GPU-Based biclustering for neural information processing

Authors:
Alan W. Y. Lo;Benben Liu;Ray C. C. Cheung
Affiliations:
Department of Electronic Engineering, City University of Hong Kong, Hong Kong;Department of Electronic Engineering, City University of Hong Kong, Hong Kong;Department of Electronic Engineering, City University of Hong Kong, Hong Kong
Venue:
ICONIP'12 Proceedings of the 19th international conference on Neural Information Processing - Volume Part V
Year:
2012

Citing 5
Cited 1

Biclustering of Expression Data

Proceedings of the Eighth International Conference on Intelligent Systems for Molecular Biology
Information-theoretic co-clustering

Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining
Biclustering Algorithms for Biological Data Analysis: A Survey

IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB)
A comparison of CPUs, GPUs, FPGAs, and massively parallel processor arrays for random number generation

Proceedings of the ACM/SIGDA international symposium on Field programmable gate arrays
Clustering categorical data using an extended modularity measure

ICONIP'10 Proceedings of the 17th international conference on Neural information processing: models and applications - Volume Part II

GPU-based biclustering for microarray data analysis in neurocomputing

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents an efficient mapping of geometric biclustering (GBC) algorithm for neural information processing on Graphical Processing Unit (GPU). The proposed designs consist of five different versions which extensively study the use of memory components on the GPU board for mapping the GBC algorithm. GBC algorithm is used to find any maximal biclusters, which are common patterns in each column in the neural processing and gene microarray data. A microarray commonly involves a huge number of data, such as thousands of rows by thousands of columns so that finding the maximal biclusters involves intensive computation. The advantage of GPU is its ability of parallel computing which means that for those independent procedures, they can be carried out at the same time. Experimental results show that the GPU-based GBC could reduce the processing time largely due to the parallel computing of GPU, and its scalability. As an example, GBC algorithm involves a large number of AND operations which utilize the parallel GPU computations, that can be further practically used for other neural processing algorithms.