Affiliation: The University of Texas
- Lack of sufficiently strong informative features limits the potential of gene expression analysis as predictive tool for many clinical classification problemsKenneth R Hess
Department of Biostatistics, University of Texas MD Anderson Cancer Center, Houston, USA
BMC Bioinformatics 12:463. 2011..Prediction models were trained to identify which cases had been perturbed. Performance was estimated using Monte-Carlo cross validation...