Gene Microarray Cancer Classification using Correlation Based Feature Selection Algorithm and Rules Classifiers

Abstract

Gene microarray classification problems are considered a challenge task since the datasets contain few number of samples with high number of genes (features). The genes subset selection in microarray data play an important role for minimizing the computational load and solving classification problems. In this paper, the Correlation-based Feature Selection (CFS) algorithm is utilized in the feature selection process to reduce the dimensionality of data and finding a set of discriminatory genes. Then, the Decision Table, JRip, and OneR are employed for classification process. The proposed approach of gene selection and classification is tested on 11 microarray datasets and the performances of the filtered datasets are compared with the original datasets. The experimental results showed that CFS can effectively screen irrelevant, redundant, and noisy features. In addition, the results for all datasets proved that the proposed approach with a small number of genes can achieve high prediction accuracy and fast computational speed. Considering the average accuracy for all the analysis of microarray data, the JRip achieved the best result as compared to Decision Table, and OneR classifier. The proposed approach has a remarkable impact on the classification accuracy especially when the data is complicated with multiple classes and high number of genes.

Incremental Search for Informative Gene Selection in Cancer Classification

“…Further, the classification accuracy and the amount of biomarkers for Leukemia4 dataset is 100% and five in the proposed study whereas it is 100% yet with seven genes in [32]. Moreover, the performance of Leukemia4 classification is better than that of mentioned in the past [4,7,12].…”

“…Recently, computational approaches have received more attention in cancer classification [4][5][6][7][8]. However, the performance of many existing cancer classification approaches does not seem to be sufficiently robust [4,8].…”

“…Recently, computational approaches have received more attention in cancer classification [4][5][6][7][8]. However, the performance of many existing cancer classification approaches does not seem to be sufficiently robust [4,8]. Some of them suffer from poor performance in terms of classification [9,10] whereas others result in huge gene's subsets [8,11,12].…”

Hybrid feature selection model based on relief‐based algorithms and regulizer algorithms for cancer classification

“…Kernel‐based techniques 4,5 like SVM have already been used for binary disease classification problems. Gene selection 6 and neural networks 7 based classifications were also reported in microarray data analysis 8 . This article presents a novel Hybrid feature selection model called RBARegulizer model based on two types of feature selection techniques two RBAs (ReliefF, MultiSURF) algorithms to select most important genes and three regularizer algorithms (Lasso, Elastic Net, Elastic Net CV) to reduce the feature subset, remove the noisy and irrelevant feature to improve the performance and accuracy of cancer (microarray) data classification and three classifiers are support vector machine, multilayer perceptron, and random forest for evaluation to the model, The relief‐based feature selection algorithms (RBAs) such as ReliefF and MultiSURF 9 .…”

Scoring Functions and Modeling of Structure-Activity Relationships for Cannabinoid Receptors

“…The cannabinoids activate special receptors in the human body to produce a pharmacological action, particularly in the central nervous system and the immune system. Cannabinoids could be useful for treating side effects in cancer [5][6][7][8][9]. Docking experiments with these receptors and cannabinoid ligands were performed and evaluated with scoring functions embedded in the software GOLD 5.2.…”