A Comparative Study of Feature Selection and Classification Methods for Gene Expression Data of Glioma

Handle URI:
http://hdl.handle.net/10754/552481
Title:
A Comparative Study of Feature Selection and Classification Methods for Gene Expression Data of Glioma
Authors:
Abusamra, Heba
Abstract:
Microarray gene expression data gained great importance in recent years due to its role in disease diagnoses and prognoses which help to choose the appropriate treatment plan for patients. This technology has shifted a new era in molecular classification. Interpreting gene expression data remains a difficult problem and an active research area due to their native nature of “high dimensional low sample size”. Such problems pose great challenges to existing classification methods. Thus, effective feature selection techniques are often needed in this case to aid to correctly classify different tumor types and consequently lead to a better understanding of genetic signatures as well as improve treatment strategies. This paper aims on a comparative study of state-of-the- art feature selection methods, classification methods, and the combination of them, based on gene expression data. We compared the efficiency of three different classification methods including: support vector machines, k-nearest neighbor and random forest, and eight different feature selection methods, including: information gain, twoing rule, sum minority, max minority, gini index, sum of variances, t-statistics, and one-dimension support vector machine. Five-fold cross validation was used to evaluate the classification performance. Two publicly available gene expression data sets of glioma were used in the experiments. Results revealed the important role of feature selection in classifying gene expression data. By performing feature selection, the classification accuracy can be significantly boosted by using a small number of genes. The relationship of features selected in different feature selection methods is investigated and the most frequent features selected in each fold among all methods for both datasets are evaluated.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Citation:
A Comparative Study of Feature Selection and Classification Methods for Gene Expression Data of Glioma 2013, 23:5 Procedia Computer Science
Journal:
Procedia Computer Science
Conference/Event name:
4th International Conference on Computational Systems-Biology and Bioinformatics, CSBio 2013
Issue Date:
1-Nov-2013
DOI:
10.1016/j.procs.2013.10.003
Type:
Conference Paper
ISSN:
18770509
Additional Links:
http://linkinghub.elsevier.com/retrieve/pii/S1877050913011381
Appears in Collections:
Conference Papers; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorAbusamra, Hebaen
dc.date.accessioned2015-05-07T14:17:37Zen
dc.date.available2015-05-07T14:17:37Zen
dc.date.issued2013-11-01en
dc.identifier.citationA Comparative Study of Feature Selection and Classification Methods for Gene Expression Data of Glioma 2013, 23:5 Procedia Computer Scienceen
dc.identifier.issn18770509en
dc.identifier.doi10.1016/j.procs.2013.10.003en
dc.identifier.urihttp://hdl.handle.net/10754/552481en
dc.description.abstractMicroarray gene expression data gained great importance in recent years due to its role in disease diagnoses and prognoses which help to choose the appropriate treatment plan for patients. This technology has shifted a new era in molecular classification. Interpreting gene expression data remains a difficult problem and an active research area due to their native nature of “high dimensional low sample size”. Such problems pose great challenges to existing classification methods. Thus, effective feature selection techniques are often needed in this case to aid to correctly classify different tumor types and consequently lead to a better understanding of genetic signatures as well as improve treatment strategies. This paper aims on a comparative study of state-of-the- art feature selection methods, classification methods, and the combination of them, based on gene expression data. We compared the efficiency of three different classification methods including: support vector machines, k-nearest neighbor and random forest, and eight different feature selection methods, including: information gain, twoing rule, sum minority, max minority, gini index, sum of variances, t-statistics, and one-dimension support vector machine. Five-fold cross validation was used to evaluate the classification performance. Two publicly available gene expression data sets of glioma were used in the experiments. Results revealed the important role of feature selection in classifying gene expression data. By performing feature selection, the classification accuracy can be significantly boosted by using a small number of genes. The relationship of features selected in different feature selection methods is investigated and the most frequent features selected in each fold among all methods for both datasets are evaluated.en
dc.relation.urlhttp://linkinghub.elsevier.com/retrieve/pii/S1877050913011381en
dc.rightsArchived with thanks to Procedia Computer Science. http://creativecommons.org/licenses/by-nc-nd/3.0/en
dc.subjectgene expressionen
dc.subjectmicroarray dataen
dc.subjectfeature selectionen
dc.subjectclassificationen
dc.subjectgliomaen
dc.titleA Comparative Study of Feature Selection and Classification Methods for Gene Expression Data of Gliomaen
dc.typeConference Paperen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.identifier.journalProcedia Computer Scienceen
dc.conference.date2013-11-07 to 2013-11-09en
dc.conference.name4th International Conference on Computational Systems-Biology and Bioinformatics, CSBio 2013en
dc.conference.locationSeoul, KORen
dc.eprint.versionPublisher's Version/PDFen
kaust.authorAbusamra, Hebaen
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.