TABLE 1 

Weighted-average ROC areas: performance validation of various decision tree analyses

The table summarizes the results using 10-fold cross-validation of machine-learning decision tree models for: 1) high-affinity drugs (with affinity less than 100 μM), 2) high-affinity drugs without using charge as an attribute, and 3) mid-affinity drugs (with affinity between 100 and 1000 μM).

Transporters ComparedHigh-Affinity DrugsMid-Affinity Drugs
Charge IncludedCharge ExcludedCharge Included as an Attribute
Correctly ClassifiedROC AreaCorrectly ClassifiedROC AreaCorrectly ClassifiedROC Area
OAT1/OCT186.57%0.90580.60%0.82382.50%0.874
OAT1/OCT283.33%0.93278.95%0.83582.22%0.868
OAT3/OCT186.33%0.88077.70%0.76480.00%0.880
OAT3/OCT293.28%0.93272.27%0.77470.83%0.779
OAT1/OAT369.77%0.79586.37%0.722
OCT1/OCT2a66.67%0.63945.45%0.450
  • a Note the poor results in the OCT1/OCT2 analysis are probably attributable to a small data set of six and five instances. —, results for OAT1/OAT3 and OCT1/OCT2 were inconclusive when charge was excluded. Please see text.