequences
Communications of the ACM
A guided tour to approximate string matching
ACM Computing Surveys (CSUR)
Parallel biological sequence comparison using prefix computations
Journal of Parallel and Distributed Computing
Space and Time Optimal Parallel Sequence Alignments
IEEE Transactions on Parallel and Distributed Systems
Parallel smith-waterman algorithm for local DNA comparison in a cluster of workstations
WEA'05 Proceedings of the 4th international conference on Experimental and Efficient Algorithms
CUDAlign: using GPU to accelerate the comparison of megabase genomic sequences
Proceedings of the 15th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming
A HMMER hardware accelerator using divergences
Proceedings of the Conference on Design, Automation and Test in Europe
A protein sequence analysis hardware accelerator based on divergences
International Journal of Reconfigurable Computing - Special issue on High-Performance Reconfigurable Computing
| Hi-index | 0.00 |
Recently, many organisms had their DNA entirely sequenced, and this reality presents the need for aligning long DNA sequences, which is a challenging task due to its high demands for computational power and memory. The algorithm proposed by Smith-Waterman (SW) is an exact method that obtains optimal local alignments in quadratic space and time. For long sequences, quadratic complexity makes the use of this algorithm impractical. In this scenario, parallel computing is a very attractive alternative. In this paper, we propose and evaluate z-align, a parallel exact strategy based on the divergence concept to locally align long biological sequences using an affine gap function. Z-align runs in limited memory space, where the amount of memory used can be defined by the user. The results collected in a cluster with 16 processors presented very good speedups for long real DNA sequences. With z-align, we were able to compare up to 3MBP (mega base-pairs) DNA sequences. As far as we know, this is the first time 3MBP sequences are compared with an affine gap exact variation of the SW algorithm. Also, by comparing the results obtained with z-align and the popular BLAST tool, it is clear that z-align is able to produce longer and more significant alignments.