Skip to main content

Table 3 Results of the DeepTGIN model and other compared models on the PDBbind2016 test set

From: DeepTGIN: a novel hybrid multimodal approach using transformers and graph isomorphism networks for protein-ligand binding affinity prediction

Models

R(\(\uparrow\))

RMSE(\(\downarrow\))

MAE(\(\downarrow\))

SD(\(\downarrow\))

CI(\(\uparrow\))

GraphDTA

0.706

1.543

1.183

1.539

0.755

DeepGLSTM

0.722

1.516

1.147

1.512

0.768

DeepDTAF

0.758

1.438

1.148

1.416

0.778

TEFDTA

0.772

1.390

1.065

1.379

0.782

DeepDTA

0.782

1.351

1.038

1.352

0.787

IGN

0.786

1.342

1.049

1.341

0.791

GIGN

0.788

1.351

1.045

1.336

0.792

CAPLA

0.799

1.324

1.063

1.307

0.797

DeepTGIN

0.834

1.203

0.949

1.197

0.823

  1. \(\uparrow\) indicates that larger values indicate better performance, while \(\downarrow\) indicates that smaller values indicate better performance. The best results are shown in bold
Back to article page

Journal of Cheminformatics

ISSN: 1758-2946

Contact us