Selection and Classification of Gene Expression Data Using a MF-GA-TS-SVM Approach

• Published in: Intelligent Computing in Bioinformatics Vol. 8590; pp. 300 - 308
• Main Authors: Luis, Hernández-Montiel Alberto, Edmundo, Bonilla-Huerta, Roberto, Morales-Caporal, José, Guevara-García Antonio
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2014; Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: Algorithms & data structures; Artificial intelligence; Feature Selection; Gene Expression Data; Genetic Algorithm; Support Vector Machine; Tabu Search; User interface design & usability
• ISBN: 9783319093291; 3319093290
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-319-09330-7_36

This article proposes a Multiple-Filter (MF) using a genetic algorithm (GA) and Tabu Search (TS) combined with a Support Vector Machine (SVM) for gene selection and classification of DNA microarray data. The proposed method is designed to select a subset of relevant genes that classify the DNA-microarray data more accurately. First, five traditional statistical methods are used for preliminary gene selection (Multiple Filter). Then different relevant gene subsets are selected by using a Wrapper (GA/TS/SVM). A gene subset, consisting of relevant genes, is obtained from each statistical method, by analyzing the frequency of each gene in the different gene subsets. Finally, the most frequent genes are evaluated by the Multiple Wrapper approach to obtain a final relevant gene subset. The proposed method is tested in four DNA-microarray datasets. In the experimental results it is observed that our model work very well than other methods reported in the literature.