Abstract
Current genomic analyses often require the managing and comparison of big data using desktop bioinformatic software that was not developed regarding multicore distribution. The task-farm SCBI_MAPREDUCE is intended to simplify the trivial parallelisation and distribution of new and legacy software and scripts for biologists who are interested in using computers but are not skilled programmers. In the case of legacy applications, there is no need of modification or rewriting the source code. It can be used from multicore workstations to heterogeneous grids. Tests have demonstrated that speed-up scales almost linearly and that distribution in small chunks increases it. It is also shown that SCBI_MAPREDUCE takes advantage of shared storage when necessary, is fault-tolerant, allows for resuming aborted jobs, does not need special hardware or virtual machine support, and provides the same results than a parallelised, legacy software. The same is true for interrupted and relaunched jobs. As proof-of-concept, distribution of a compiled version of BLAST+ in the SCBI_DISTRIBUTED_BLAST gem is given, indicating that other blast binaries can be used while maintaining the same SCBI_DISTRIBUTED_BLAST code. Therefore, SCBI_MAPREDUCE suits most parallelisation and distribution needs in, for example, gene and genome studies.
Highlights
The study of genomes is undergoing a revolution: the production of an ever-growing amount of sequences increases year by year at a rate that outpaces computing performance [1]
This paper describes SCBI MapReduce, a new task-farm skeleton for the Ruby scripting language [32] that gathers the requirements presented in the Introduction, and simplifies the creation of parallel and distributed software to researchers without skills in distributed programming
Basic Local Alignment Search Tool (Blast) [4] is the tool most frequently used for calculating sequence similarity, usually being the computationally intensive part of most genomic analyses
Summary
The study of genomes is undergoing a revolution: the production of an ever-growing amount of sequences increases year by year at a rate that outpaces computing performance [1]. This huge amount of sequences needs to be processed with the well-proven algorithms that will not run faster in new computer chips since around 2003 chipmakers discovered that they were no longer able to sustain faster sequential execution except for generating the multicore chips [2, 3]. Paired sequence comparison is inherently a parallel process in which many sequence pairs can be analysed at the same time by means of functions or algorithms that are iteratively performed over sequences. This is impelling the parallelisation of sequence comparison algorithms [5,6,7,8,9] as well as other bioinformatic algorithms [10, 11]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
