in the repository
URN to cite this document: urn:nbn:de:bvb:703-epub-7960-4
Title data
Margraf, Johannes T.:
Neural graph distance embedding for molecular geometry generation.
In: Journal of Computational Chemistry.
Vol. 45
(2024)
Issue 21
.
- pp. 1784-1790.
ISSN 1096-987X
DOI der Verlagsversion: https://doi.org/10.1002/jcc.27349
![[thumbnail of J Comput Chem - 2024 - Margraf - Neural graph distance embedding for molecular geometry generation.pdf]](https://epub.uni-bayreuth.de/style/images/fileicons/application_pdf.png) |
|
||||||||
|
Download (1MB)
|
Abstract
Abstract This article introduces neural graph distance embedding (nGDE), a method for generating 3D molecular geometries. Leveraging a graph neural network trained on the OE62 dataset of molecular geometries, nGDE predicts interatomic distances based on molecular graphs. These distances are then used in multidimensional scaling to produce 3D geometries, subsequently refined with standard bioorganic forcefields. The machine learning-based graph distance introduced herein is found to be an improvement over the conventional shortest path distances used in graph drawing. Comparative analysis with a state-of-the-art distance geometry method demonstrates nGDE's competitive performance, particularly showcasing robustness in handling polycyclic molecules—a challenge for existing methods.
Download Statistics