Parallel Position Weight Matrices algorithms

Position Weight Matrices (PWMs) are broadly used in computational biology. The basic problems, Scan and MultipleScan, aim to find all the occurrences of a given PWM or a set of PWMs in long sequences. Some other PWM tasks share a common NP-hard subproblem, ScoreDistribution. The existing algorithms rely on the enumeration on a large set of scores or words, and they are mostly not suitable for parallelization. We propose a new algorithm, BucketScoreDistribution, that is both very efficient and suitable for parallelization. We bound the error induced by this algorithm. We realized a GPU prototype for Scan, MultipleScan and BucketScoreDistribution with the CUDA libraries, and report for the different problems speedups larger than 10× on several Nvidia cards.

Research highlights
► Study of several PWMs (Position Weight Matrices) problems for bioinformatics.
► Simple and efficient parallelization of the Scan problem.
► New parallel algorithm, BucketScoreDistribution, for scores and P-values estimations.
► Speed-ups larger than 10× on several NVIDIA cards.