期刊
TOXICOLOGY IN VITRO
卷 27, 期 2, 页码 852-856出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.tiv.2012.12.024
关键词
Ion channel-targeted conotoxins; RBF network; Binomial distribution; Dipeptide
类别
资金
- National Nature Scientific Foundation of China [61202256, 61100092]
- Fundamental Research Funds for the Central Universities [ZYGX2012J113]
- Scientific Research Startup Foundation of UESTC
Conotoxins are small disulfide-rich peptide toxins, which have the exceptional diversity of sequences. Because conotoxins are able to specifically bind to ion channels and interfere with neurotransmission, they are considered as the excellent pharmacological candidates in drug design. Appropriate type assignment of newly sequenced mature ion channel-targeted conotoxins with computational method is conducive to explore the biological and pharmacological functions of conotoxins. In this paper, we developed a novel method based on binomial distribution and radial basis function network to predict the types of ion-channel targeted conotoxins. We achieved the overall accuracy of 89.3% with average accuracy of 89.7% in the prediction of three types of ion channel-targeted conotoxins in jackknife cross-validation test, indicating that the method is superior to other state-of-the-art methods. In addition, we evaluated the proposed model with an independent dataset including 77 conotoxins. The overall accuracy of 85.7% was achieved, validating that our model is reliable. Moreover, we used the proposed method to annotate 336 function-undefined mature conotoxins in the UniProt Database. The model provides the valuable instructions for theoretical and experimental research on conotoxins. (C) 2012 Elsevier Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据