Prediction of protein-protein interactions from amino acid sequences with ensemble extreme learning machines and principal component analysis

Abstract

BackgroundProtein-protein interactions (PPIs) play crucial roles in the execution of various cellular processes and form the basis of biological mechanisms. Although large amount of PPIs data for different species has been generated by high-throughput experimental techniques, current PPI pairs obtained with experimental methods cover only a fraction of the complete PPI networks, and further, the experimental methods for identifying PPIs are both time-consuming and expensive. Hence, it is urgent and challenging to develop automated computational methods to efficiently and accurately predict PPIs.ResultsWe present here a novel hierarchical PCA-EELM (principal component analysis-ensemble extreme learning machine) model to predict protein-protein interactions only using the information of protein sequences. In the proposed method, 11188 protein pairs retrieved from the DIP database were encoded into feature vectors by using four kinds of protein sequences information. Focusing on dimension reduction, an effective feature extraction method PCA was then employed to construct the most discriminative new feature set. Finally, multiple extreme learning machines were trained and then aggregated into a consensus classifier by majority voting. The ensembling of extreme learning machine removes the dependence of results on initial random weights and improves the prediction performance.ConclusionsWhen performed on the PPI data of Saccharomyces cerevisiae, the proposed method achieved 87.00% prediction accuracy with 86.15% sensitivity at the precision of 87.59%. Extensive experiments are performed to compare our method with state-of-the-art techniques Support Vector Machine (SVM). Experimental results demonstrate that proposed PCA-EELM outperforms the SVM method by 5-fold cross-validation. Besides, PCA-EELM performs faster than PCA-SVM based method. Consequently, the proposed approach can be considered as a new promising and powerful tools for predicting PPI with excellent performance and less time.

A Survey on Study of Various Machine Learning Methods for Classification

“…More or less all the existing machine algorithms have been executed in this field. The improved classified efficiency is proved in [5][6][7][8][9].It also proves its betterment in the field of image processing by generating high resolution images from low resolution input [3,[10][11].ELM also entered in the field of system modeling and prediction [12][13].…”

An Ensemble Classifier with Random Projection for Predicting Protein–Protein Interactions Using Sequence and Evolutionary Information

“…Furthermore, PCA converts primitive variables into a linear combination set, the principal components (PCs), which catch the data variables, are linearly independent, and are weighted in decreasing order of variance coverage [45]. This can reduce the data dimension directly by discarding low variability characteristic elements.…”

Towards Data Analytics of Pathogen-Host Protein-Protein Interaction: A Survey

“…For each protein pair, a 3422 dimensional vector is constructed to represent it and to be used as a feature vector for Extreme Learning Machine. Method in [12] is a bit different from this partition method introduced in [36]. As discussed in Section II, 10 local regions of varying length are selected out of every protein sequence.…”