GPU Accelerated PK-means Algorithm for Gene Clustering

In this paper, a novel GPU accelerated scheme for the PK-means gene clustering algorithm is proposed. According to the native particle-pair structure of the PKmeans algorithm, a fragment shader program is tailor-made to process a pair of particles in one pass for the computationintensive portion. As the output channel of a fragment consisting of 4 floating-point values is fully utilized, overhead for each data points in searching for its nearest centroid throughout the particle-pair is reduced. Experimental evaluations on three popular gene expression datasets show that the proposed GPU accelerated scheme can attain an order of magnitude speedup as compared with the original PK-means algorithm.

[1]  Jiang Lai.  A Strategy of Particle-Pair for Vector Quantization in Image Coding , 2007 .

[2]  Teuvo Kohonen,et al.  The self-organizing map , 1990 .

[3]  Graham Cameron,et al.  One-stop shop for microarray data , 2000, Nature.

[4]  Russell C. Eberhart,et al.  A new optimizer using particle swarm theory , 1995, MHS'95. Proceedings of the Sixth International Symposium on Micro Machine and Human Science.

[5]  Sushmita Mitra,et al.  Natural computing methods in bioinformatics: A survey , 2009, Inf. Fusion.

[6]  Ash A. Alizadeh,et al.  Distinct types of diffuse large B-cell lymphoma identified by gene expression profiling , 2000, Nature.

[7]  D. Botstein,et al.  The transcriptional program of sporulation in budding yeast. , 1998, Science.

[8]  Zhen Ji,et al.  PK-means: A new algorithm for gene clustering , 2008, Comput. Biol. Chem..

[9]  Randima Fernando,et al.  The CG Tutorial: The Definitive Guide to Programmable Real-Time Graphics , 2003 .

[10]  J. Bezdek,et al.  FCM: The fuzzy c-means clustering algorithm , 1984 .

[11]  D. Botstein,et al.  Cluster analysis and display of genome-wide expression patterns. , 1998, Proceedings of the National Academy of Sciences of the United States of America.

[12]  James Kennedy,et al.  Particle swarm optimization , 2002, Proceedings of ICNN'95 - International Conference on Neural Networks.

[13]  Tao Jiang,et al.  Algorithmic Approaches to Clustering Gene Expression Data , 2002 .

[14]  D. Botstein,et al.  Cluster analysis and display of genome-wide expression patterns. , 1998, Proceedings of the National Academy of Sciences of the United States of America.

[15]  Michael Ruogu Zhang,et al.  Comprehensive identification of cell cycle-regulated genes of the yeast Saccharomyces cerevisiae by microarray hybridization. , 1998, Molecular biology of the cell.