A Consistency-Based Feature Selection Method Allied with Linear SVMs for HIV-1 Protease Cleavage Site Prediction

Abstract

BackgroundPredicting type-1 Human Immunodeficiency Virus (HIV-1) protease cleavage site in protein molecules and determining its specificity is an important task which has attracted considerable attention in the research community. Achievements in this area are expected to result in effective drug design (especially for HIV-1 protease inhibitors) against this life-threatening virus. However, some drawbacks (like the shortage of the available training data and the high dimensionality of the feature space) turn this task into a difficult classification problem. Thus, various machine learning techniques, and specifically several classification methods have been proposed in order to increase the accuracy of the classification model. In addition, for several classification problems, which are characterized by having few samples and many features, selecting the most relevant features is a major factor for increasing classification accuracy.ResultsWe propose for HIV-1 data a consistency-based feature selection approach in conjunction with recursive feature elimination of support vector machines (SVMs). We used various classifiers for evaluating the results obtained from the feature selection process. We further demonstrated the effectiveness of our proposed method by comparing it with a state-of-the-art feature selection method applied on HIV-1 data, and we evaluated the reported results based on attributes which have been selected from different combinations.ConclusionApplying feature selection on training data before realizing the classification task seems to be a reasonable data-mining process when working with types of data similar to HIV-1. On HIV-1 data, some feature selection or extraction operations in conjunction with different classifiers have been tested and noteworthy outcomes have been reported. These facts motivate for the work presented in this paper.Software availabilityThe software is available at http://ozyer.etu.edu.tr/c-fs-svm.rar.The software can be downloaded at esnag.etu.edu.tr/software/hiv_cleavage_site_prediction.rar; you will find a readme file which explains how to set the software in order to work.

Utilizing maximal frequent itemsets and social network analysis for HIV data analysis

“…It has been reported that and positions in octamer are important as they are informative to locate where cleavage happens. In this approach, only frequent itemsets containing items relevant to the mentioned positions have been considered [ 14 ]. The third approach utilizes social network analysis (SNA) methods for filtering.…”

Machine learning approaches to study HIV/AIDS infection: A Review

“…Prediction of coreceptor usage for viral entry from Gp120 V3 loop amino acid sequences using SVM, heuristic and statistical learning methods, two-level machine, random forest, boosted decision tree, and neural network machine learning algorithms has been done in India, Germany and USA respectively (Raghava 2013Sander et al 2007Dybowski 2010and Vaisman 2010. Prediction of HIV-1 protease cleavage site and inhibitors using Feature selection subset method of multi-layered perceptron (FS-MLP) learning, SVM, ANN pharmacophore and docking methods have been done 80.0% ~ 97.4% accuracy in Taiwan, Korea, Turkey and China respectively (Kim et al 2010Singh Su 2016Öztürk et al 2013and Wei et al 2015.…”

The importance of physicochemical characteristics and nonlinear classifiers in determining HIV-1 protease specificity

“…The SVMs were combined into an ensemble and their collective output selected using the "max rule." € Ozt€ urk et al 30 present a novel hybrid algorithm to reduce the dimensionality of orthogonal encoding which looks at the overlap between 2 separate feature selection algorithms; consistency based, and an SVM based method of Recursive Feature Elimination (RFE). € Ozt€ urk et al also highlight combining orthogonal encoding and physicochemical properties as an approach to improving performance.…”

“…30,31,35,46 Given this information, it was decided that each physicochemical encoding should be evaluated in conjunction with orthogonal encoding. Additional evaluations were carried out using combinations of the most promising feature sets: {Orthogonal, Physicochemical, Niu}, {Orthogo-nal, Physicochemical, Niu, z-Scales}, and combining the most promising feature set {Orthogonal, Physicochemical, Niu} with the occurrence percentage, as defined by Jaeger.…”