Novel QSAR combination forecast model for insect repellent coupling support vector regression and K-nearest-neighbor.

Li-Feng  Wang; Xian-Sheng  Tan; Zhe-Ming  Yuan; Lian-Yang  Bai

Author(s)

Li-Feng Wang Hunan Provincial Key Laboratory of Crop Germplasm Innovation and Utilization, Hunan Agricultural University, Changsha, China; Hunan Provincial Key Laboratory for Biology and Control of Plant Disease and Insect Pests, Hunan Agricultural University, Changsha, China

Xian-Sheng Tan Hunan Institute of Humanities; Science and Technology, Loudi, China

Zhe-Ming Yuan Hunan Provincial Key Laboratory of Crop Germplasm Innovation and Utilization, Hunan Agricultural University, Changsha, China; Hunan Provincial Key Laboratory for Biology and Control of Plant Disease and Insect Pests, Hunan Agricultural University, Changsha, China

Lian-Yang Bai Hunan Provincial Key Laboratory for Biology and Control of Plant Disease and Insect Pests, Hunan Agricultural University, Changsha, China; Hunan Institute of Humanities; Science and Technology, Loudi, China

Abstract

To improve the precision of quantitative structure-activity relationship (QSAR) modeling for aromatic carboxylic acid derivatives insect repellent, a novel nonlinear combination forecast model was proposed integrating support vector regression (SVR) and K-nearest neighbor (KNN): Firstly, search optimal kernel function and nonlinearly select molecular descriptors by the rule of minimum MSE value using SVR. Secondly, illuminate the effects of all descriptors on biological activity by “multi-round enforcement resistance-selection”. Thirdly, construct the sub- models with predicted values of different KNN. Then, get the optimal kernel and corresponding retained sub-models through subtle selection. Finally, make prediction with leave-one-out (LOO) method in the basis of reserved sub-models. Compared with previous widely used models, our work shows significant improvement in modeling performance, which demonstrates the superiority of the present combination forecast model.

Publication Details

Page(s) 1075-1080

DOI DOI not available

Published Journal: Journal of Chemical Society of Pakistan, Volume: 35, Issue: 4, Year: 2013

Request the full text from PASTIC