EurekaMag
+ Most Popular
Cunninghamia lanceolata plantations in China
Mammalian lairs in paleo ecological studies and palynology
Studies on technological possibilities in utilization of anhydrous milk fat for production of recombined butter-like products
Should right-sided fibroelastomas be operated upon?
Large esophageal lipoma
Apoptosis in the mammalian thymus during normal histogenesis and under various in vitro and in vivo experimental conditions
Poissons characoides nouveaux ou non signales de l'Ilha do Bananal, Bresil
Desensitizing efficacy of Colgate Sensitive Maximum Strength and Fresh Mint Sensodyne dentifrices
Administration of fluid by subcutaneous infusion: revival of a forgotten method
Tundra mosquito control - an impossible dream?
Schizophrenia for primary care providers: how to contribute to the care of a vulnerable patient population
Geochemical pattern analysis; method of describing the Southeastern limestone regional aquifer system
Incidence of low birth weights in a hospital of Mexico City
Tabanidae
Graded management intensity of grassland systems for enhancing floristic diversity
Microbiology and biochemistry of cheese and fermented milk
The ember tetra: a new pygmy characid tetra from the Rio das Mortes, Brazil, Hyphessobrycon amandae sp. n. (Pisces, Characoidei)
Risk factors of contrast-induced nephropathy in patients after coronary artery intervention
Renovation of onsite domestic wastewater in a poorly drained soil
Observations of the propagation velocity and formation mechanism of burst fractures caused by gunshot
Systolic blood pressure in a population of infants in the first year of life: the Brompton study
Haematological studies in rats fed with metanil yellow
Studies on pasteurellosis. I. A new species of Pasteurella encountered in chronic fowl cholera
Dormancy breaking and germination of Acacia salicina Lindl. seeds
therapy of lupus nephritis. a two-year prospective study

Combining Docking Pose Rank and Structure with Deep Learning Improves Protein-Ligand Binding Mode Prediction over a Baseline Docking Approach


Combining Docking Pose Rank and Structure with Deep Learning Improves Protein-Ligand Binding Mode Prediction over a Baseline Docking Approach



Journal of Chemical Information and Modeling 60(9): 4170-4179



ISSN/ISBN: 1549-9596

PMID: 32077698

DOI: 10.1021/acs.jcim.9b00927

We present a simple, modular graph-based convolutional neural network that takes structural information from protein-ligand complexes as input to generate models for activity and binding mode prediction. Complex structures are generated by a standard docking procedure and fed into a dual-graph architecture that includes separate subnetworks for the ligand bonded topology and the ligand-protein contact map. Recent work has indicated that data set bias drives many past promising results derived from combining deep learning and docking. Our dual-graph network allows contributions from ligand identity that give rise to such biases to be distinguished from effects of protein-ligand interactions on classification. We show that our neural network is capable of learning from protein structural information when, as in the case of binding mode prediction, an unbiased data set is constructed. We next develop a deep learning model for binding mode prediction that uses docking ranking as input in combination with docking structures. This strategy mirrors past consensus models and outperforms a baseline docking program (AutoDock Vina) in a variety of tests, including on cross-docking data sets that mimic real-world docking use cases. Furthermore, the magnitudes of network predictions serve as reliable measures of model confidence.

Please choose payment method:






(PDF emailed within 0-6 h: $19.90)

Accession: 069832246

Download citation: RISBibTeXText

Related references

Incorporating backbone flexibility in MedusaDock improves ligand-binding pose prediction in the CSAR2011 docking benchmark. Journal of Chemical Information and Modeling 53(8): 1871-1879, 2013

Higher Accuracy Achieved for Protein-Ligand Binding Pose Prediction by Elastic Network Model-Based Ensemble Docking. Journal of chemical information and modeling 60(6): 2939-2950, 2020

Biased Docking for Protein-Ligand Pose Prediction. Methods in Molecular Biology 2266: 39-72, 2021

Cross-docking benchmark for automated pose and ranking prediction of ligand binding. Protein Science: a Publication of the Protein Society 29(1): 298-305, 2020

Combining machine learning systems and multiple docking simulation packages to improve docking prediction reliability for network pharmacology. Plos one 8(12): E83922, 2013

Multiple grid arrangement improves ligand docking with unknown binding sites: Application to the inverse docking problem. Computational Biology and Chemistry 73: 139-146, 2018

Multiple grid arrangement improves ligand docking with unknown binding sites: Application to the inverse docking problem. Computational Biology and Chemistry 73: 139-146, 2018

Blind docking method combining search of low-resolution binding sites with ligand pose refinement by molecular dynamics-based global optimization. Journal of Computational Chemistry 31(5): 1080-1092, 2010

A machine learning approach to predicting protein-ligand binding affinity with applications to molecular docking. Bioinformatics 26(9): 1169-1175, 2010

Binding mode prediction of cytochrome p450 and thymidine kinase protein-ligand complexes by consideration of water and rescoring in automated docking. Journal of Medicinal Chemistry 48(7): 2308-2318, 2005

Prediction of N-Methyl-D-Aspartate Receptor GluN1-Ligand Binding Affinity by a Novel SVM-Pose/SVM-Score Combinatorial Ensemble Docking Scheme. Scientific Reports 7: 40053, 2017

Protein-Ligand Docking in Drug Design: Performance Assessment and Binding-Pose Selection. Methods in Molecular Biology 1824: 67-88, 2018

Structure-based prediction of transcription factor binding sites using a protein-DNA docking approach. Proteins 72(4): 1114-1124, 2008

Using diverse potentials and scoring functions for the development of improved machine-learned models for protein-ligand affinity and docking pose prediction. Journal of Computer-Aided Molecular Design 35(11): 1095-1123, 2021

COACH-D: improved protein-ligand binding sites prediction with refined ligand-binding poses through molecular docking. Nucleic Acids Research 46(W1): W438-W442, 2018