This Article Full Text Full Text (PDF) Purchase Article View Shopping Cart Services Similar articles in this journal Similar articles in PubMed Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via HighWire Citing Articles via Google Scholar Google Scholar Articles by Bloom, G. Articles by Yeatman, T. J. Search for Related Content PubMed PubMed Citation Articles by Bloom, G. Articles by Yeatman, T. J.

(American Journal of Pathology. 2004;164:9-16.)
© 2004 American Society for Investigative Pathology

Short Communication

Multi-Platform, Multi-Site, Microarray-Based Human Tumor Classification

Greg Bloom^*, Ivana V. Yang, David Boulware^*, Ka Yin Kwong, Domenico Coppola^*, Steven Eschrich^*, John Quackenbush and Timothy J. Yeatman^*

From the H. Lee Moffitt Cancer Center,^* University of South Florida, Tampa, Florida; and The Institute for Genomic Research, Rockville, Maryland

The introduction of gene expression profiling has resulted in the production of rich human data sets with potential for deciphering tumor diagnosis, prognosis, and therapy. Here we demonstrate how artificial neural networks (ANNs) can be applied to two completely different microarray platforms (cDNA and oligonucleotide), or a combination of both, to build tumor classifiers capable of deciphering the identity of most human cancers. First, 78 tumors representing eight different types of histologically similar adenocarcinoma, were evaluated with a 32k cDNA microarray and correctly classified by a cDNA-based ANN, using independent training and test sets, with a mean accuracy of 83%. To expand our approach, oligonucleotide data derived from six independent performance sites, representing 463 tumors and 21 tumor types, were assembled, normalized, and scaled. An oligonucleotide-based ANN, trained on a random fraction of the tumors (n = 343), was 88% accurate in predicting known pathological origin of the remaining fraction of tumors (n = 120) not exposed to the training algorithm. Finally, a mixed-platform classifier using a combination of both cDNA and oligonucleotide microarray data from seven performance sites, normalized and scaled from a large and diverse tumor set (n = 539), produced similar results (85% accuracy) on independent test sets. Further validation of our classifiers was achieved by accurately (84%) predicting the known primary site of origin for an independent set of metastatic lesions (n = 50), resected from brain, lung, and liver, potentially addressing the vexing classification problems imposed by unknown primary cancers. These cDNA- and oligonucleotide-based classifiers provide a first proof of principle that data derived from multiple platforms and performance sites can be exploited to build multi-tissue tumor classifiers.

This article has been cited by other articles:

				J. Quackenbush Extracting biology from high-dimensional biological data J. Exp. Biol., May 1, 2007; 210(9): 1507 - 1517. [Abstract] [Full Text] [PDF]

				E. H. Jensen, J. M. Lewis, J. M. McLoughlin, M. D. Alvarado, A. Daud, J. Messina, S. Enkemann, T. J. Yeatman, V. K. Sondak, and A. I. Riker Down-Regulation of Pro-Apoptotic Genes is an Early Event in the Progression of Malignant Melanoma Ann. Surg. Oncol., April 1, 2007; 14(4): 1416 - 1423. [Abstract] [Full Text] [PDF]

				G. Pentheroudakis, E. Briasoulis, and N. Pavlidis Cancer of Unknown Primary Site: Missing Primary or Missing Biology? Oncologist, April 1, 2007; 12(4): 418 - 425. [Abstract] [Full Text] [PDF]

				D. N. Hayes, S. Monti, G. Parmigiani, C. B. Gilks, K. Naoki, A. Bhattacharjee, M. A. Socinski, C. Perou, and M. Meyerson Gene Expression Profiling Reveals Reproducible Human Lung Adenocarcinoma Subtypes in Multiple Independent Patient Cohorts J. Clin. Oncol., November 1, 2006; 24(31): 5079 - 5090. [Abstract] [Full Text] [PDF]

				D. Talantov, J. Baden, T. Jatkoe, K. Hahn, J. Yu, Y. Rajpurohit, Y. Jiang, C. Choi, J. S. Ross, D. Atkins, et al. A Quantitative Reverse Transcriptase-Polymerase Chain Reaction Assay to Identify Metastatic Carcinoma Tissue of Origin J. Mol. Diagn., July 1, 2006; 8(3): 320 - 329. [Abstract] [Full Text] [PDF]

				J. Quackenbush Microarray analysis and tumor classification. N. Engl. J. Med., June 8, 2006; 354(23): 2463 - 2472. [Full Text] [PDF]

				S. Eschrich, I. Yang, G. Bloom, K. Y. Kwong, D. Boulware, A. Cantor, D. Coppola, M. Kruhoffer, L. Aaltonen, T. F. Orntoft, et al. Molecular Staging for Survival Prediction of Colorectal Cancer Patients J. Clin. Oncol., May 20, 2005; 23(15): 3526 - 3535. [Abstract] [Full Text] [PDF]

				R. W. Tothill, A. Kowalczyk, D. Rischin, A. Bousioutas, I. Haviv, R. K. van Laar, P. M. Waring, J. Zalcberg, R. Ward, A. V. Biankin, et al. An Expression-Based Site of Origin Diagnostic Method Designed for Clinical Application to Cancer of Unknown Origin Cancer Res., May 15, 2005; 65(10): 4031 - 4040. [Abstract] [Full Text] [PDF]

				E. Rico-Bautista, C. J. Greenhalgh, P. Tollet-Egnell, D. J. Hilton, W. S. Alexander, G. Norstedt, and A. Flores-Morales Suppressor of Cytokine Signaling-2 Deficiency Induces Molecular and Metabolic Changes that Partially Overlap with Growth Hormone-Dependent Effects Mol. Endocrinol., March 1, 2005; 19(3): 781 - 793. [Abstract] [Full Text] [PDF]

				K. K. Dobbin, D. G. Beer, M. Meyerson, T. J. Yeatman, W. L. Gerald, J. W. Jacobson, B. Conley, K. H. Buetow, M. Heiskanen, R. M. Simon, et al. Interlaboratory Comparability Study of Cancer Gene Expression Analysis Using Oligonucleotide Microarrays Clin. Cancer Res., January 15, 2005; 11(2): 565 - 572. [Abstract] [Full Text] [PDF]

				C. Morrison, W. Farrar, J. Kneile, N. Williams, Y. Liu-Stratton, A. Bakaletz, M. A. Aldred, and C. Eng Molecular Classification of Parathyroid Neoplasia by Gene Expression Profiling Am. J. Pathol., August 1, 2004; 165(2): 565 - 576. [Abstract] [Full Text] [PDF]