Skip to main content

Table 1 The labeled compound toxicity datasets for 12 toxicological endpoints and the unlabeled dataset

From: Chemical toxicity prediction based on semi-supervised learning and graph convolutional neural network

Endpoint

Compounds(labeled)

Training set

Validation set

Test set

NR-AhR

6549

5239

655

655

NR-AR-LBD

6758

5406

676

676

NR-AR

7265

5812

726

727

NR-Aromatase

5821

4656

582

583

NR-ER-LBD

6955

5564

695

696

NR-ER

6193

4954

619

620

NR-PPAR-gamma

6450

5160

645

645

SR-ARE

5832

4665

583

584

SR-ATAD5

7072

5657

707

708

SR-HSE

6467

5173

647

647

SR-MMP

5810

4648

581

581

SR-p53

6774

5419

677

678

Unlabeled data

50527

–

–

–