Consistency of predictive signature genes and classifiers generated using different microarray platforms

• Published in: The pharmacogenomics journal Vol. 10; no. 4; pp. 247 - 257
• Main Authors: Fan, X, Lobenhofer, E K, Chen, M, Shi, W, Huang, J, Luo, J, Zhang, J, Walker, S J, Chu, T-M, Li, L, Wolfinger, R, Bao, W, Paules, R S, Bushel, P R, Li, J, Shi, T, Nikolskaya, T, Nikolsky, Y, Hong, H, Deng, Y, Cheng, Y, Fang, H, Shi, L, Tong, W
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 01.08.2010; Nature Publishing Group
• Subjects: 631/208/191/2018; 631/208/212/1728; 692/53/2423; 692/699/1503/1607/2749; Algorithms; Animals; Biomedical and Life Sciences; Biomedicine; Databases, Genetic; DNA microarrays; DNA Probes; Gene Expression; Gene Expression Profiling; Genes; Human Genetics; Humans; Methods; Oligonucleotide Array Sequence Analysis - methods; Oncology; Original; original-article; Pharmacogenetics; Pharmacogenetics - methods; Pharmacotherapy; Phenotype; Predictive Value of Tests; Psychopharmacology; Quality Control; Technology application; Toxicogenetics - methods; United States; classifier; microarray; cross-platform; gene signature; MAQC; hepatotoxicity
• ISSN: 1470-269X; 1473-1150; 1473-1150
• DOI: 10.1038/tpj.2010.34

Microarray-based classifiers and associated signature genes generated from various platforms are abundantly reported in the literature; however, the utility of the classifiers and signature genes in cross-platform prediction applications remains largely uncertain. As part of the MicroArray Quality Control Phase II (MAQC-II) project, we show in this study 80–90% cross-platform prediction consistency using a large toxicogenomics data set by illustrating that: (1) the signature genes of a classifier generated from one platform can be directly applied to another platform to develop a predictive classifier; (2) a classifier developed using data generated from one platform can accurately predict samples that were profiled using a different platform. The results suggest the potential utility of using published signature genes in cross-platform applications and the possible adoption of the published classifiers for a variety of applications. The study reveals an opportunity for possible translation of biomarkers identified using microarrays to clinically validated non-array gene expression assays.