Prediction of protein binding sites in protein structures using hidden Markov support vector machine

Abstract

BackgroundPredicting the binding sites between two interacting proteins provides important clues to the function of a protein. Recent research on protein binding site prediction has been mainly based on widely known machine learning techniques, such as artificial neural networks, support vector machines, conditional random field, etc. However, the prediction performance is still too low to be used in practice. It is necessary to explore new algorithms, theories and features to further improve the performance.ResultsIn this study, we introduce a novel machine learning model hidden Markov support vector machine for protein binding site prediction. The model treats the protein binding site prediction as a sequential labelling task based on the maximum margin criterion. Common features derived from protein sequences and structures, including protein sequence profile and residue accessible surface area, are used to train hidden Markov support vector machine. When tested on six data sets, the method based on hidden Markov support vector machine shows better performance than some state-of-the-art methods, including artificial neural networks, support vector machines and conditional random field. Furthermore, its running time is several orders of magnitude shorter than that of the compared methods.ConclusionThe improved prediction performance and computational efficiency of the method based on hidden Markov support vector machine can be attributed to the following three factors. Firstly, the relation between labels of neighbouring residues is useful for protein binding site prediction. Secondly, the kernel trick is very advantageous to this field. Thirdly, the complexity of the training step for hidden Markov support vector machine is linear with the number of training samples by using the cutting-plane algorithm.

Effects of error-correction of heterozygous next-generation sequencing data

“…This benchmark has been used by many studies, which can provide good comparability with previous approaches [4,16,18,28-30,35,36]. There are 54 families and 4352 proteins selected from SCOP version 1.53.…”

Protein Remote Homology Detection by Combining Chou’s Pseudo Amino Acid Composition and Profile‐Based Protein Representation

“…Experimental results demonstrate that the proposed methods are efficient for protein remote homology detection. The proposed PseAACIndex would be applied to many tasks of the computational biology, such as enzyme functional class, [66][67] protein-protein interaction, [68] protein binding site prediction, [69][70][71] knowledge-based mean force potential, [72] membrane protein type [73] and protein subcellular location. [74][75][76][77][78] Since user-friendly and publicly accessible webservers represent the future direction for developing practically more useful models, simulated methods, or predictors, [79] we shall make efforts in our future work to provide a web-server for the method presented in this paper.…”

Identification of DNA-Binding and Protein-Binding Proteins Using Enhanced Graph Wavelet Features

“…Additionally, alpha shape models [25], [29] are applied to describe the surface of the protein-DNA structures and defined a conditional probability function [30], which showed a better performance than the distance-dependent method [31] in distinguishing the native structures from the docking decoy sets. Furthermore, several machine learning methods, such as support vector machines [15], [32], [33], Bayesian classifiers [5], and neural networks [34], can be used for the prediction of biomolecular interactions. For example, Kumar et al developed DNAbinder [35] for predicting DNA-binding proteins from their amino acid sequence using various compositional features of proteins and exploited SVM classifier to classify DNA-binding proteins or not.…”

“…Generally, primary sequences [4], [6], [7], [8], molecular structures [9], [10], [11], [12], [13], [14], [15], biochemical properties [16], [17], [18], [19], [20], and hybrid information [21], [22], [23], [24], [25], [26], [27], [28] are used as the sources for the prediction of the interactions. Additionally, alpha shape models [25], [29] are applied to describe the surface of the protein-DNA structures and defined a conditional probability function [30], which showed a better performance than the distance-dependent method [31] in distinguishing the native structures from the docking decoy sets.…”