Skip to main content

Table 1 10-fold cross-validation results of different machine learning methods

From: Finding the molecular scaffold of nuclear receptor inhibitors through high-throughput screening based on proteochemometric modelling

Method

Accuracy

Precision

Recall

F1_score

AUC

RF

0.740

0.761

0.768

0.762

0.829

RC

0.624

0.643

0.713

0.674

–a

LR

0.453

0.490

0.000

0.000

0.452

DT

0.701

0.726

0.727

0.726

0.700

SVC

0.583

0.569

0.984

0.720

–a

  1. Results in Table 1 were calculated based on descriptor T1
  2. aThis parameters can’t be calculated in here (continuous predict values are needed to calculate AUC value)