Evolving GeneChip correlation predictors on parallel graphics hardware
Mathematical and Biological Sciences, University of Essex,Colchester CO4 3SQ, UK
IEEE Congress on Evolutionary Computation, 2008. CEC 2008. (IEEE World Congress on Computational Intelligence), p.4151-4156
@conference{langdon2008evolving,
title={Evolving GeneChip correlation predictors on parallel graphics hardware},
author={Langdon, WB},
booktitle={Evolutionary Computation, 2008. CEC 2008.(IEEE World Congress on Computational Intelligence). IEEE Congress on},
pages={4151–4156},
year={2008},
organization={IEEE}
}
A GPU is used to datamine five million correlations between probes within Affymetrix HG-U133A probesets across 6685 human tissue samples from NCBIpsilas GEO database. These concordances are used as machine learning training data for genetic programming running on a Linux PC with a RapidMind OpenGL GLSL backend. GPGPU is used to identify technological factors influencing high density oligonuclotide arrays (HDONA) performance. GP suggests mismatch (PM/MM) and adenosine/guanine ratio influence microarray quality. Initial results hint that Watson-Crick probe self hybridisation or folding is not important. Under GPGPGPU an nVidia GeForce 8800 GTX interprets 300 million GP primitives/second (300 MGPops, approx 8 GFLOPS).
January 21, 2011 by hgpu
