Molecular classification of cancer: class discovery and class prediction by gene expression monitoring
- PMID: 10521349
- DOI: 10.1126/science.286.5439.531
Molecular classification of cancer: class discovery and class prediction by gene expression monitoring
Abstract
Although cancer classification has improved over the past 30 years, there has been no general approach for identifying new cancer classes (class discovery) or for assigning tumors to known classes (class prediction). Here, a generic approach to cancer classification based on gene expression monitoring by DNA microarrays is described and applied to human acute leukemias as a test case. A class discovery procedure automatically discovered the distinction between acute myeloid leukemia (AML) and acute lymphoblastic leukemia (ALL) without previous knowledge of these classes. An automatically derived class predictor was able to determine the class of new leukemia cases. The results demonstrate the feasibility of cancer classification based solely on gene expression monitoring and suggest a general strategy for discovering and predicting cancer classes for other types of cancer, independent of previous biological knowledge.
Similar articles
-
Acute leukemia: subtype discovery and prediction of outcome by gene expression profiling.Verh Dtsch Ges Pathol. 2003;87:66-71. Verh Dtsch Ges Pathol. 2003. PMID: 16888896
-
Classification of multiple cancer types by multicategory support vector machines using gene expression data.Bioinformatics. 2003 Jun 12;19(9):1132-9. doi: 10.1093/bioinformatics/btg102. Bioinformatics. 2003. PMID: 12801874
-
A gene selection algorithm based on the gene regulation probability using maximal likelihood estimation.Biotechnol Lett. 2005 Apr;27(8):597-603. doi: 10.1007/s10529-005-3253-0. Biotechnol Lett. 2005. PMID: 15973495
-
Multifaceted approach to the diagnosis and classification of acute leukemias.Clin Chem. 2000 Aug;46(8 Pt 2):1252-9. Clin Chem. 2000. PMID: 10926919 Review.
-
Acute leukemias in children with Down syndrome.Pediatr Clin North Am. 2008 Feb;55(1):53-70, x. doi: 10.1016/j.pcl.2007.11.001. Pediatr Clin North Am. 2008. PMID: 18242315 Review.
Cited by
-
Multicategory reclassification statistics for assessing improvements in diagnostic accuracy.Biostatistics. 2013 Apr;14(2):382-94. doi: 10.1093/biostatistics/kxs047. Epub 2012 Nov 28. Biostatistics. 2013. PMID: 23197381 Free PMC article.
-
A target based approach identifies genomic predictors of breast cancer patient response to chemotherapy.BMC Med Genomics. 2012 May 11;5:16. doi: 10.1186/1755-8794-5-16. BMC Med Genomics. 2012. PMID: 22578285 Free PMC article.
-
High expression of ID family and IGJ genes signature as predictor of low induction treatment response and worst survival in adult Hispanic patients with B-acute lymphoblastic leukemia.J Exp Clin Cancer Res. 2016 Apr 5;35:64. doi: 10.1186/s13046-016-0333-z. J Exp Clin Cancer Res. 2016. PMID: 27044543 Free PMC article.
-
Isolated Hoxa9 overexpression predisposes to the development of lymphoid but not myeloid leukemia.Exp Hematol. 2013 Jun;41(6):518-529.e5. doi: 10.1016/j.exphem.2013.02.006. Epub 2013 Feb 19. Exp Hematol. 2013. PMID: 23435313 Free PMC article.
-
HoxA10 protein regulates transcription of gene encoding fibroblast growth factor 2 (FGF2) in myeloid cells.J Biol Chem. 2012 May 25;287(22):18230-48. doi: 10.1074/jbc.M111.328401. Epub 2012 Apr 4. J Biol Chem. 2012. PMID: 22493287 Free PMC article.
Publication types
MeSH terms
Substances
LinkOut - more resources
Full Text Sources
Other Literature Sources
Molecular Biology Databases
Miscellaneous