Skip to main content

Table 3 Performance comparison on the DUD-E dataset

From: Multi-PLI: interpretable multi‐task deep learning model for unifying protein–ligand interaction datasets

Metric

Vina

AtomNet

3D-CNN

CNN/Graph

Single-task on DUD-E

Multi-task

AUC

0.716

0.895

0.868

0.950

0.973

0.971

  1. The AUC scores of Vina, 3D-CNN, AtomNet and CNN/Graph are derived from [9, 10, 13]
  2. Best values are higlhlighted in bold
Back to article page

Journal of Cheminformatics

ISSN: 1758-2946

Contact us