A Study of Network-based Kernel Methods on Protein-Protein Interaction for Protein Functions Prediction

摘要：

Predicting protein functions is an important issue in the post-genomic era. In this paper, we studied several network-based kernels including Local Linear Embedding (LLE) kernel method, Diffusion kernel and Laplacian Kernel to uncover the relationship between proteins functions and Protein-Protein Interactions (PPI). We first construct kernels based on PPI networks, we then apply support Vector Machine (SVM) techniques to classify proteins into different functional groups. 5fold cross validation is then applied to the selected 359 GO terms to compare the performance of different kernels and guilt-by-association methods including neighbor counting methods and Chisquare methods. Finally we made predictions of functions of some unknown genes and verified the preciseness of our prediction in part by the information of other data source.

关键词： Protein Function Prediction Kernel Method Local Linear Embedding (LLE) Kernel Laplacian Kernel Diffusion Kernel Support Vector Machine

作者: Wai-Ki Ching Limin Li Yat-Ming Chan Hiroshi Mamitsuka

作者单位: Advanced Modeling and Applied Computing Laboratory,Department of Mathematics,The University of Hong Bioinformatics Center,Institute for Chemical Research,Kyoto University,Gokasho,Uji,Kyoto 611-0011,Ja

会议类型: 国际会议

会议名称: The 3rd International Symposium on Optimization and System Biology(第三届最优化与系统生物学国际会议 OSB09)

会议地点: 张家界

会议语种:英文

页码: 25-32

在线出版日期: 2009-09-20（万方平台首次上网日期，不代表论文的发表时间）