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
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