Protein-Protein Interaction Detection By SVM From Sequence Information

摘要：

Proteins frequently bind together in pairs or larger complexes to take part in biological processes. Understanding such protein functions and biological processes in a cell across the entire genome is an important goal with diverse implications about protein function. In this paper, we propose a method to detect protein-protein interaction (PPI) based on sequence neighboring information and support vector machine (SVM). When applied on the currently available protein-protein interaction data for the yeast Saccharomyces cerevisiae, it yields a predictive accuracy of 87.98%. It is further evaluated on an independent PPIs with the test accuracy of 79.05%, which delivered the proposed method reasonable and promising.

关键词： Saccharomyces cerevisiae protein-protein interactions (PPIs) support vector machine(SVM) feature eztraction

作者: Hong-Wei Liu

作者单位: School of Information,Beijing Wuzi University,Beijing 101149,China Institute of Applied Mathematics Academy of Mathematics and Systems Science,CAS,Beijing 100080,China

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: 198-206

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）