Titel
Machine learning based energy-free structure predictions of molecules, transition states, and solids
Abstract
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 Å 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.
Stichwort
CheminformaticsComputational chemistryQuantum chemistryStructure prediction
Objekt-Typ
Sprache
Englisch [eng]
Persistent identifier
Erschienen in
Titel
Nature Communications
Band
12
ISSN
2041-1723
Erscheinungsdatum
2021
Publication
Springer Science and Business Media LLC
Projekt
Kod / Identifikator
952165
Projekt
Kod / Identifikator
957189
Projekt
Kod / Identifikator
772834
Erscheinungsdatum
2021
Zugänglichkeit
Rechteangabe
© The Author(s) 2021

Herunterladen

Universität Wien | Universitätsring 1 | 1010 Wien | T +43-1-4277-0