scholarly journals Gene Selection using a Hybrid RFE Along with LASSO for Cancer Classification

2019 ◽  
Vol 9 (1S3) ◽  
pp. 83-96
Keyword(s):  
Gene Expression ◽  
Gene Expression Data ◽  
Gene Selection ◽  
Classification Model ◽  
Recursive Feature Elimination ◽  
Support Vector ◽  
Expression Data ◽  
Cancer Prediction ◽  
Selection Operator ◽  
Selection Of

Gene expression profiling using microarray technology has done with the chip based phenomena. For studying gene expression data are more helpful in knowing various diseases and more useful in finding diseases. Recently in the bioinformatics field, cancer prediction using gene expression data had made the assuring area. Samples having the gene attributes will not surely give the efficient amount of classification. Overcoming these contribution, a strong method is required for selecting the relevant gene features for building the classification model effectively. Basically least absolute shrinkage and selection operator (LASSO) and Recursive feature elimination (RFE) are automatic gene feature selection methods used for classification. Here in our proposed work, we use these two methods as a hybrid one for selecting the features and later it applied into the Support vector machine (SVM) for easy classification. It made best when compared to the existing techniques by their performance measures, were regulated on six publically available cancer datasets. Just out it gives the good awareness in the selection of features.

scholarly journals Statistical Approach for Biologically Relevant Gene Selection from High-Throughput Gene Expression Data

2020 ◽  
Author(s):  
Samarendra Das ◽  
Shesh N. Rai
Keyword(s):  
Gene Expression ◽  
Statistical Approach ◽  
Gene Selection ◽  
Statistical Significance ◽  
High Dimensional ◽  
Support Vector ◽  
Expression Data ◽  
Test Statistic ◽  
Biologically Relevant ◽  
Selection Of

Selection of biologically relevant genes from high dimensional expression data is a key research problem in gene expression genomics. Most of the available gene selection methods are either based on relevancy or redundancy measure, which are usually adjudged through post selection classification accuracy. Through these methods the ranking of genes was done on a single high-dimensional expression data, which leads to the selection of spuriously associated and redundant genes. Hence, we developed a statistical approach through combining Support Vector Machine with Maximum Relevance and Minimum Redundancy under a sound statistical setup for the selection of biologically relevant genes. Here, the genes are selected through statistical significance values computed using a non-parametric test statistic under a bootstrap based subject sampling model. Further, a systematic and rigorous evaluation of the proposed approach with nine existing competitive methods was carried on six different real crop gene expression datasets. This performance analysis was carried out under three comparison settings, i.e. subject classification, biological relevant criteria based on quantitative trait loci, and gene ontology. Our analytical results showed that the proposed approach selects genes that are more biologically relevant as compared to the existing methods. Moreover, the proposed approach was also found to be better with respect to the competitive existing methods. The proposed statistical approach provides a framework for combining filter, and wrapper methods of gene selection.

CASCADING SVMS AS A TOOL FOR MEDICAL DIAGNOSIS USING MULTI-CLASS GENE EXPRESSION DATA

2006 ◽  
Vol 15 (03) ◽  
pp. 335-352
Author(s):  
ILIAS N. FLAOUNAS ◽  
DIMITRIS K. IAKOVIDIS ◽  
DIMITRIS E. MAROULIS
Keyword(s):  
Gene Expression ◽  
Gene Expression Data ◽  
Medical Diagnosis ◽  
Gene Selection ◽  
Selection Process ◽  
Support Vector ◽  
Specific Gene ◽  
Processing Unit ◽  
Expression Data ◽  
Medical Diagnostic

In this paper we propose a novel Support Vector Machines-based architecture for medical diagnosis using multi-class gene expression data. It consists of a pre-processing unit and N-1 sequentially ordered blocks capable of classifying N classes in a cascading manner. Each block embodies both a gene selection and a classification module. It offers the flexibility of constructing block-specific gene expression spaces and hypersurfaces for the discrimination of the different classes. The proposed architecture was applied for medical diagnostic tasks including prostate and lung cancer diagnosis. Its performance was evaluated by using a leave-one-out cross validation approach which avoids the bias introduced by the gene selection process. The results show that it provides high accuracy which in most cases exceeds the accuracy achieved by the popular one-vs-one and one-vs-all SVM combination schemes and Nearest-Neighbor classifiers. The cascading SVMs can be successfully applied as a medical diagnostic tool.

scholarly journals A COMPARATIVE STUDY ON GENE SELECTION METHODS FOR TISSUES CLASSIFICATION ON LARGE SCALE GENE EXPRESSION DATA

2016 ◽  
Vol 78 (5-10) ◽  
Author(s):  
Farzana Kabir Ahmad
Keyword(s):  
Gene Expression ◽  
Feature Selection ◽  
Gene Expression Data ◽  
Large Scale ◽  
Gene Selection ◽  
Support Vector ◽  
Breast Cancer Dataset ◽  
Expression Data ◽  
Selection Methods ◽  
Normal Tissues

Deoxyribonucleic acid (DNA) microarray technology is the recent invention that provided colossal opportunities to measure a large scale of gene expressions simultaneously. However, interpreting large scale of gene expression data remain a challenging issue due to their innate nature of “high dimensional low sample size”. Microarray data mainly involved thousands of genes, n in a very small size sample, p which complicates the data analysis process. For such a reason, feature selection methods also known as gene selection methods have become apparently need to select significant genes that present the maximum discriminative power between cancerous and normal tissues. Feature selection methods can be structured into three basic factions; a) filter methods; b) wrapper methods and c) embedded methods. Among these methods, filter gene selection methods provide easy way to calculate the informative genes and can simplify reduce the large scale microarray datasets. Although filter based gene selection techniques have been commonly used in analyzing microarray dataset, these techniques have been tested separately in different studies. Therefore, this study aims to investigate and compare the effectiveness of these four popular filter gene selection methods namely Signal-to-Noise ratio (SNR), Fisher Criterion (FC), Information Gain (IG) and t-Test in selecting informative genes that can distinguish cancer and normal tissues. In this experiment, common classifiers, Support Vector Machine (SVM) is used to train the selected genes. These gene selection methods are tested on three large scales of gene expression datasets, namely breast cancer dataset, colon dataset, and lung dataset. This study has discovered that IG and SNR are more suitable to be used with SVM. Furthermore, this study has shown SVM performance remained moderately unaffected unless a very small size of genes was selected.

scholarly journals Statistical Approach for Biologically Relevant Gene Selection from High-Throughput Gene Expression Data

Entropy ◽  
2020 ◽  
Vol 22 (11) ◽  
pp. 1205
Author(s):  
Samarendra Das ◽  
Shesh N. Rai
Keyword(s):  
Gene Expression ◽  
Statistical Approach ◽  
Gene Selection ◽  
Statistical Significance ◽  
High Dimensional ◽  
Support Vector ◽  
Expression Data ◽  
Test Statistic ◽  
Biologically Relevant ◽  
Selection Of

Selection of biologically relevant genes from high-dimensional expression data is a key research problem in gene expression genomics. Most of the available gene selection methods are either based on relevancy or redundancy measure, which are usually adjudged through post selection classification accuracy. Through these methods the ranking of genes was conducted on a single high-dimensional expression data, which led to the selection of spuriously associated and redundant genes. Hence, we developed a statistical approach through combining a support vector machine with Maximum Relevance and Minimum Redundancy under a sound statistical setup for the selection of biologically relevant genes. Here, the genes were selected through statistical significance values and computed using a nonparametric test statistic under a bootstrap-based subject sampling model. Further, a systematic and rigorous evaluation of the proposed approach with nine existing competitive methods was carried on six different real crop gene expression datasets. This performance analysis was carried out under three comparison settings, i.e., subject classification, biological relevant criteria based on quantitative trait loci and gene ontology. Our analytical results showed that the proposed approach selects genes which are more biologically relevant as compared to the existing methods. Moreover, the proposed approach was also found to be better with respect to the competitive existing methods. The proposed statistical approach provides a framework for combining filter and wrapper methods of gene selection.

A multi-objective strategy in genetic algorithms for gene selection of gene expression data

2009 ◽  
Vol 13 (2) ◽  
pp. 410-413 ◽  
Author(s):  
Mohd Saberi Mohamad ◽  
Sigeru Omatu ◽  
Safaai Deris ◽  
Muhammad Faiz Misman ◽  
Michifumi Yoshioka
Keyword(s):  
Gene Expression ◽  
Genetic Algorithms ◽  
Gene Expression Data ◽  
Gene Selection ◽  
Expression Data ◽  
Multi Objective ◽  
Selection Of

scholarly journals Classification of Gene Expression Data using Efficient Feature Selection Technique and Resampling Method

2019 ◽  
Vol 8 (6) ◽  
pp. 406-414
Keyword(s):  
Gene Expression ◽  
Feature Selection ◽  
Gene Expression Data ◽  
Classification Model ◽  
Support Vector ◽  
Expression Data ◽  
Feature Selection Technique ◽  
Selection Technique ◽  
Resampling Method

Microarray technology has been developed as one of the powerful tools that have attracted many researchers to analyze gene expression level for a given organism. It has been observed that gene expression data have very large (in terms of thousands) of features and less number of samples (in terms of hundreds). This characteristic makes difficult to do an analysis of gene expression data. Hence efficient feature selection technique must be applied before we go for any kind of analysis. Feature selection plays a vital role in the classification of gene expression data. There are several feature selection techniques have been induced in this field. But Support Vector Machine with Recursive Feature Elimination (SVM-RFE) has been proven as the promising feature selection methods among others. SVM-RFE ranks the genes (features) by training the SVM classification model and with the combination of RFE method key genes are selected. Huge time consumption is the main issue of SVM-RFE. We introduced an efficient implementation of linier SVM to overcome this problem and improved the RFE with variable step size. Then, combined method was used for selecting informative genes. Effective resampling method is proposed to preprocess the datasets. This is used to make the distribution of samples balanced, which gives more reliable classification results. In this paper, we have also studied the applicability of common classifiers. Detailed experiments are conducted on four commonly used microarray gene expression datasets. The results show that the proposed method comparable classification performance

Sign in / Sign up

Export Citation Format

Share Document