Uncovering signaling networks based on high-throughput data
BackgroundGenerally, the protein-protein interactions(PPIs) are assumed to be mediated by domaindomain interactions (DDI). We propose a novel discriminative method for predicting DDIs from both available experiment data of PPIs and the derived information of non-PPIs,which improves the prediction reliability. In particular, the DDI identification is formalized as a feature selection problem, which is consistent with the parsimonious principle and is able to predict both DDIs and PPIs in a systematic and accurate manner.
Xing-Ming Zhao Luonan Chen
Institute of Systems Biology Shanghai University, 200444 Shanghai, China
国际会议
The 7th Asia-Pacific Bioinformatics Conference(第七届亚太生物信息学大会)
北京
英文
870
2009-01-01(万方平台首次上网日期,不代表论文的发表时间)