New Hybrid Genetic Based Support Vector Regression as QSAR Approach for Analyzing Flavonoids-GABA(A) Complexes

• DOI: 10.1021/ci900075f
• Publication Date: 2009-06-03T14:12:43Z
• Authors: Mohammad Goodarzi; Pablo R. Duchowicz; Chih H. Wu; Francisco M. Fern...; Eduardo A. Castro
• Keywords: Kernel (algebra)

Several studies were conducted in past years which used the evolutionary process of Genetic Algorithms for optimizing Support Vector Regression parameter values although, however, few them devoted to simultaneously optimization type kernel function involved established model. The present work introduces a new hybrid genetic-based approach, whose statistical quality and predictive capability is afterward analyzed compared other standard chemometric techniques, such as Partial Least Squares, Back-Propagation Artificial Neural Networks, Machines based on Cross-Validation. For this purpose, we employ data set experimentally determined binding affinity constants toward benzodiazepine site GABA (A) receptor complex 78 flavonoid ligands.