Data set name: prostate


Original data set (Singh et al.)
Data set for Orange
Brief description:
Gene expression measurements for samples of prostate tumors and adjacent prostate tissue not containing tumor were used to build this classification model.

Platform: Affymetrix Human Genome U95Av2 Array

Diagnostic classes:
- normal tissue (normal): 50 examples (49.0%)
- prostate tumor (tumor): 52 examples (51.0%)
Number of genes: 12533
Number of samples: 102
Predictive accuracy with 10-fold cross validation (classifying using the best projection with eight attributes):
Classification accuracy: 85.36%
Area under curve (AUC): 0.914
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: 95.07%
Genes:
38028_at: LIM domain only 3 (rhombotin-like 2), LMO3
40282_s_at: D component of complement (adipsin), DF
41504_s_at: v-maf musculoaponeurotic fibrosarcoma oncogene homolog (avian), MAF
1767_s_at: "transforming growth factor, beta 3", TGFB3
31527_at: ribosomal protein S2, RPS2
39756_g_at: X-box binding protein 1, XBP1
37639_at: "hepsin (transmembrane protease, serine 1)", HPN
33121_g_at: regulator of G-protein signalling 10, RGS10
Score: 93.49%
Genes:
33137_at: latent transforming growth factor beta binding protein 4, LTBP4
41504_s_at: v-maf musculoaponeurotic fibrosarcoma oncogene homolog (avian), MAF
38028_at: LIM domain only 3 (rhombotin-like 2), LMO3
37720_at: heat shock 60kDa protein 1 (chaperonin), HSPD1
37639_at: "hepsin (transmembrane protease, serine 1)", HPN
40436_g_at: "solute carrier family 25 (mitochondrial carrier; adenine nucleotide translocator), member 6", SLC25A6
Score: 92.20%
Genes:
38087_s_at: "S100 calcium binding protein A4 (calcium protein, calvasculin, metastasin, murine placental homolog)", S100A4
41504_s_at: v-maf musculoaponeurotic fibrosarcoma oncogene homolog (avian), MAF
37639_at: "hepsin (transmembrane protease, serine 1)", HPN
40435_at: "solute carrier family 25 (mitochondrial carrier; adenine nucleotide translocator), member 6", SLC25A6

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:
37639_at: "hepsin (transmembrane protease, serine 1)", HPN
32598_at: NEL-like 2 (chicken), NELL2
40282_s_at: D component of complement (adipsin), DF
38028_at: LIM domain only 3 (rhombotin-like 2), LMO3
38406_f_at: prostaglandin D2 synthase 21kDa (brain), PTGDS
37720_at: heat shock 60kDa protein 1 (chaperonin), HSPD1
39756_g_at: X-box binding protein 1, XBP1
556_s_at: glutathione S-transferase M1 /// glutathione S-transferase M2 (muscle) /// glutathione S-transferase M4, GSTM1 /// GSTM2 /// GSTM4
37366_at: PDZ and LIM domain 5, PDLIM5
1767_s_at: "transforming growth factor, beta 3", TGFB3
41468_at: T cell receptor gamma constant 2 /// T cell receptor gamma variable 9 /// similar to T-cell receptor gamma chain C region PT-gamma-1/2 /// similar to T-cell receptor gamma chain V region PT-gamma-1/2 precursor /// TCR gamma alternate reading frame protein, TRGC2 /// TRGV9 /// LOC442532 /// LOC442670 /// TARP
40436_g_at: "solute carrier family 25 (mitochondrial carrier; adenine nucleotide translocator), member 6", SLC25A6
41288_at: "calmodulin 1 (phosphorylase kinase, delta)", CALM1
38087_s_at: "S100 calcium binding protein A4 (calcium protein, calvasculin, metastasin, murine placental homolog)", S100A4
39939_at: "collagen, type IV, alpha 6", COL4A6
38634_at: "retinol binding protein 1, cellular", RBP1
41504_s_at: v-maf musculoaponeurotic fibrosarcoma oncogene homolog (avian), MAF
36666_at: "procollagen-proline, 2-oxoglutarate 4-dioxygenase (proline 4-hydroxylase), beta polypeptide (protein disulfide isomerase-associated 1)", P4HB
575_s_at: tumor-associated calcium signal transducer 1, TACSTD1
914_g_at: v-ets erythroblastosis virus E26 oncogene like (avian), ERG