Skip to main content

Table 1 GA selected PCs and the classification model performance (ROC)

From: Selection of microbial biomarkers with genetic algorithm and principal component analysis

Data for creating PCAResultModel
_6 PCs
Model
_5 PCs
Model
_4 PCs
Model
_3 PCs
Model
_2 PCs
Model
_1 PC
AllPCs selectedPC1+, PC2–, PC7+, PC11+, PC15–, PC27–PC1+, PC2–, PC7+, PC11+, PC27–PC1+, PC2–, PC7+, PC27–PC1+, PC2–, PC7+PC1+, PC7+ (or PC2–)PC1+
AUC (CV)0.870.850.840.810.770.69
ObesityPCs selectedPC2–, PC4–, PC14+, PC16–
PC18+, PC19–
PC2–, PC4–, PC14+, PC18+
PC19–
PC2–, PC4–, PC14+, PC18+PC2–, PC14+, PC18+PC14+, PC18+PC14+
AUC (CV)0.920.920.900.870.840.80
HealthyPCs selectedPC1+,PC3+, PC5–,PC23+, PC28–,PC34+PC1+,PC3+, PC23+,PC28–
PC34+
PC1+,PC23+, PC28–,PC34+PC1+,PC23+, PC34+PC1+,PC34+PC1+
AUC (CV)0.920.900.880.870.830.72
  1. + Positive correlation coefficient in the model
  2. – Negative correlation coefficient in the model