Skip to main content

Table 1 Performance parameters of the two-step binary-class models

From: A machine learning model for classifying G-protein-coupled receptors as agonists or antagonists

Model

Accuracy

Sensitivity

Specificity

PPV1

NPV2

F13

MCC4

AUC5

T-model

0.726

0.699

0.744

0.652

0.783

0.675

0.439

0.787

A-model

0.758

0.780

0.744

0.647

0.849

0.707

0.510

0.823

Integrated6

0.733

0.716

0.744

0.651

0.797

0.682

0.454

0.795

  1. 1Positive predictive value
  2. 2Negative predictive value
  3. 3Harmonic means of PPV and sensitivity
  4. 4Matthews correlation coefficient
  5. 5Area under the ROC curve
  6. 6The performance values were measured with micro-average
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us