Molecular classification of cancer: class discovery and class prediction by gene expression monitoring.

@article{Golub1999MolecularCO,
  title={Molecular classification of cancer: class discovery and class prediction by gene expression monitoring.},
  author={Todd R. Golub and Donna K. Slonim and Pablo Tamayo and Christine Huard and Michelle Gaasenbeek and Jill P. Mesirov and Hilary A. Coller and Mignon L. Loh and James R. Downing and Michael A. Caligiuri and Clara D. Bloomfield and Eric S. Lander},
  journal={Science},
  year={1999},
  volume={286 5439},
  pages={
          531-7
        }
}
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… Expand
Class prediction and discovery using gene expression data
TLDR
A method for performing class prediction is described and illustrated by correctly classifying bone marrow and blood samples from acute leukemia patients, and it is demonstrated how this technique could have discovered the key distinctions among leukemias if they were not already known. Expand
ALL/AML Cancer Classification by Gene Expression Data Using SVM and CSVM Approach
TLDR
This paper is a report of the work on the classification (prediction) part of this problem following Golub et al. Expand
Class discovery and classification of tumor samples using mixture modeling of gene expression data - a unified approach
TLDR
This paper offers a unified approach to class discovery and classification, which it is believed is more appropriate, and has greater applicability, in practical situations. Expand
Making genome expression data meaningful: prediction and discovery of classes of cancer through a connectionist learning approach
  • F. Azuaje
  • Biology, Computer Science
  • Proceedings IEEE International Symposium on Bio-Informatics and Biomedical Engineering
  • 2000
TLDR
A new approach to genome expression pattern interpretation is described and applied to the recognition of B-cell malignancies as a test set and discovers the distinction between patients with molecularly distinct forms of DLBCL without previous knowledge of those subtypes. Expand
Selecting Informative Genes for Cancer Classification Using Gene Expression Data
TLDR
Although effectiveness of such an approach was already demonstrated, the proposed information processing methods were rather heuristic (Golub, 1999; Tsunoda, 2000), so further studies should be done for making more accurate classification. Expand
Comparison of Discrimination Methods for the Classification of Tumors Using Gene Expression Data
A reliable and precise classification of tumors is essential for successful diagnosis and treatment of cancer. cDNA microarrays and high-density oligonucleotide chips are novel biotechnologiesExpand
Cancer classification from serial analysis of gene expression with event models
TLDR
Experiments results on several SAGE datasets show that event models are better than standard Naïve Bayes in general, and Normalized Information Gain (NIG), an extension of Information Gain, is proposed for gene selection. Expand
Multi‐class cancer subtype classification based on gene expression signatures with reliability analysis
TLDR
A new method of gene selection with reliability analysis is devised, and it is demonstrated that this method can identify a more compact set of genes than other methods for constructing a classifier with optimum predictive performance for both small round blue cell tumors and leukemia. Expand
Class discovery analysis of the lung cancer gene expression data.
  • A. Ptitsyn
  • Biology, Medicine
  • DNA and cell biology
  • 2004
TLDR
This work attempts to build a molecular classification of lung cancer subtypes based on the public data available from a few independent sources and reanalyzed with a new cluster analysis algorithm to preserve the high dimensionality of data and produce the cluster structure without preliminary selection of significant genes. Expand
Classification and Prediction of Disease Classes using Gene Microarray Data
TLDR
The objective of this paper is to present a tool designed exclusively to predict and classify leukemia into its types based on decision rules, which is found to work with an accuracy of 94%. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 69 REFERENCES
Tissue microarrays for high-throughput molecular profiling of tumor specimens
TLDR
An array-based high-throughput technique that facilitates gene expression and copy number surveys of very large numbers of tumors is developed and the detection of six gene amplifications as well as p53 and estrogen receptor expression in breast cancer demonstrates the power of this technique for defining new subgroups of tumors. Expand
Expression profiling in cancer using cDNA microarrays
TLDR
The principles of the microarray technology as applied to cancer research are described, the literature on its use so far is summarized, and speculate on the future application of this powerful technique are speculated on. Expand
Interpreting patterns of gene expression with self-organizing maps: methods and application to hematopoietic differentiation.
  • P. Tamayo, D. Slonim, +5 authors T. Golub
  • Biology, Medicine
  • Proceedings of the National Academy of Sciences of the United States of America
  • 1999
TLDR
The application of self-organizing maps, a type of mathematical cluster analysis that is particularly well suited for recognizing and classifying features in complex, multidimensional data, is described. Expand
Use of a cDNA microarray to analyse gene expression patterns in human cancer
TLDR
Previously unrecognized alterations in the expression of specific genes provide leads for further investigation of the genetic basis of the tumorigenic phenotype of these cells. Expand
Gene expression profiling of alveolar rhabdomyosarcoma with cDNA microarrays.
TLDR
The use of cDNA microarrays containing 1238 cDNAs to investigate the gene expression profile of a group of seven alveolar rhabdomyosarcoma (ARMS) cell lines determined that ARMS cells show a consistent pattern of gene expression, which allows the cells to be clustered together. Expand
The Ewing family of tumors--a subgroup of small-round-cell tumors defined by specific chimeric transcripts.
TLDR
A subgroup of small-round-cell tumors identified as belonging to the Ewing family of tumors can be defined according to a specific molecular genetic lesion that is detectable by a rapid, reliable, and efficient method. Expand
Expression of myeloid differentiation antigens in acute nonlymphocytic leukemia: increased concentration of CD33 antigen predicts poor outcome--a report from the Childrens Cancer Study Group.
TLDR
This study indicates that patients whose ANll blasts displayed the CD33 antigen in an amount associated with immature myeloid cells experienced a worse outcome than patients with ANLL blasts that expressed a phenotype associated with more mature cells. Expand
TEL/AML-1 dimerizes and is associated with a favorable outcome in childhood acute lymphoblastic leukemia.
TLDR
Co-immunoprecipitation experiments demonstrated that TEL/AML-1 formed homodimers in vitro, and heterodimerized with the normal TEL protein when the two proteins were expressed together. Expand
mb-1: A New Marker for B-Lineage Lymphoblastic Leukemia
TLDR
Results indicate that mb-1 is a sensitive and specific reagent for B-lineage blasts that will aid in the classification of B-cell precursor ALL and in the identification of biphenotypic leukemia presenting as AML. Expand
Leukemia-associated antigens in ALL.
TLDR
Using only CALLA and antisera specific for Ia-like and T-cell antigens, the authors can now distinguish most cases of ALL from AML and other hematologic malignancies. Expand
...
1
2
3
4
5
...