Prognostic classification of relapsing favorable histology Wilms tumor using cDNA microarray expression profiling and support vector machines
Article first published online: 16 JUN 2004
Copyright © 2004 Wiley-Liss, Inc.
Genes, Chromosomes and Cancer
Volume 41, Issue 1, pages 65–79, September 2004
How to Cite
Williams, R. D., Hing, S. N., Greer, B. T., Whiteford, C. C., Wei, J. S., Natrajan, R., Kelsey, A., Rogers, S., Campbell, C., Pritchard-Jones, K. and Khan, J. (2004), Prognostic classification of relapsing favorable histology Wilms tumor using cDNA microarray expression profiling and support vector machines. Genes Chromosom. Cancer, 41: 65–79. doi: 10.1002/gcc.20060
- Issue published online: 28 JUN 2004
- Article first published online: 16 JUN 2004
- Manuscript Accepted: 15 APR 2004
- Manuscript Received: 18 DEC 2003
- Cancer Research UK
- Royal Marsden Hospital Children's Cancer Unit Fund
- David Adams Appeal Fund
- Gobat family
Treatment of Wilms tumor has a high success rate, with some 85% of patients achieving long-term survival. However, late effects of treatment and management of relapse remain significant clinical problems. If accurate prognostic methods were available, effective risk-adapted therapies could be tailored to individual patients at diagnosis. Few molecular prognostic markers for Wilms tumor are currently defined, though previous studies have linked allele loss on 1p or 16q, genomic gain of 1q, and overexpression from 1q with an increased risk of relapse. To identify specific patterns of gene expression that are predictive of relapse, we used high-density (30 k) cDNA microarrays to analyze RNA samples from 27 favorable histology Wilms tumors taken from primary nephrectomies at the time of initial diagnosis. Thirteen of these tumors relapsed within 2 years. Genes differentially expressed between the relapsing and nonrelapsing tumor classes were identified by statistical scoring (t test). These genes encode proteins with diverse molecular functions, including transcription factors, developmental regulators, apoptotic factors, and signaling molecules. Use of a support vector machine classifier, feature selection, and test evaluation using cross-validation led to identification of a generalizable expression signature, a small subset of genes whose expression potentially can be used to predict tumor outcome in new samples. Similar methods were used to identify genes that are differentially expressed between tumors with and without genomic 1q gain. This set of discriminators was highly enriched in genes on 1q, indicating close agreement between data obtained from expression profiling with data from genomic copy number analyses. © 2004 Wiley-Liss, Inc.