Pose Classification using 3D Atomic Structure-Based Neural Networks Applied to Ion Channel-Ligand Docking

Heesung Shim, Hyo-Jin Kim, Jonathan Allen, Heike WulffChemRxiv 2022 · DOI

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 3D 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 datasets including the standard PDBbind CASF-2016 benchmark dataset and various compound libraries with structurally different protein targets including an ion-channel dataset extracted from Protein Data Bank (PDB) and an inhouse KCa3.1 inhibitor dataset. 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.
BibTeX
@inproceedings{shim2022pose,
  author = {Heesung Shim and Hyo-Jin Kim and Jonathan Allen and Heike Wulff},
  title = {{Pose Classification using 3D Atomic Structure-Based Neural Networks Applied to Ion Channel-Ligand Docking}},
  booktitle = {ChemRxiv},
  year = {2022},
  doi = {10.26434/chemrxiv-2022-q8cpx},
}

Loading related content...

Figure