In this work, we present graph-convolutional neural networks for the prediction of binding constants of protein-ligand complexes. We derived the model using multi task learning, where the target variables are the dissociation constant ( ), inhibition constant ( ), and half maximal inhibitory concentration (IC). Being rigorously trained on the PDBbind dataset, the model achieves the Pearson correlation coefficient of 0.87 and the RMSE value of 1.05 in pK units, outperforming recently developed 3D convolutional neural network model .
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7081425 | PMC |
| http://dx.doi.org/10.1021/acsomega.9b04162 | DOI Listing |
Publication Analysis
Top Keywords
protein-ligand complexes
8
graphdelta mpnn
4
mpnn scoring
4
scoring function
4
function affinity
4
affinity prediction
4
prediction protein-ligand
4
complexes work
4
work graph-convolutional
4
graph-convolutional neural
4
Similar Publications
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!