Hybrid Selective Neural Network Ensembles for Prediction of MHC Class Ⅱ-binding Peptides

摘要：

Predictions of the binding ability of antigen peptides to major histocompatibility complex (MHC) class II molecules are important for immunology research and vaccine design. The variable length of each binding peptide complicates this prediction. In this paper, hybrid selective neural network ensemble is proposed for prediction of MHC class II-binding peptides, the ensemble is built on two-level ensemble architecture.The first-level ensemble is used to create primary neural network ensemble(NNE),where migration differential evolution-based selective neural network and GASEN are used to build some NNEs.The second-level ensemble is that primary NNEs are selected to make up the final ensemble. Experiment results indicate that the hybrid ensemble model has better generalization and performance compared to any of individual neural networks and traditional selective neural network ensemble.

关键词： major histocompatibility complez (MHC) neural networks ensemble differential evolution, genetic algorithm

作者: Gui-Wu Hu

作者单位: Department of Mathematics & Computational Science Guangdong University of Business Studies Guangzhou, China

会议类型: 国际会议

会议名称: The 2nd International Conference on Bioinformatics and Biomedical Engineering(iCBBE 2008)(第二届生物信息与生物医学工程国际会议)

会议地点: 上海

会议语种:英文

页码: 660-663

在线出版日期: 2008-05-16（万方平台首次上网日期，不代表论文的发表时间）