Gene Expression Model Selector

Latest version of GEMS:

A note on using GEMS for analysis of extremely small sample datasets

Any questions or problems? Email us: alexander.statnikov@vanderbilt.edu

Copyright, © 2003-2005, Alexander Statnikov, Constantin F. Aliferis, Ioannis Tsamardinos, Discovery Systems Laboratory, Department of Biomedical Informatics, Vanderbilt University, Nashville, TN, USA
Publications

  • A. Statnikov, I. Tsamardinos, Y. Dosbayev, C.F. Aliferis, "GEMS: A System for Automated Cancer Diagnosis and Biomarker Discovery from Microarray Gene Expression Data", International Journal of Medical Informatics, 2005 Aug;74(7-8):491-503. [Pubmed]

  • A. Statnikov, C.F. Aliferis, I. Tsamardinos, D. Hardin, S. Levy. " A Comprehensive Evaluation of Multicategory Classification Methods for Microarray Gene Expression Cancer Diagnosis", Bioinformatics, 2005 Mar 1;21(5):631-43 [Pubmed] [Appendix]

  • A. Statnikov, C.F. Aliferis, I. Tsamardinos. "Methods for Multi-Category Cancer Diagnosis from Gene Expression Data: A Comprehensive Evaluation to Inform Decision Support System Development", Medinfo, 2004;2004:813-7 [Article] [Appendix]

  • Datasets used for evaluation

    Dataset name Diagnostic Task PubMed link File
    11_Tumors 11 various human tumor types [PubMed] 11_Tumors.mat (8,520kb)
    11_Tumors.txt (1kb)
    For use with GEMS: 11_Tumors_GEMS.txt (?kb)
    14_Tumors 14 various human tumor types and 12 normal tissue types [PubMed] 14_Tumors.mat (36,118kb)
    14_Tumors.txt (1kb)
    For use with GEMS: 14_Tumors_GEMS.txt (?kb)
    9_Tumors 9 various human tumor types [PubMed] 9_Tumors.mat (672kb)
    9_Tumors.txt (1kb)
    For use with GEMS: 9_Tumors_GEMS.txt (?kb)
    Brain_Tumor1 5 human brain tumor types [PubMed] Brain_Tumor1.mat (2,082kb)
    Brain_Tumor1.txt (1kb)
    For use with GEMS: Brain_Tumor1_GEMS.txt (?kb)
    Brain_Tumor2 4 malignant glioma types [PubMed] Brain_Tumor2.mat (4,051kb)
    Brain_Tumor2.txt (1kb)
    For use with GEMS: Brain_Tumor2_GEMS.txt (?kb)
    Leukemia1 Acute myelogenous leukemia (AML), acute lympboblastic leukemia (ALL) B-cell, and ALL T-cell [PubMed] Leukemia1.mat (1,499kb)
    Leukemia1.txt (1kb)
    For use with GEMS: Leukemia1_GEMS.txt (?kb)
    Leukemia2 AML, ALL, and mixed-lineage leukemia (MLL) [PubMed] Leukemia2.mat (6,315kb)
    Leukemia2.txt (1kb)
    For use with GEMS: Leukemia2_GEMS.txt (?kb)
    Lung_Cancer 4 lung cancer types and normal tissues [PubMed] Lung_Cancer.mat (19,985kb)
    Lung_Cancer.txt (1kb)
    For use with GEMS: Lung_Cancer_GEMS.txt (?kb)
    SRBCT Small, round blue cell tumors (SRBCT) of childhood [PubMed] SRBCT.mat (1,498kb)
    SRBCT.txt (1kb)
    For use with GEMS: SRBCT_GEMS.txt (?kb)
    Prostate_Tumor Prostate tumor and normal tissues [PubMed] Prostate_Tumor.mat (8,376kb)
    Prostate_Tumor.txt (1kb)
    For use with GEMS: Prostate_Tumor_GEMS.txt (?kb)
    DLBCL Diffuse large b-cell lymphomas (DLBCL) and follicular lymphomas [PubMed] DLBCL.mat (1,646kb)
    DLBCL.txt (1kb)
    For use with GEMS: DLBCL_Tumor_GEMS.txt (?kb)

    Datasets are distributed as Matlab data files (.mat). Each file contains a matrix with columns corresponding to diagosis (1st column) and genes, and rows corresponding to samples. The encoding of diagnosis (1st column) is provided in .txt file.