dc.contributor.author
Kilgour, Michael
dc.contributor.author
Rogal, Jutta
dc.contributor.author
Tuckerman, Mark
dc.date.accessioned
2023-08-07T09:23:19Z
dc.date.available
2023-08-07T09:23:19Z
dc.identifier.uri
https://refubium.fu-berlin.de/handle/fub188/39701
dc.identifier.uri
http://dx.doi.org/10.17169/refubium-39419
dc.description.abstract
We develop and test new machine learning strategies for accelerating molecular crystal structure ranking and crystal property prediction using tools from geometric deep learning on molecular graphs. Leveraging developments in graph-based learning and the availability of large molecular crystal data sets, we train models for density prediction and stability ranking which are accurate, fast to evaluate, and applicable to molecules of widely varying size and composition. Our density prediction model, MolXtalNet-D, achieves state-of-the-art performance, with lower than 2% mean absolute error on a large and diverse test data set. Our crystal ranking tool, MolXtalNet-S, correctly discriminates experimental samples from synthetically generated fakes and is further validated through analysis of the submissions to the Cambridge Structural Database Blind Tests 5 and 6. Our new tools are computationally cheap and flexible enough to be deployed within an existing crystal structure prediction pipeline both to reduce the search space and score/filter crystal structure candidates.
en
dc.format.extent
14 Seiten
dc.rights.uri
https://creativecommons.org/licenses/by/4.0/
dc.subject
Crystal structure
en
dc.subject
Molecular modeling
en
dc.subject.ddc
500 Naturwissenschaften und Mathematik::540 Chemie::540 Chemie und zugeordnete Wissenschaften
dc.title
Geometric Deep Learning for Molecular Crystal Structure Prediction
dc.type
Wissenschaftlicher Artikel
dcterms.bibliographicCitation.doi
10.1021/acs.jctc.3c00031
dcterms.bibliographicCitation.journaltitle
Journal of Chemical Theory and Computation
dcterms.bibliographicCitation.number
14
dcterms.bibliographicCitation.pagestart
4743
dcterms.bibliographicCitation.pageend
4756
dcterms.bibliographicCitation.volume
19
dcterms.bibliographicCitation.url
https://doi.org/10.1021/acs.jctc.3c00031
refubium.affiliation
Physik
refubium.resourceType.isindependentpub
no
dcterms.accessRights.openaire
open access
dcterms.isPartOf.eissn
1549-9626
refubium.resourceType.provider
WoS-Alert