Identification of informative genes and pathways using an improved penalized support vector machine with a weighting scheme

• Main Authors: Weng, Howe Chan, Tan Ah Chik @ Mohamad, Mohd Saberi, Deris, Safaai, Zaki, Nazar, Kasim, Shahreen, Omatu, Sigeru, Juan, Manuel Corchado, Hany, Al Ashwal
• Format: Article
• Published: ELSEVIER 2016
• Subjects: QA75 Electronic computers. Computer science
• Online Access: http://eprints.utm.my/id/eprint/68183/; http://dx.doi.org/10.1016/j.compbiomed.2016.08.004
• Institution: Universiti Teknologi Malaysia

Incorporation of pathway knowledge into microarray analysis has brought better biological interpreta- tion of the analysis outcome. However, most pathway data are manually curated without speci fi c bio- logical context. Non-informative genes could be included when the pathway data is used for analysis of context speci fi c data like cancer microarray data. Therefore, ef fi cient identi fi cation of informative genes is inevitable. Embedded methods like penalized classi fi ers have been used for microarray analysis due to their embedded gene selection. This paper proposes an improved penalized support vector machine with absolute t -test weighting scheme to identify informative genes and pathways. Experiments are done on four microarray data sets. The results are compared with previous methods using 10-fold cross validation in terms of accuracy, sensitivity, speci fi city and F-score. Our method shows consistent improvement over the previous methods and biological validation has been done to elucidate the relation of the selected genes and pathway with the phenotype under study.