Maqola

Molecular Classification of Cancer: Class Discovery and Class Prediction by Gene Expression Monitoring

Todd R. GolubDana-Farber Cancer Institute and Harvard Medical School, Boston, MA 02115, USADonna K. SlonimWhitehead Institute/Massachusetts Institute of Technology Center for Genome Research, Cambridge, MA 02139, USAPablo TamayoWhitehead Institute/Massachusetts Institute of Technology Center for Genome Research, Cambridge, MA 02139, USAC. HuardWhitehead Institute/Massachusetts Institute of Technology Center for Genome Research, Cambridge, MA 02139, USAMichelle GaasenbeekWhitehead Institute/Massachusetts Institute of Technology Center for Genome Research, Cambridge, MA 02139, USAJill P. MesirovWhitehead Institute/Massachusetts Institute of Technology Center for Genome Research, Cambridge, MA 02139, USAHilary A. CollerWhitehead Institute/Massachusetts Institute of Technology Center for Genome Research, Cambridge, MA 02139, USAMignon L. LohDana-Farber Cancer Institute and Harvard Medical School, Boston, MA 02115, USAJames R. DowningSt. Jude Children's Research Hospital, Memphis, TN 38105, USAM. A. CaligiuriComprehensive Cancer Center and Cancer and Leukemia Group B, Ohio State University, Columbus, OH 43210, USAC. D. BloomfieldComprehensive Cancer Center and Cancer and Leukemia Group B, Ohio State University, Columbus, OH 43210, USAEric S. LanderDepartment of Biology, Massachusetts Institute of Technology, Cambridge, MA 02142, USA

1999en

ABI

Annotatsiya

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.

Hali tarjima qilinmagan

Identifikatorlar

DOI: 10.1126/science.286.5439.531

Iqtiboslar va manbalar

2 ta iqtibos0 ta foydalanilgan manba

Koʻrsatkichlar — AkademScholar