Machine learning based energy-free structure predictions of molecules, transition states, and solids

Author(s)
Dominik Lemm, Guido Falk von Rudorff, O. Anatole von Lilienfeld
Abstract

Accurate computational prediction of atomistic structure with traditional methods is challenging. The authors report a kernel-based machine learning model capable of reconstructing 3D atomic coordinates from predicted interatomic distances across a variety of system classes.The computational prediction of atomistic structure is a long-standing problem in physics, chemistry, materials, and biology. Conventionally, force-fields or ab initio methods determine structure through energy minimization, which is either approximate or computationally demanding. This accuracy/cost trade-off prohibits the generation of synthetic big data sets accounting for chemical space with atomistic detail. Exploiting implicit correlations among relaxed structures in training data sets, our machine learning model Graph-To-Structure (G2S) generalizes across compound space in order to infer interatomic distances for out-of-sample compounds, effectively enabling the direct reconstruction of coordinates, and thereby bypassing the conventional energy optimization task. The numerical evidence collected includes 3D coordinate predictions for organic molecules, transition states, and crystalline solids. G2S improves systematically with training set size, reaching mean absolute interatomic distance prediction errors of less than 0.2 A for less than eight thousand training structures - on par or better than conventional structure generators. Applicability tests of G2S include successful predictions for systems which typically require manual intervention, improved initial guesses for subsequent conventional ab initio based relaxation, and input generation for subsequent use of structure based quantum machine learning models.

Organisation(s)
Computational Materials Physics
External organisation(s)
Universität Basel
Journal
Nature Communications
Volume
12
No. of pages
10
ISSN
2041-1723
DOI
https://doi.org/10.1038/s41467-021-24525-7
Publication date
07-2021
Peer reviewed
Yes
Austrian Fields of Science 2012
103006 Chemical physics
Keywords
Portal url
https://ucris.univie.ac.at/portal/en/publications/machine-learning-based-energyfree-structure-predictions-of-molecules-transition-states-and-solids(ee23cc48-b9e2-4209-a53e-37e9b74fb359).html