Skip to main content
Fig. 6 | Journal of Cheminformatics

Fig. 6

From: Integrating concept of pharmacophore with graph neural networks for chemical property prediction and interpretation

Fig. 6

Explanation of the importance of pharmacophore or substructure. a The chemical structure of the pha-739358, an AURKA inhibitor. b The importance of pharmacophore learned by RG-MPNN. We can see that Y (aliphatic and positively ionizable), Co (acyclic and donor), Ti (aromatic and donor), Ni (acyclic and acceptor) and Sc (aromatic and no feature) play important roles in AURKA bioactivity. c Ligand-receptor interactions in the crystal complex (PDB ID: 2J50). Of note, Nitrogen atoms within Co and Ti form two important hydrogen bonds with receptor, which is consistent with the analysis of pharmacophore importance

Back to article page