«

»

BLAST performance analysis

Performance Characterization of BLAST on the Grid

BLAST (Basic Local Alignment Search Tool) is a commonly used bioinformatics application for performing query searches and analysis of biological data. As the amount of search data increases so do job search times. As means of reducing job turnaround times, scientists are resorting to new technologies such as grid computing to obtain needed computational and storage resources. Inherent with advent of new technologies, are additional complexities that arise, forcing scientists to deal with them. In case of grid computing, dynamic and transient state of heterogeneous resources are exemplified, thus becoming a major obstacle in realizing user desired levels of service. Many users do not realize that techniques used during job submission as were applied in more traditional cluster environments do not simply transition into grid environment. This projects aims at analyzing resource and application dependencies for BLAST in terms of job parameters that result in performance tradeoffs. Through a set of examples and benchmarks, we derive at observations as to which resource components, and parameters are most influential in terms of execution time and associated resource cost. These experiments lead to BLAST parameter analysis and principles that offer execution time tradeoffs one can follow when submitting BLAST jobs.

Current benchmarking results

Here are available results from experiments and benchmarks as performed for above stated analysis. [Microsoft Excel format]

People

Publications

  • Afgan E., Bangalore P., “Performance Characterization of BLAST on the Grid”, IEEE 7th International Symposium on Bioinformatics & Bioengineering (IEEE BIBE 2007), Boston, MA, Oct 14-17, 2007. PDF