Skip to main content

Table 1 Balanced accuracies of prediction obtained in various phenotypes using the metagene classifier (ROC) and linear SVM (SVM).

From: Robust assignment of cancer subtypes from expression data using a uni-variate gene expression average as classifier

Phenotype/
Method
Training1 Validation Validation Training Validation Validation Training Validation Validation Mean
ER 2 (BC) vandeVijver WangY Sotiriou WangY vandeVijver Sotiriou Sotiriou vandeVijver WangY  
ROC 0.95 0.89 0.74 0.89 0.94 0.77 0.77 0.90 0.88 0.85
SVM 0.94 0.82 0.71 0.82 0.95 0.73 0.69 0.95 0.82 0.83
Grade 3 (BC) vandeVijver Sotiriou   Sotiriou vandeVijver      
ROC 0.79 0.85   0.84 0.82      0.84
SVM 0.72 0.78   0.84 0.78      0.78
Size 4 (BC) vandeVijver Sotiriou   Sotiriou vandeVijver      
ROC 0.63 0.65   0.70 0.60      0.63
SVM 0.57 0.51   0.61 0.48      0.49
MYCN 5 (NB) WangQ JanoueixL Attiyeh JanoueixL WangQ Attiyeh Attiyeh WangQ JanoueixL  
ROC 0.94 0.91 0.82 0.87 0.89 0.79 0.81 0.95 0.89 0.88
SVM 0.98 0.83 0.75 0.88 0.97 0.67 0.85 0.98 0.87 0.84
Stage 6 (NB) WangQ JanoueixL Attiyeh JanoueixL WangQ Attiyeh Attiyeh WangQ JanoueixL  
ROC 0.74 0.58 0.82 0.66 0.65 0.70 0.69 0.62 0.48 0.64
SVM 0.79 0.58 0.74 0.61 0.73 0.61 0.60 0.72 0.54 0.65
AD/SQ 7 (LC) Angulo Takeuchi   Takeuchi Angulo      
ROC 0.93 0.96   0.95 0.96      0.96
SVM 0.89 0.91   0.93 0.84      0.88
Grade 8 (LC) Angulo Takeuchi   Takeuchi Angulo      
ROC 0.67 0.69   0.69 0.68      0.68
SVM 0.63 0.64   0.63 0.59      0.61
  1. 1 Accuracies given in italics indicates accuracies obtained in the training set using LOOCV
  2. 2 ER+ vs. ER-
  3. 3 grade 1 vs. grade 3
  4. 4 tumors < = 2 cm vs. tumors > 2 cm
  5. 5 MYCN amplification positive vs. MYCN amplification negative
  6. 6 stage 1 and 2 vs. stage 3 and 4
  7. 7 adenocarcinoma vs. squamous cell carcinoma
  8. 8 grade 1 vs. grade 2 and 3
  9. Abbreviations; BC = Breast Cancer, NB = Neuroblastoma, LC = Lung Cancer