Table of Contents Author Guidelines Submit a Manuscript
The Scientific World Journal
Volume 2012 (2012), Article ID 989637, 9 pages
http://dx.doi.org/10.1100/2012/989637
Research Article

Robust Microarray Meta-Analysis Identifies Differentially Expressed Genes for Clinical Prediction

1Department of Biomedical Engineering, Georgia Institute of Technology and Emory University, 313 Ferst Drive, Atlanta, GA 30332, USA
2Department of Pathology and Laboratory Medicine, Emory University School of Medicine, Grady Health System, Grady Memorial Hospital, Atlanta, GA 30303, USA

Received 2 November 2012; Accepted 28 November 2012

Academic Editors: N. S. T. Hirata, M. A. Kon, and K. Najarian

Copyright © 2012 John H. Phan et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Supplementary Material

Supplemental Table S1 – Rating meta-analysis methods by prediction performance when combining all available datasets. This table lists the predictive performance (AUC, area under the ROC curve x 100) for each clinical application (breast cancer, renal cancer, and pancreatic cancer), data platform heterogeneity (Hom: Homogeneous, Het: Heterogeneous), and classifier (LR: Logistic Regression, DLDA: Diagonal LDA, and Linear SVM). The numbers in parentheses indicate the performance rating relative to other meta-analysis methods (rated horizontally, higher is better). A mean rating is computed for each clinical application and each meta-analysis method across all combinations of data platform heterogeneity and classifier. An overall mean rating is computed for each meta-analysis method. Ratings are proportional to bar lengths in Figure 3.

  1. Supplementary Material