Mining expressed sequence tags identifies cancer markers of clinical interest

Background: Gene expression data are a rich source of information about the transcriptional disregulation of genes in cancer. Genes that display differential regulation in cancer are a subtype of cancer biomarkers. Results: We present an approach to mine expressed sequence tags to discover cancer biomarkers. A false discovery rate analysis suggests that the approach generates less than 22% false discoveries when applied to combined human and mouse whole genome screens. With this approach, we identify the 200 genes most consistently differentially expressed in cancer ( called HM200) and proceed to characterize these genes. When used for prediction in a variety of cancer classification tasks (in 24 independent cancer microarray datasets, 59 classifications total), we show that HM200 and the shorter gene list HM100 are very competitive cancer biomarker sets. Indeed, when compared to 13 published cancer marker gene lists, HM200 achieves the best or second best classification performance in 79% of the classifications considered. Conclusion: These results indicate the existence of at least one general cancer marker set whose predictive value spans several tumor types and classification types. Our comparison with other marker gene lists shows that HM200 markers are mostly novel cancer markers. We also identify the previously published Pomeroy-400 list as another general cancer marker set. Strikingly, Pomeroy-400 has 27 genes in common with HM200. Our data suggest that a core set of genes are responsive to the deregulation of pathways involved in tumorigenesis in a variety of tumor types and that these genes could serve as transcriptional cancer markers in applications of clinical interest. Finally, our study suggests new strategies to select and evaluate cancer biomarkers in microarray studies.