Machine Learned Model for Solid Form Volume Estimation Based on Packing-Accessible Surface and Molecular Topological Fragments
Authors:
- 30 November 2020
- journal article
- research article
- Published by American Chemical Society (ACS) in The Journal of Physical Chemistry A
- Vol. 124 (49) , 10330-10345
Abstract
We present a machine learned model for predicting the volume of a homomolecular crystal based on the single-molecule structure, implemented in the open-source Python package for Molecular Volume Estimation (PyMoVE). The model is based on two descriptors: the volume enclosed by the packing-accessible surface and molecular topological fragments. To calculate the volume enclosed by the molecular surface, we have developed a new “projected marching cubes” algorithm. The new algorithm achieves a higher accuracy with a smaller number of elements than the traditional marching cubes algorithm, the marching tetrahedron variant, and Monte Carlo methods. The packing-accessible surface is then calculated using an optimized probe radius. The molecular topological fragments are used to construct a representation that captures the bonding environments of the atoms in the molecule. Feature selection is used to determine which fragments to include in the model. The accuracy and robustness of the model may be attributed to including both geometric and chemical features. The volume enclosed by the packing-accessible surface accounts for the presence of voids and sterically hindered regions as well as for the effect of conformational changes. The molecular topological fragments account for the effect of intermolecular interactions on the packing density. The model is trained on a dataset of structures extracted from the Cambridge Structural Database. Excellent performance is demonstrated for three validation sets of unseen data.Keywords
Funding Information
- Army Research Office (W911NF1810148)
- Division of Materials Research (DMR-1554428)
This publication has 101 references indexed in Scilit:
- Rational Construction of an Extrinsic Porous Molecular Crystal with an Extraordinary High Specific Surface AreaAngewandte Chemie International Edition, 2012
- Predicting protein-protein interface residues using local surface structural similarityBMC Bioinformatics, 2012
- Ligand docking and binding site analysis with PyMOL and Autodock/VinaJournal of Computer-Aided Molecular Design, 2010
- Generating Triangulated Macromolecular Surfaces by Euclidean Distance TransformPLOS ONE, 2009
- Detection of multiscale pockets on protein surfaces using mathematical morphologyProteins: Structure, Function, and Bioinformatics, 2009
- PoreWalker: A Novel Tool for the Identification and Characterization of Channels in Transmembrane Proteins from Their Three-Dimensional StructurePLOS Computational Biology, 2009
- Fast protein tertiary structure retrieval based on global surface shape similarityProteins: Structure, Function, and Bioinformatics, 2008
- MOLE: A Voronoi Diagram-Based Explorer of Molecular Channels, Pores, and TunnelsStructure, 2007
- Green primary explosives: 5-Nitrotetrazolato- N 2 -ferrate hierarchiesProceedings of the National Academy of Sciences, 2006
- Environment and exposure to solvent of protein atoms. Lysozyme and insulinJournal of Molecular Biology, 1973