Systems, Man, and Cybernetics

 

Home

• [P723] Recognition of Drug-Target Interaction Patterns using Genetic Algorithm-optimized Bayesian-regularized Neural Networks and Support Vector Machines
  Author(s): Michael Fernandez, Akinori Sarai, Shandar Ahmad
  
  

  Abstract
  Genetic algorithm (GA) applied to feature selection and model optimization improved the performance of robust mathematical models such as Bayesian-regularized neural networks (BRANNs) and support vector machines (SVMs) on different drug design datasets. The modeled datasets included anti-cancer drugs, acetylcholinesterase inhibitors, HIV-1 protease inhibitors, ion-channel and calcium entry blockers, antiprotozoan compounds and protein functional properties. The main weaknesses of neural network modeling: the selection of optimum input variables and the adjustment of network weights and biases to optimum values for yielding generalizable neural network predictors were overcome when combining Bayesian training and GA based-variable selection. Similarly, kernel and regularization parameters of SVMs were properly set by GA optimization. The predictors were more accurate and robust than previous published models on the same datasets. In addition, feature selection over large pools of molecular descriptors allowed determining the structural and atomic properties of the ligands that are ruling the biological interactions with the target.

  
   

Full Text (PDF)