Support Vector Machine Prediction of Drug Solubility on GPUs.

The landscape in the high performance computing arena opens up great opportunities in the simulation of relevant biological systems and for applications in Bioinformatics, Computational Biology and Computational Chemistry. Larger databases increase the chances of generating hits or leads, but the computational time needed increases with the size of the database and with the accuracy of the Virtual Screening (VS) method and the model. In this work we discuss the benefits of using massively parallel architectures for the optimization of prediction of compound solubility using computational intelligence methods such as Support Vector Machines (SVM) methods. SVMs are trained with a database of known soluble and insoluble compounds, and this information is being exploited afterwards to improve VS prediction. We empirically demonstrate that GPUs are well-suited architecture for the acceleration of Computational Intelligence methods as SVM, obtaining up to a 15 times sustained speedup compared to its sequential counterpart version.