Hybrid Method for Prediction of Metastasis in Breast Cancer Patients Using Gene Expression Signals

Using primary tumor gene expression has been shown to have the ability of finding metastasis?driving gene markers for predictionof breast cancer recurrence (bcr). however, there are some difficulties associated with analysis of microarray data, which led topoor predictive power and inconsistency of previously introduced gene signatures. in this study, a hybrid method was proposed foridentifying more predictive gene signatures from microarray datasets. initially, the parameters of a rough set (rs) theory basedfeature selection method were tuned to construct a customized gene extraction algorithm. afterward, using rs gene selectionmethod the most informative genes selected from six independent breast cancer datasets. then, combined set of these six signaturesets, containing 114 genes, was evaluated for prediction of bcr. in final, a meta?signature, containing 18 genes, selected from thecombination of datasets and its prediction accuracy compared to the combined signature. the results of 10 fold cross validationtest showed acceptable misclassification error rate (mcr) over 1338 cases of breast cancer patients. in comparison to a recentsimilar work, our approach reached more than 5% reduction in mcr using a fewer number of genes for prediction. the results alsodemonstrated 7% improvement in average accuracy in six utilized datasets, using the combined set of 114 genes in comparison with18-genes meta signature. in this study, a more informative gene signature was selected for prediction of bcr using a rs based geneextraction algorithm. to conclude, combining different signatures demonstrated more stable prediction over independent datasets.