Data set name: glioblastoma


Original data set (Nutt et al.)
Data set for Orange
Brief description:
Malignant gliomas and oligodendrogliomas can be histologically divided into 2 subgroups, the classic and nonclassic type. Tumors in the nonclassic subgroup are diagnostically especially challenging, generating considerable interobserver variability and limited diagnostic reproducibility when the classification is done by histological features. The model shown distinguishes between 4 diagnostic classes (classic and nonclassic gliomas and oligodendrogliomas) on the basis of DNA gene expression signatures.

Platform: Affymetrix Human Genome U95Av2 Array

Diagnostic classes:
- classic glioblastoma (CG): 14 examples (28.0%)
- classic oligodendroglioma (CO): 7 examples (14.0%)
- nonclassic glioblastoma (NG): 14 examples (28.0%)
- nonclassic oligodendroglioma (NO): 15 examples (30.0%)
Number of genes: 12625
Number of samples: 50
Predictive accuracy with 10-fold cross validation (classifying using the best projection with eight attributes):
Classification accuracy: 70.00%
Area under curve (AUC): 0.891
Following are the three best-ranked visualization with eight, six and four attributes in respect to the visualization score, that is, visualizations where examples from different diagnostic classes are best separated:

Score: 95.03%
Genes:
630_at: dCMP deaminase, DCTD
446_at: "casein kinase 1, gamma 2", CSNK1G2
38609_at: "sarcoglycan, alpha (50kDa dystrophin-associated glycoprotein)", SGCA
37807_at: "glucokinase (hexokinase 4, maturity onset diabetes of the young 2)", GCK
AFFX-BioC-3_st: ---, ---
31569_at: "solute carrier family 1 (glutamate transporter), member 7", SLC1A7
41269_r_at: apoptosis inhibitor 5, API5
36164_at: "pyruvate dehydrogenase complex, component X", PDHX
Score: 90.44%
Genes:
35195_at: RNA terminal phosphate cyclase domain 1, RTCD1
1367_f_at: ubiquitin C, UBC
347_s_at: ribosomal protein S23, RPS23
36164_at: "pyruvate dehydrogenase complex, component X", PDHX
1961_f_at: nitric oxide synthase 3 (endothelial cell), NOS3
38609_at: "sarcoglycan, alpha (50kDa dystrophin-associated glycoprotein)", SGCA
Score: 86.32%
Genes:
1367_f_at: ubiquitin C, UBC
38609_at: "sarcoglycan, alpha (50kDa dystrophin-associated glycoprotein)", SGCA
33468_at: desmoglein 2, DSG2
36164_at: "pyruvate dehydrogenase complex, component X", PDHX

Attribute ranking

Following is the histogram of genes showing how often are they present in one of the top 100 radviz visualizations with 8 attributes.

Genes:
38609_at: "sarcoglycan, alpha (50kDa dystrophin-associated glycoprotein)", SGCA
36164_at: "pyruvate dehydrogenase complex, component X", PDHX
446_at: "casein kinase 1, gamma 2", CSNK1G2
33619_at: ribosomal protein S13, RPS13
493_at: "casein kinase 1, delta", CSNK1D
40055_s_at: matrix metallopeptidase 19, MMP19
33468_at: desmoglein 2, DSG2
37807_at: "glucokinase (hexokinase 4, maturity onset diabetes of the young 2)", GCK
347_s_at: ribosomal protein S23, RPS23
1961_f_at: nitric oxide synthase 3 (endothelial cell), NOS3
AFFX-BioC-3_st: ---, ---
35567_at: Chromosome 20 open reading frame 194, C20orf194
35905_s_at: glyceraldehyde-3-phosphate dehydrogenase, GAPDH
41846_at: Cone-rod homeobox, CRX
41269_r_at: apoptosis inhibitor 5, API5
35276_at: claudin 4, CLDN4
32690_s_at: prostaglandin E receptor 3 (subtype EP3), PTGER3
AFFX-HUMGAPDH/M33197_3_at: glyceraldehyde-3-phosphate dehydrogenase, GAPDH
38421_at: taxilin alpha, TXLNA
37613_at: parvalbumin, PVALB