Protein–Protein interaction site prediction in Homo sapiens and E. coli using an interaction-affinity based membership function in fuzzy SVM

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.

Developing Computational Model to Predict Protein-Protein Interaction Sites Based on the XGBoost Algorithm

“…Fortunately, predicting protein-protein interaction sites using computational methods has become a hot topic with the development of machine learning algorithms [4][5][6][7][8]. Previous studies showed that support vector machine (SVM) and its improved methods can predict effectively protein interaction sites [9][10][11][12][13][14]. Computational algorithms such as random forests, KNN, and Naive Bayes Classifier have been also applied to the prediction of PPIs [15][16][17][18].…”

Protein–protein interaction network: an emerging tool for understanding fish disease in aquaculture

“…Among the methods used in ML‐based PPI prediction, support vector machine (SVM) (Sriwastava et al . 2015) and random forests (RF) (Šikić et al . 2009; Li et al .…”

“…Machine learning (ML)based methods involve automated knowledge discovery and data mining from the previously generated data to predict PPIs. Among the methods used in ML-based PPI prediction, support vector machine (SVM)(Sriwastava et al 2015) and random forests (RF)( Siki c et al 2009; are the most commonly used. However, each MLbased method has its distinctive challenges, and to date, researchers are still improving and developing new MLbased methods to identify PPI(Chen et al 2019b).…”

Prediction of Protein–Protein Interaction Sites Using Convolutional Neural Network and Improved Data Sets

“…With the fast expansion of resolved sequences and structural data of proteins, several kinds of computational methods such as molecular dynamics methods [17,18] and machine learning methods have been proposed to predict PPI sites. Among these methods, machine-learning methods are most successful, using the following models [14,19]: support vector machine (SVM) [20][21][22][23][24][25] and fuzzy SVM [26], neural networks (NN) [27][28][29][30][31][32], Bayesian networks (BN) [33,34], naive Bayes classifier (NBC) [35,36], random forests (RF) [12,[37][38][39], cascade random forests (CRF) [40], conditional random fields (CRF) [41], extreme learning machine (ELM) [42], L1-logreg classifier [43], and the ensemble method [14,15,44,45]. As a recent development of neural networks, deep-learning is a rapidly growing branch of machine learning and has also been used to predict PPI sites [19].…”