A Review of Cancer Classification Software for Gene Expression Data

Abstract

Microarray technology provides a way for researchers to measure the expression level of thousands of genes simultaneously in a single experiment. Due to the increasing amount of microarray data, the field of microarray data analysis has become a major topic among researchers. One of the examples of microarray data analysis is classification. Classification is the process of determining the classes for samples. The goal of classification is to identify the differentially expressed genes so that these genes can be used to predict the classes for new samples. In order to perform the tasks of classification of microarray data, classification software is required for effective classification and analysis of large-scale data. This paper reviews numerous classification software applications for gene expression data. In this paper, the reviewed software can be categorized into six supervised classification methods: Support Vector Machine, K-Nearest Neighbour, Neural Network, Linear Discriminant Analysis, Bayesian Classifier, and Random Forest. implementation of software that facilitates and eases the understanding of biological processes. InSrinivasan et al. [3],the most general definition of bioinformatics in addressing biological problems is discussed.Most biomedical researchers are looking for appropriate software which is not only can achieve high prediction accuracy but also includes a user friendly design in order to ease the implementation. Moreover, such softwareisvery useful if the source code is available.In addition, the software should be up-to-date with the related information to make sure that it is competitive with other software.In this paper, the classification software applications for six supervised classification methodsare reviewed. The six supervised classification methods include the Support Vector Machine (SVM), K-Nearest Neighbour (KNN), Neural Network (NN), Bayesian Classifier, Linear Discriminant Analysis (LDA), and Random Forest (RF). Furthermore, the sources of the software and web-based applications are listed as well. Software for Support Vector Machine (SVM) LIBSVMLIBSVM, a library for SVMs, was developed by Chang and Lin [4]. The main purpose of developing this software was to help users implementing SVM. This package supports three main learning tasks: classification, regression, and estimation of probability. For classification, it supports binary and multi-class classification. It also includes various formulations of SVM such as c-classification, v-classification, ∈-regression, and vregression. Other features include support for cross-validation for performance measurement, model selection, and solving of unbalanced data using weighted SVM. It is mainly implemented in C++ and Java but there are many extensions such as R, MATLAB, Python, and Perl that have been developed by Chang and Lin and others. Moreover, it also provides different kernel settings such as linear, polynomial, and radial basis functions. This package is mainly for Windows and Linux. SVMlightSVMlight was developed...

A Comparative Analysis of Feature Extraction Methods for Classifying Colon Cancer Microarray Data

“…The algorithms like (LDA, QDA, and KNN) have been used in this work and found that LDA have performed efficiently and reduces the attributes effectively. In 2014 [16] reviewed numerous development application to help users implement feature extraction of gene expression data, the paper presented review of software for feature ext raction methods such as PCA, ICA, PLA and LLE. The software applications have limitations in terms of co mputational performance and there is need for development of classification methods to improve performances of these feature extraction methods.…”

“…The software applications have limitations in terms of co mputational performance and there is need for development of classification methods to improve performances of these feature extraction methods. 2015 [16] co mpared dimension reduction based on logic regression models for the case-control genome-wide association by employing PCA and PLS, there were limitat ions in the interaction of the genes of dataset used affecting the goodness of fit and accuracy of the parameter estimation of PLS and needed further investigations.…”

“…This is attained by transforming the p initial variables X=[x 1 ,x 2 ,….,x p ], [16] to a latest set of q predictor variables. PCA is a widely used unsupervised feature extraction technique; it works by replacing the original variables in a data with nu merical variab les called p rincipal co mponent by capturing the most descriptive features with respect to the most relevant ones [15].…”

“…PCA identifies patterns of similarit ies and differences in a data, these patterns are determined and can be co mpressed by reducing the numbers of dimensions without much loss of information. In order to conduct the PCA analysis for the input data, the following steps are performed by adopting [16] …”

“…Partial Least Square (PLS) is a supervised feature extraction technique, which is widely used as a procedure in modeling associations linking blocks of experimental variables by means of latent variable, it tries finding uncorrelated linear transformations (latent components) of the original predictor variables which have high covariance with the response variables [16]. The goal of PLS is to find the linear relationship between the response and exp lanatory variables y and X:…”