FRI > Biolab > Supplements

Data set name: GSE2379


Original data set (GSE2379)
Data set for Orange
Brief description:
The prognosis of hypopharyngeal cancers is influenced by many known factors (TNM staging and grading of differentiation). However, these factors are not sufficient to predict the outcome, so new markers are needed that would be able to stage patients in prognostic groups. This is the problem addressed in our second classification model of this data set. Namely, we are trying to distinguish between normal tissue (N), early tumors (E_T) and late tumors that are additionally subdivided into three subtypes according to clinical behavior 3 years or more after surgery: patients who did not (NM) or did (M) develop metastases, or had local recurrence (LR) within 3 years.

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

Diagnostic classes:
- late tumor without metastases (T_NM): 11 examples (28.9%)
- normal tissue (N): 4 examples (10.5%)
- early tumor (T_E): 4 examples (10.5%)
- late tumor with local recurrence (T_LR): 4 examples (10.5%)
- late tumor with metastases (T_M): 15 examples (39.5%)
Number of genes: 9021
Number of samples: 38
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: 38.33%
Area under curve (AUC): 0.602
Following are 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: 85.12%
Genes:
1364_at: protein tyrosine phosphatase, receptor-type, Z polypeptide 1, PTPRZ1
37632_s_at: zuotin related factor 1, ZRF1
36569_at: C-type lectin domain family 3, member B, CLEC3B
37762_at: epithelial membrane protein 1, EMP1
218_at: IK cytokine, down-regulator of HLA II, IK
32849_at: SMC1 structural maintenance of chromosomes 1-like 1 (yeast), SMC1L1
32378_at: pyruvate kinase, muscle, PKM2
38922_at: tyrosine kinase, non-receptor, 1, TNK1
Score: 96.39%
Genes:
35463_at: homeo box (expressed in ES cells) 1, HESX1
160031_at: cadherin 3, type 1, P-cadherin (placental), CDH3
38922_at: tyrosine kinase, non-receptor, 1, TNK1
948_s_at: peptidylprolyl isomerase D (cyclophilin D), PPID
37600_at: extracellular matrix protein 1, ECM1
36345_g_at: coagulation factor II (thrombin) receptor-like 1, F2RL1
Score: 64.29%
Genes:
37632_s_at: zuotin related factor 1, ZRF1
36890_at: periplakin, PPL
37171_at: kinesin family member 23, KIF23
218_at: IK cytokine, down-regulator of HLA II, IK

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:
38922_at: tyrosine kinase, non-receptor, 1, TNK1
38302_at: zinc finger protein 202, ZNF202
37632_s_at: zuotin related factor 1, ZRF1
218_at: IK cytokine, down-regulator of HLA II, IK
37762_at: epithelial membrane protein 1, EMP1
37985_at: lamin B1, LMNB1
36290_s_at: fucosyltransferase 3 (galactoside 3(4)-L-fucosyltransferase, Lewis blood group included) /// fucosyltransferase 5 (alpha (1,3) fucosyltransferase) /// fucosyltransferase 6 (alpha (1,3) fucosyltransferase), FUT3 /// FUT5 /// FUT6
36890_at: periplakin, PPL
37939_at: apolipoprotein B mRNA editing enzyme, catalytic polypeptide-like 3C, APOBEC3C
35749_at: transcriptional adaptor 3 (NGG1 homolog, yeast)-like, TADA3L
36345_g_at: coagulation factor II (thrombin) receptor-like 1, F2RL1
36569_at: C-type lectin domain family 3, member B, CLEC3B
910_at: thymidine kinase 1, soluble, TK1
32378_at: pyruvate kinase, muscle, PKM2
1364_at: protein tyrosine phosphatase, receptor-type, Z polypeptide 1, PTPRZ1
32520_at: thyroid hormone receptor, alpha (erythroblastic leukemia viral (v-erb-a) oncogene homolog, avian) /// nuclear receptor subfamily 1, group D, member 1, THRA /// NR1D1
38190_r_at: DEP domain containing 5, DEPDC5
32868_at: transglutaminase 3 (E polypeptide, protein-glutamine-gamma-glutamyltransferase), TGM3
1772_s_at: farnesyltransferase, CAAX box, alpha, FNTA
37171_at: kinesin family member 23, KIF23