文献类型：期刊文献

英文题名：Accurate prediction of RNA-binding protein residues with two discriminative structural descriptors

作者：Sun, Meijian[1];Wang, Xia[1];Zou, Chuanxin[1];He, Zenghui[1];Liu, Wei[1];Li, Honglin[1]

机构：[1]E China Univ Sci & Technol, Sch Pharm, Shanghai Key Lab New Drug Design, State Key Lab Bioreactor Engn, 130 Mei Long Rd, Shanghai 200237, Peoples R China

年份：2016

卷号：17

期号：1

外文期刊名：BMC BIOINFORMATICS

收录：;EI(收录号：20162502512202);WOS:【SCI-EXPANDED(收录号:WOS:000377262500002)】；

基金：This work was supported by the 863 Hi-Tech Program of China (grant 2012AA020308), the National Natural Science Foundation of China (grants 81222046 and 81230076), Special Program for Applied Research on Super Computation of the NSFC-Guangdong Joint Fund (the second phase), and the Fundamental Research Funds for the Central Universities, Honglin Li is also sponsored by the Innovation Program of Shanghai Municipal Education Commission (grant 13SG32) and Fok Ying Tung Education Foundation (141035).

语种：英文

外文关键词：Protein-RNA interactions; Residue triplet interface propensity; Residue electrostatic surface potential; Random forest classifier; Structural analysis

摘要：Background: RNA-binding proteins participate in many important biological processes concerning RNA-mediated gene regulation, and several computational methods have been recently developed to predict the protein-RNA interactions of RNA-binding proteins. Newly developed discriminative descriptors will help to improve the prediction accuracy of these prediction methods and provide further meaningful information for researchers. Results: In this work, we designed two structural features (residue electrostatic surface potential and triplet interface propensity) and according to the statistical and structural analysis of protein-RNA complexes, the two features were powerful for identifying RNA-binding protein residues. Using these two features and other excellent structure-and sequence-based features, a random forest classifier was constructed to predict RNA-binding residues. The area under the receiver operating characteristic curve (AUC) of five-fold cross-validation for our method on training set RBP195 was 0.900, and when applied to the test set RBP68, the prediction accuracy (ACC) was 0.868, and the F-score was 0.631. Conclusions: The good prediction performance of our method revealed that the two newly designed descriptors could be discriminative for inferring protein residues interacting with RNAs. To facilitate the use of our method, a web-server called RNAProSite, which implements the proposed method, was constructed and is freely available at http://lilab.ecust.edu.cn/NABind.