Pose Classification Using Three-Dimensional Atomic Structure-Based Neural Networks Applied to Ion Channel–Ligand Docking
Open Access
- 21 April 2022
- journal article
- research article
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 62 (10) , 2301-2315
Abstract
The identification of promising lead compounds showing pharmacological activities toward a biological target is essential in early stage drug discovery. With the recent increase in available small-molecule databases, virtual high-throughput screening using physics-based molecular docking has emerged as an essential tool in assisting fast and cost-efficient lead discovery and optimization. However, the best scored docking poses are often suboptimal, resulting in incorrect screening and chemical property calculation. We address the pose classification problem by leveraging data-driven machine learning approaches to identify correct docking poses from AutoDock Vina and Glide screens. To enable effective classification of docking poses, we present two convolutional neural network approaches: a three-dimensional convolutional neural network (3D-CNN) and an attention-based point cloud network (PCN) trained on the PDBbind refined set. We demonstrate the effectiveness of our proposed classifiers on multiple evaluation data sets including the standard PDBbind CASF-2016 benchmark data set and various compound libraries with structurally different protein targets including an ion channel data set extracted from Protein Data Bank (PDB) and an in-house KCa3.1 inhibitor data set. Our experiments show that excluding false positive docking poses using the proposed classifiers improves virtual high-throughput screening to identify novel molecules against each target protein compared to the initial screen based on the docking scores.Keywords
All Related Versions
Funding Information
- U.S. Department of War (HDTRA1036045)
- CounterACT Program, National Institutes of Health Office of the Director (U54NS079202)
This publication has 51 references indexed in Scilit:
- Lessons Learned in Empirical Scoring with smina from the CSAR 2011 Benchmarking ExerciseJournal of Chemical Information and Modeling, 2013
- Variability in docking success rates due to dataset preparationJournal of Computer-Aided Molecular Design, 2012
- NNScore 2.0: A Neural-Network Receptor–Ligand Scoring FunctionJournal of Chemical Information and Modeling, 2011
- NNScore: A Neural-Network-Based Scoring Function for the Characterization of Protein−Ligand ComplexesJournal of Chemical Information and Modeling, 2010
- A machine learning approach to predicting protein–ligand binding affinity with applications to molecular dockingBioinformatics, 2010
- AutoDock Vina: Improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreadingJournal of Computational Chemistry, 2009
- AutoDock4 and AutoDockTools4: Automated docking with selective receptor flexibilityJournal of Computational Chemistry, 2009
- Overcoming the challenges of membrane protein crystallographyCurrent Opinion in Structural Biology, 2008
- MedusaScore: An Accurate Force Field-Based Scoring Function for Virtual Drug ScreeningJournal of Chemical Information and Modeling, 2008
- Knowledge-based scoring function to predict protein-ligand interactionsJournal of Molecular Biology, 2000