The course of parallelism in Bioinformatics: which R parallelization scheme to use?

FERREYRA, NICOLÁS EMANUEL; MARZIONI, EMILIANO; FRESNO, CRISTOBAL; OLIVERA, ANIBAL; VENIER, GERARDO; PRATO, LAURA; FERNÁNDEZ, ELMER ANDRÉS

Rosario (Santa Fe)

Congreso; 4to. Congreso Argentino de Bioinformática y Biología Computacional (4CAB2C); 2013

Asociación Argentina de Bioinformática y Biología Computacional + Sociedad Iberoamericana de Bioinformática

Bioinformatics it´s a complex field that requires a lot of computational cost. R software[1] provides libraries that help us solve several problems from that field, but most of them are implemented sequentially. However, R also provides libraries that enable the parallel processing applying several techniques. Unfortunately, to date there is no works for efficiency comparisons of R parallel techniques. This fact leave us with an important question to answer: which technique should I use for my problem? Here, we evaluate the solution of a parameter estimation on matrix through columns permutation (typical problem in bioinformatics).