计算机科学 ›› 2015, Vol. 42 ›› Issue (8): 75-77.

• 2014’江苏省人工智能学术会议 • 上一篇    下一篇

基于序列的G蛋白偶联受体-药物相互作用预测研究

丁林松,郑宇杰   

  1. 南京理工大学计算机科学与工程学院 南京210094,中国电子科技集团公司第28研究所 南京210007
  • 出版日期:2018-11-14 发布日期:2018-11-14
  • 基金资助:
    本文受国家自然科学基金(61373062),江苏省自然科学基金(BK20141403)资助

Research on Sequence-based Predictor for GPCR-Drug Interaction Prediction

DING Lin-song and ZHENG Yu-jie   

  • Online:2018-11-14 Published:2018-11-14

摘要: 准确预测G蛋白质偶联受体(GPCR)是否与药物(Drug)相互作用是新药开发的关键步骤之一。从时间和费用方面来说,通过生物实验的方法来确定GPCR-Drug是否相互作用的代价是昂贵的。因此,直接从蛋白质序列出发预测GPCR-Drug的相互作用具有重要的意义。提出了一种基于序列的GPCR-Drug相互作用预测方法:从蛋白质序列抽取进化信息特征;对药物抽取指纹特征;基于上述两种特征,使用基于证据理论的K近邻算法进行分类预测。在标准数据集上的实验结果表明了所述方法的有效性。

关键词: G蛋白质偶联受体,药物,特征抽取,预测

Abstract: Accurately identifying whether a G-protein-coupled receptor(GPCR) will interact with a drug is a crucial step in drug discovery.However,experimentally determining the interactions between GPCR and drug is time-consuming and expensive.Hence,developing automated prediction methods for GPCT-Drug interaction prediction solely from protein sequence is in urgent need.In this study,a new sequence-based method for GPCT-Drug interaction prediction was proposed.Evolutionary information feature from protein sequence and footprint feature from drug were combined to form discriminative feature.And the optimized evidence-theoretic K-nearest neighbor(OET-KNN) prediction algorithm was taken as classifier.Experimental results demonstrate that the proposed method achieves good performance and can act as complementary predictor to existing methods.

Key words: G-protein-coupled receptor,Drug,Feature extraction,Prediction

[1] Tilley D G.G protein-dependent and G protein-independent signaling pathways and their impact on cardiacfunction [J].Circ Res,2011,9(2):217-230
[2] Alexander S P,Mathie A,Peters J A.Guide to Receptors and Channels(GRAC) [J].Br J Pharmacol,2011,4(supp.1):S1-324
[3] Knowles J,Gromo G.A guide to drug discovery:Target selection in drug discovery[J].Nat Rev Drug Discov,2003,2(1):63-69
[4] Chou K C.Review:Structural bioinformatics and its impact to biomedical science[J].Current Medicinal Chemistry,2004,1(16):2105-2134
[5] OZhu S,Okuno Y,Tsujimoto G,et al.A probabilistic modelformining implicit ‘chemical compound-gene’ relations from li-terature[J].Bioinformatics,2005,1(2):245-251
[6] Yamanishi Y,Araki M,Gutteridge A,et al.Prediction of drug-target interaction networks from the integration of chemicaland genomic spaces[J].Bioinformatics,2008,4(13):232-240
[7] Chou K C,Shen H B.Review:recent advances in developingWeb-servers for predicting protein attributes[J].Natural Science,2009,1(2):63-92
[8] Zouhal L M,Denoeux T.An evidence-theoretic KNN rule with parameter optimization[J].IEEE Transactions on Systems,Man and Cybernetics,1998,8(2):263-271
[9] Xuan Xiao,Jian-Liang Min,Pu Wang,et al.iGPCR-Drug:A Web Server for Predicting Interaction between GPCRs and Drugs in Cellular Networking [J].PLoSONE,2013,8(8):e72234
[10] O’Boyle N M,Banck M,James C A,et al.Open Babel:An open chemical toolbox[J].J Cheminform,2011,3(33)
[11] Schaffer A A.Improving the accuracy of PSI-BLASTprotein database searches with composition-based statistics and other refinements[J].Nucleic Acids Res,2011,29(14):2994-3005
[12] Liu T,et al.Accurate prediction of protein structural class using auto covariance transformation of PSI-BLAST profiles[J].Amino Acids,2012,42(6):2243-2249
[13] Denoeux T.A k-nearest neighbor classification rule based onDempsterShafer theory[J].IEEE Transactions on Systems Man and Cybernetics,1995,25(5):804-813
[14] He Z,Zhang J,Shi XH,et al.Predicting drug-target interaction networks based on functional groups and biological features[J].PLoSONE,2010,5(3):e9603

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!