Poster: GPU-accelerated artificial neural network for QSAR modeling
Center for Structural Biology, Vanderbilt University, Nashville TN, USA
IEEE 1st International Conference on Computational Advances in Bio and Medical Sciences (ICCABS), 2011
@poster{Lowe_Woetzel_Meiler_2011,
title={Poster: GPU-accelerated artificial neural network for QSAR modeling},
url={http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=5729907},
journal={2011 IEEE 1st International Conference on Computational Advances in Bio and Medical Sciences (ICCABS)},
publisher={IEEE},
author={Lowe, Edward W. and Woetzel, Nils and Meiler, Jens},
year={2011},
pages={254-254}
}
Here, we present a GPU-accelerated OpenCL implementation of a back-propagation artificial neural network for the creation of QSAR models for drug discovery and virtual high-throughput screening. A QSAR model for HSD achieved an enrichment of 5.9 and area under the curve of 0.83 on an independent data set which signifies sufficient predictive ability for virtual high-throughput screening efforts. The speed-up demonstrated on this data set allows for the complete cross-validated feature optimization of QSAR models based on ANNs within 24 hours on a workstation equipped with 4 consumer GPUs of $260 each (GTX 470), achieving performance equal to that of ~340 cores. This GPU-accelerated ANN framework for the creation of optimized QSAR models from biological data will be available free of charge for academic users at http://www.meilerlab.org through a server interface.
April 1, 2011 by hgpu
