Skip to main content
Fig. 1 | Journal of Cheminformatics

Fig. 1

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

Fig. 1

Components of the PDBbind2020 dataset. The PDBbind2020 dataset is divided into a general set, a refined set, the PDBbind 2016 core set, and the PDBbind 2013 core set. The training set and the validation set are derived from the general set and refined set. The PDBbind 2016 core set and the PDBbind 2013 core set are used as the test sets. Among them, there are 107 duplicated complexes between v2016 and v2013

Back to article page