PT  - JOURNAL ARTICLE
AU  - Majid Mohammadi
AU  - Hossein Sharifi Noghabi
AU  - Ghosheh Abed Hodtani
AU  - Habib Rajabi Mashhadi
TI  - Robust and Stable Gene Selection via Maximum-Minimum Correntropy Criterion
AID  - 10.1101/029538
DP  - 2015 Jan 01
TA  - bioRxiv
PG  - 029538
4099  - http://biorxiv.org/content/early/2015/10/21/029538.short
4100  - http://biorxiv.org/content/early/2015/10/21/029538.full
AB  - One of the central challenges in cancer research is identifying significant genes among thousands of others on a microarray. Since preventing outbreak and progression of cancer is the ultimate goal in bioinformatics and computational biology, detection of genes that are most involved is vital and crucial. In this article, we propose a Maximum-Minimum Correntropy Criterion (MMCC) approach for selection of biologically meaningful genes from microarray data sets which is stable, fast and robust against diverse noise and outliers and competitively accurate in comparison with other algorithms. Moreover, via an evolutionary optimization process, the optimal number of features for each data set is determined. Through broad experimental evaluation, MMCC is proved to be significantly better compared to other well-known gene selection algorithms for 25 commonly used microarray data sets. Surprisingly, high accuracy in classification by Support Vector Machine (SVM) is achieved by less than10 genes selected by MMCC in all of the cases.