Identifying tumor origin using a gene expression-based classification map

Abstract

Identifying the primary site in cases of metastatic carcinoma of unknown origin has profound clinical importance in managing cancer patients. Although transcriptional profiling promises molecular solutions to this clinical challenge, simpler and more reliable methods for this purpose are needed. A training set of 11 serial analysis of gene expression (SAGE) libraries was analyzed using a combination of supervised and unsupervised computational methods to select a small group of candidate genes with maximal power to discriminate carcinomas of different tissue origins. Quantitative real-time PCR was used to measure their expression levels in an independent validation set of 62 samples of ovarian, breast, colon, and pancreatic adenocarcinomas and normal ovarian surface epithelial controls. The diagnostic power of this set of genes was evaluated using unsupervised cluster analysis methods. From the training set of 21,321 unique SAGE transcript tags derived from 11 libraries, five genes were identified with expression patterns that distinguished four types of adenocarcinomas. Quantitative real-time PCR expression data obtained from the validation set clustered tumor samples in an unsupervised manner, generating a self-organized map with distinctive tumor site-specific domains. Eighty-one percent (50 of 62) of the carcinomas were correctly allocated in their corresponding diagnostic regions. Metastases clustered tightly with their corresponding primary tumors. A classification map diagnostic of tumor types was generated based on expression patterns of five genes selected from the SAGE database. This expression map analysis may provide a reliable and practical approach to determine tumor type in cases of metastatic carcinoma of clinically unknown origin.