FRI > Biolab > Supplements

Data set name: GSE967


Original data set (GSE967)
Data set for Orange
Brief description:
In the second model using the GSE967 data set we subdivided the rhabdomyosarcoma samples into embryonal rhabdomyosarcomas (eRMS) and alveolar rhabdomyosarcomas (aRMS), so that we had three diagnostic classes (EWS, eRMS and aRMS).

Platform: Affymetrix GeneChip Human Genome U95 Version [1 or 2] Set HG-U95A

Diagnostic classes:
- Ewing's sarcoma (EWS): 11 examples (47.8%)
- embryonal rhabdomyosarcoma (eRMS): 3 examples (13.0%)
- alveolar rhabdomyosarcoma (aRMS): 9 examples (39.1%)
Number of genes: 9945
Number of samples: 23
Note: From the originally measured 12625 probe sets we removed genes that were not present (P) in at least one sample
Predictive accuracy with 10-fold cross validation (classifying using the best projection with eight attributes):
Classification accuracy: 78.33%
Area under curve (AUC): 0.840
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: 99.96%
Genes:
38277_at: protein phosphatase 3 (formerly 2B), catalytic subunit, beta isoform (calcineurin A beta), PPP3CB
34877_at: Janus kinase 1 (a protein tyrosine kinase), JAK1
1487_at: estrogen-related receptor alpha, ESRRA
39325_at: left-right determination factor 2, LEFTY2
35663_at: neuronal pentraxin II, NPTX2
260_at: quinoid dihydropteridine reductase, QDPR
39084_at: enolase 3 (beta, muscle), ENO3
38730_at: myosin phosphatase-Rho interacting protein, M-RIP
Score: 99.95%
Genes:
40468_at: formin binding protein 1, FNBP1
41138_at: CD99 antigen, CD99
1487_at: estrogen-related receptor alpha, ESRRA
35663_at: neuronal pentraxin II, NPTX2
33404_at: CAP, adenylate cyclase-associated protein, 2 (yeast), CAP2
35266_at: bladder cancer associated protein, BLCAP
Score: 99.88%
Genes:
31432_g_at: Fc fragment of IgG, receptor, transporter, alpha, FCGRT
34198_at: protein tyrosine phosphatase, non-receptor type 13 (APO-1/CD95 (Fas)-associated phosphatase), PTPN13
33803_at: thrombomodulin, THBD
35321_at: tousled-like kinase 2, TLK2

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:
40570_at: forkhead box O1A (rhabdomyosarcoma), FOXO1A
33803_at: thrombomodulin, THBD
31432_g_at: Fc fragment of IgG, receptor, transporter, alpha, FCGRT
34877_at: Janus kinase 1 (a protein tyrosine kinase), JAK1
34198_at: protein tyrosine phosphatase, non-receptor type 13 (APO-1/CD95 (Fas)-associated phosphatase), PTPN13
41138_at: CD99 antigen, CD99
40795_at: titin, TTN
1487_at: estrogen-related receptor alpha, ESRRA
38650_at: insulin-like growth factor binding protein 5, IGFBP5
41215_s_at: inhibitor of DNA binding 2, dominant negative helix-loop-helix protein /// inhibitor of DNA binding 2B, dominant negative helix-loop-helix protein, ID2 /// ID2B
39721_at: ephrin-B1, EFNB1
38277_at: protein phosphatase 3 (formerly 2B), catalytic subunit, beta isoform (calcineurin A beta), PPP3CB
35321_at: tousled-like kinase 2, TLK2
37539_at: ral guanine nucleotide dissociation stimulator-like 1, RGL1
36734_at: small proline-rich protein 2D, SPRR2D
39084_at: enolase 3 (beta, muscle), ENO3
36119_at: caveolin 1, caveolae protein, 22kDa, CAV1
38730_at: myosin phosphatase-Rho interacting protein, M-RIP
35663_at: neuronal pentraxin II, NPTX2
41454_at: heme binding protein 2, HEBP2