• Fulltext


        Click here to view fulltext PDF

      Permanent link:

    • Keywords


      Fuzzy support vector machine; interaction affinity; protein–protein interaction

    • Abstract


      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.

    • Author Affiliations


      Brijesh Kumar Sriwastava1 Subhadip Basu2 Ujjwal Maulik2

      1. Department of Computer Science and Engineering, Government College of Engineering and Leather Technology, Kolkata 700 098, India
      2. Department of Computer Science and Engineering, Jadavpur University, Kolkata 700 032, India
    • Dates

    • Supplementary Material

  • Journal of Biosciences | News

    • Editorial Note on Continuous Article Publication

      Posted on July 25, 2019

      Click here for Editorial Note on CAP Mode

© 2021-2022 Indian Academy of Sciences, Bengaluru.