Skip to main content

Table 1 Summary of the datasets used throughout the experiments

From: Designing optimized drug candidates with Generative Adversarial Network

Dataset

# Compounds

Labeled

Observations

ChEMBL [32]

1,178,946

No

 

Zinc Biogenic [15]

108,283

No

 

ADORA2A

4729

Yes

CHEMBL251

KOR

5262

Yes

CHEMBL237

JAK2

1697

Yes

CHEMBL2971

USP7 [33]

1109

Yes

CHEMBL2157850

bbbp [27]

1340

Yes

 

composed_dataset_1

100,000

No

 

composed_dataset_2

500,000

No