Sriwastava Brijesh Kumar, Basu Subhadip, Maulik Ujjwal
Department of Computer Science and Engineering, Government College of Engineering and Leather Technology, Kolkata 700 098, India.
J Biosci. 2015 Oct;40(4):809-18. doi: 10.1007/s12038-015-9564-y.
Protein-protein interaction (PPI) site prediction aids to ascertain the interface residues that participate in interaction processes. Fuzzy support vector machine (F-SVM) is proposed as an effective method to solve this problem, and we have shown that the performance of the classical SVM can be enhanced with the help of an interaction-affinity based fuzzy membership function. The performances of both SVM and F-SVM on the PPI databases of the Homo sapiens and E. coli organisms are evaluated and estimated the statistical significance of the developed method over classical SVM and other fuzzy membership-based SVM methods available in the literature. Our membership function uses the residue-level interaction affinity scores for each pair of positive and negative sequence fragments. The average AUC scores in the 10-fold cross-validation experiments are measured as 79.94% and 80.48% for the Homo sapiens and E. coli organisms respectively. On the independent test datasets, AUC scores are obtained as 76.59% and 80.17% respectively for the two organisms. In almost all cases, the developed F-SVM method improves the performances obtained by the corresponding classical SVM and the other classifiers, available in the literature.
蛋白质-蛋白质相互作用（PPI）位点预测有助于确定参与相互作用过程的界面残基。模糊支持向量机（F-SVM）被提出作为解决这一问题的有效方法，并且我们已经表明，借助基于相互作用亲和力的模糊隶属函数可以提高经典支持向量机的性能。评估了支持向量机（SVM）和模糊支持向量机（F-SVM）在人类和大肠杆菌生物体的PPI数据库上的性能，并估计了所开发方法相对于经典支持向量机和文献中其他基于模糊隶属度的支持向量机方法的统计显著性。我们的隶属函数使用每对正、负序列片段的残基水平相互作用亲和力得分。在10折交叉验证实验中，人类和大肠杆菌生物体的平均AUC得分分别为79.94%和80.48%。在独立测试数据集上，两种生物体的AUC得分分别为76.59%和80.17%。在几乎所有情况下，所开发的模糊支持向量机方法都提高了相应经典支持向量机和文献中其他分类器所获得的性能。
