Email updates

Keep up to date with the latest news and content from BMC Bioinformatics and BioMed Central.

Open Access Highly Accessed Methodology article

Improving accuracy for cancer classification with a new algorithm for genes selection

Hongyan Zhang125, Haiyan Wang3*, Zhijun Dai12, Ming-shun Chen4 and Zheming Yuan12*

Author Affiliations

1 Hunan Provincial Key Laboratory of Crop Germplasm Innovation and Utilization, Changsha, 410128, China

2 College of Bio-safety Science and Technology, Hunan Agricultural University, Changsha, 410128, China

3 Department of Statistics, Kansas State University, Manhattan, KS, 66506, USA

4 USDA-ARS and Department of Entomology, Kansas State University, Manhattan, KS, 66506, USA

5 College of Information Science and Technology, Hunan Agricultural University, Changsha, 410128, China

For all author emails, please log on.

BMC Bioinformatics 2012, 13:298  doi:10.1186/1471-2105-13-298

Published: 13 November 2012

Additional files

Additional file 1:

This file contains Supplementary Tables S1 - S4. Supplementary Table S1 reports the Accession number, name, and putative function for selected genes in each data set. Supplementary Table S2 gives the comparison of LOOCV accuracy on nine cancer data sets for BMSF with results reported in literature. Supplementary Table S3 list the selected genes from 30 separate runs of BMSF on Leukemia data. Supplementary Table S4 reports the LOOCV accuracy of BMSF, random forest (GeneSrF), SVM-RFE, and 11 other variable selection criteria from RankGene and mRMR. The same number of genes (determined by BMSF) is used for all criteria except for random forest, which automatically determines the number of genes to be used.

Format: PDF Size: 178KB Download file

This file can be viewed with: Adobe Acrobat Reader

Open Data

Additional file 2:

The BMSF Matlab code and datasets with selected genes are included in this file. The NCBI links for the cancer datasets are also included.

Format: PDF Size: 87KB Download file

This file can be viewed with: Adobe Acrobat Reader

Open Data