Using the GEMS System for Cancer Diagnosis and Biomarker Discovery from Microarray Gene Expression Data

Alexander Statnikov, Ioannis Tsamardinos, Constantin F. Aliferis

We will demonstrate the GEMS system for automated development and evaluation of high-quality cancer diagnostic models and biomarker discovery from microarray gene expression data. The development of GEMS was informed by the results of an extensive algorithmic evaluation using 11 microarray datasets. The system was further evaluated in two cross-dataset applications and using 5 microarray datasets. The performance of models produced by GEMS is comparable or better than the results obtained by human analysts, and these models generalize well to independent samples in cross-dataset applications. The system is freely available for download from for noncommercial use.

This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.