• Partnerships
• Contribute
• Careers
• Contact Us

• What is Broad
  • Our Approach
  • Areas of Focus
  • History & Leadership
  • Who is Broad
  • Partner Institutions
  • Artist-in-Residence
• News and Publications
  • News & Multimedia
  • Scientific Publications
  • For Journalists
  • BroadMinded Blog
• For the Scientific Community
  • Science
  • Data
  • Software

Cancer Program Publication

Molecular Classification of Cancer: Class Discovery and Class Prediction by Gene Expression
Project	Leukemia
Additional Projects/ Categories	Bioinformatics & Computational Biology
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.
Authors	T.R. Golub, D.K. Slonim, P. Tamayo, C. Huard, M. Gaasenbeek, J.P. Mesirov, H. Coller, M. Loh, J.R. Downing, M.A. Caligiuri, C.D. Bloomfield, and E.S. Lander
Publication Date	10/15/1999
Contact emails	golub@genome.wi.mit.edu lander@genome.wi.mit.edu
Publication URL	http://www.sciencemag.org/cgi/content/abstract/286/5439/531
Citation	Science 286:531-537. (1999).
Keywords	Leukemia, ALL, AML, gene expression, prediction, class discovery, gene marker, molecular classification, supervised, unsupervised.
Supplemental Information
Files Description File Paper (PDF) Golub_et_al_1999.pdf Files description Files_descriptions.txt Experimental protocol protocol.html Rescaling factors table_ALL_AML_rfactors.txt Samples table (Word) table_ALL_AML_samples.rtf Samples table (text) table_ALL_AML_samples.txt Train dataset (Excel) data_set_ALL_AML_train.tsv Train dataset (text) data_set_ALL_AML_train.txt Test datset (Excel) data_set_ALL_AML_independent.tsv Test dataset (text) data_set_ALL_AML_independent.txt Prediction results (Word) table_ALL_AML_predic.rtf Prediction results (text) table_ALL_AML_predic.txt Original and supplemental figures (Powerpoint) Figures_original_plus_suppl.ppt Train dataset in WI format ALL_vs_AML_train_set_38_sorted.res Train dataset class vector in WI format ALL_vs_AML_train_set_38_sorted.cls Test dataset in WI format Leuk_ALL_AML.test.res Test dataset class vector in WI format Leuk_ALL_AML.test.cls