[发明专利]基于回归森林模型的蛋白质序列二硫键连接模式的预测方法

说明书

技术领域

本发明涉及生物信息学蛋白质序列中二硫键预测技术领域，具体而言涉及一种基于回归森林模型的蛋白质序列二硫键连接模式的预测方法。

背景技术

二硫键是最重要的蛋白质结构特性之一。二硫键是在蛋白质多肽链中两个半胱氨酸残基之间形成的主共价键，它们可以在肽链的链间或者链内形成。二硫键在蛋白质折叠方式以及稳定性方面有着非常重要的作用。因此，预测蛋白质里面的半胱氨酸残基组成二硫键的方式在预测蛋白质结构和功能上起着举足轻重的作用。

目前有很多种预测二硫键的方法，比如，DISULFIND法(A.Ceroni,A.Passerini,A.Vullo et al.,“DISULFIND:a disulfide bonding state and cysteine connectivity prediction server,”Nucleic Acids Research,vol.34,no.suppl2,pp.W177-W181,2006.)、Pair-Wise SVM法(C.-H.Tsai,B.-J.Chen,C.-h.Chan et al.,“Improving disulfide connectivity prediction with sequential distance between oxidized cysteines,”Bioinformatics,vol.21,no.24,pp.4416-4419,2005.)、SS_SVR法(J.Song,Z.Yuan,H.Tan et al.,“Predicting disulfide connectivity from protein sequence using multiple sequence feature vectors and secondary structure,”Bioinformatics,vol.23,no.23,pp.3147-3154,2007.)、FS_SVR法(L.Zhu,J.Yang,J.N.Song et al.,“Improving the accuracy of predicting disulfide connectivity by feature selection,”J Comput Chem,vol.31,no.7,pp.1478-85,May,2010.)、DBCP法(H.-H.Lin,and L.-Y.Tseng,“DBCP:a web server for disulfide bonding connectivity pattern prediction without the prior knowledge of the bonding state of cysteines,”Nucleic acids research,vol.38,no.suppl2,pp.W503-W507,2010.)、DISLOCATE法(DISLOCATE+MIp+iCOV)(C.Savojardo,P.Fariselli,M.Alhamdoosh et al.,“Improving the prediction of disulfide bonds in Eukaryotes with machine learning methods and protein subcellular localization,”Bioinformatics,vol.27,no.16,pp.2224-30,Aug15,2011.)、DMC法(C.Savojardo,P.Fariselli,P.L.Martelli et al.,“Prediction of disulfide connectivity in proteins with machine-learning methods and correlated mutations,”BMC Bioinformatics,vol.14,no.Suppl1,pp.S10,2013.)、DiANNA法(F.Ferrè,and P.Clote,“DiANNA1.1:an extension of the DiANNA web server for ternary cysteine classification,”Nucleic Acids Research,vol.34,no.suppl2,pp.W182-W185,2006.)等等。