Skip to main content

Table 2 Overview of the six transporter datasets that were used for the training of the models

From: Using Jupyter Notebooks for re-training machine learning models

Endpoint

Training

Test

 

Actives

Inactives

Actives

Inactives

Breast cancer resistance protein (BCRP)

904

786

149

38

Bile salt export pump (BSEP)

221

1100

3

7

Organic anion transporting polypeptide 1B1 (OATP1B1)

292

1675

18

3

Organic anion transporting polypeptide 1B3 (OATP1B3)

168

1818

13

4

Multidrug resistance associated protein (MRP3)

74

569

0

3

P-glycoprotein (Pgp)

1281

953

136

236

  1. The training set comprises data from LiverTox plus those extracted from ChEMBL 26 and 27, the test set contains data extracted from ChEMBL 28 and PubChem