Data set name: GSE1577


Original data set (GSE1577)
Data set for Orange
Brief description:
Additional B-precursor acute lymphoblastic leukemia (B-ALL) bone marrow samples were added as a new diagnostic class. This model now contains samples from three diagnostic classes (T-ALL, T-LL and B-ALL).

Platform: Affymetrix GeneChip Human Genome U133 Array Set HG-U133A

Diagnostic classes:
- T-cell lymphoblastic lymphoma (T-LL): 9 examples (31.0%)
- T-cell acute lymphoblastic leukemia (T-ALL): 10 examples (34.5%)
- B-cell acute lymphoblastic leukemia (B-ALL): 10 examples (34.5%)
Number of genes: 15434
Number of samples: 29
Note: From the originally measured 22283 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: 86.67%
Area under curve (AUC): 0.946
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: 99.98%
Genes:
202112_at: von Willebrand factor, VWF
209121_x_at: nuclear receptor subfamily 2, group F, member 2, NR2F2
209120_at: nuclear receptor subfamily 2, group F, member 2, NR2F2
210788_s_at: dehydrogenase/reductase (SDR family) member 7, DHRS7
210715_s_at: serine protease inhibitor, Kunitz type, 2, SPINT2
209009_at: esterase D/formylglutathione hydrolase, ESD
203380_x_at: splicing factor, arginine/serine-rich 5, SFRS5
200092_s_at: ribosomal protein L37 /// ribosomal protein L37, RPL37
Score: 99.98%
Genes:
202112_at: von Willebrand factor, VWF
204570_at: cytochrome c oxidase subunit VIIa polypeptide 1 (muscle), COX7A1
210788_s_at: dehydrogenase/reductase (SDR family) member 7, DHRS7
210715_s_at: serine protease inhibitor, Kunitz type, 2, SPINT2
200092_s_at: ribosomal protein L37 /// ribosomal protein L37, RPL37
203380_x_at: splicing factor, arginine/serine-rich 5, SFRS5
Score: 99.98%
Genes:
217757_at: alpha-2-macroglobulin, A2M
209120_at: nuclear receptor subfamily 2, group F, member 2, NR2F2
202207_at: ADP-ribosylation factor-like 7, ARL7
203380_x_at: splicing factor, arginine/serine-rich 5, SFRS5

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:
203380_x_at: splicing factor, arginine/serine-rich 5, SFRS5
209120_at: nuclear receptor subfamily 2, group F, member 2, NR2F2
202112_at: von Willebrand factor, VWF
217717_s_at: tyrosine 3-monooxygenase/tryptophan 5-monooxygenase activation protein, beta polypeptide, YWHAB
209121_x_at: nuclear receptor subfamily 2, group F, member 2, NR2F2
209290_s_at: nuclear factor I/B, NFIB
217757_at: alpha-2-macroglobulin, A2M
201339_s_at: sterol carrier protein 2, SCP2
202131_s_at: RIO kinase 3 (yeast) /// RIO kinase 3 (yeast), RIOK3
217627_at: zinc finger protein 573, ZNF573
203492_x_at: translokin, PIG8
210715_s_at: serine protease inhibitor, Kunitz type, 2, SPINT2
204570_at: cytochrome c oxidase subunit VIIa polypeptide 1 (muscle), COX7A1
201226_at: NADH dehydrogenase (ubiquinone) 1 beta subcomplex, 8, 19kDa, NDUFB8
202207_at: ADP-ribosylation factor-like 7, ARL7
210788_s_at: dehydrogenase/reductase (SDR family) member 7, DHRS7
200092_s_at: ribosomal protein L37 /// ribosomal protein L37, RPL37
218204_s_at: FYVE and coiled-coil domain containing 1, FYCO1
206702_at: TEK tyrosine kinase, endothelial (venous malformations, multiple cutaneous and mucosal), TEK
202713_s_at: KIAA0391, KIAA0391