GraphDelta : MPNN scoring function for the affinity prediction of protein-ligand complexes
Karlov, Dmitry S. and Sosnin, Sergey and Fedorov, Maxim V. and Popov, Petr (2020) GraphDelta : MPNN scoring function for the affinity prediction of protein-ligand complexes. ACS Omega, 5 (10). pp. 5150-5159. ISSN 2470-1343 (https://doi.org/10.1021/acsomega.9b04162)
Preview |
Text.
Filename: Karlov_etal_ACSO_2020_graphDelta_MPNN_scoring_function_for_the_affinity_prediction.pdf
Final Published Version License: Download (2MB)| Preview |
Abstract
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 (Kd), inhibition constant (Ki), and half maximal inhibitory concentration (IC50). 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 Kdeep. ©
-
-
Item type: Article ID code: 71993 Dates: DateEvent17 March 2020Published9 March 2020Published Online21 February 2020AcceptedSubjects: Science > Physics
Science > ChemistryDepartment: Faculty of Science > Physics Depositing user: Pure Administrator Date deposited: 07 Apr 2020 10:41 Last modified: 11 Nov 2024 12:38 Related URLs: URI: https://strathprints.strath.ac.uk/id/eprint/71993