Prediction of E.coli Protein-Protein Interaction Sites Using Inter-Residue Distances and High-Quality-Index Features

Sriwastava, Brijesh Kumar; Basu, Subhadip; Maulik, Ujjwal; Plewczyński, Dariusz

doi:10.1007/978-3-642-27443-5_96

Cited by 2 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…based on the interaction affinity of both positive as well as negative interacting residues. We have worked with 21 length window fragment (win_size) (Sriwastava et al 2012(Sriwastava et al , 2013a and considered a fragment pair to be positive if at least the central residue interaction is found. On the other hand, a fragment pair is considered to be negative if the central residues of the fragments are not interacting with each other.…”

Section: Design Of the Fuzzy Membership Functionmentioning

confidence: 99%

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

Sriwastava¹,

Basu

Maulik

2015

J Biosci

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Design Of the Fuzzy Membership Functionmentioning

confidence: 99%

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

Sriwastava¹,

Basu

Maulik

2015

J Biosci

Self Cite

View full text Add to dashboard Cite

show abstract

“…In practice, we determine the membership function based on domain experience. We are working with 21 size window fragment ( _ ) [8,9] and we are considering a fragment to be positive if there are at least 2 interactions. The choice of two interactions is made to avoid possible noise, in the form of isolated interaction residue, in the positive dataset.…”

Section: Fuzzy Membership Evaluationmentioning

confidence: 99%

Fuzzy SVM with a Novel Membership Function for Prediction of Protein-Protein Interaction Sites in Homo sapiens

Sriwastava¹,

Basu

Maulik

2013

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Predicting residues that participate in protein-protein interactions (PPI) helps to identify the amino acids located at the interface. In this work, experimentally verified 3-D structures of protein complexes are used for building the training model and subsequent prediction protein interactions from sequence information. Fuzzy SVM (F-SVM), which is developed on top of the classical SVM, is an effective method to solve this problem and we demonstrate that the performance of the SVM can further be improved with the use of a customdesigned fuzzy membership function. We evaluate the performances of both SVM and F-SVM on the PPI database of the Homo sapiens organism and evaluate the statistical significance of F-SVM over classical SVM. To predict interaction sites in protein complexes, local composition of amino acids together with their physico-chemical characteristics are used. The F-SVM based residues prediction method exploits the membership function for each pair sequence fragment and in all cases F-SVM improves the performances obtained by the corresponding SVM classifiers. The F-SVM performance on the test samples is measured by area under ROC curve (AUC) as 80.16% which is around 1.55% higher than the classical SVM classifier.

show abstract

Prediction of E.coli Protein-Protein Interaction Sites Using Inter-Residue Distances and High-Quality-Index Features

Cited by 2 publications

References 17 publications

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

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

Fuzzy SVM with a Novel Membership Function for Prediction of Protein-Protein Interaction Sites in Homo sapiens

Contact Info

Product

Resources

About