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):
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