Vis enkel innførsel

dc.contributor.authorLederer, Jonas
dc.contributor.authorGastegger, Michael
dc.contributor.authorSchütt, Kristof T.
dc.contributor.authorKampffmeyer, Michael Christian
dc.contributor.authorMüller, Klaus-Robert
dc.contributor.authorUnke, Oliver T.
dc.description.abstractIn recent years, the prediction of quantum mechanical observables with machine learning methods has become increasingly popular. Message-passing neural networks (MPNNs) solve this task by constructing atomic representations, from which the properties of interest are predicted. Here, we introduce a method to automatically identify chemical moieties (molecular building blocks) from such representations, enabling a variety of applications beyond property prediction, which otherwise rely on expert knowledge. The required representation can either be provided by a pretrained MPNN, or be learned from scratch using only structural information. Beyond the data-driven design of molecular fingerprints, the versatility of our approach is demonstrated by enabling the selection of representative entries in chemical databases, the automatic construction of coarse-grained force fields, as well as the identification of reaction coordinates.en_US
dc.identifier.citationLederer, Gastegger, Schütt, Kampffmeyer, Müller, Unke. Automatic identification of chemical moieties. Physical Chemistry, Chemical Physics - PCCP. 2023;25(38):26370-26379en_US
dc.identifier.cristinIDFRIDAID 2185846
dc.publisherRoyal Society of Chemistryen_US
dc.relation.journalPhysical Chemistry, Chemical Physics - PCCP
dc.rights.holderCopyright 2023 The Owner Societiesen_US
dc.rightsAttribution-NonCommercial 4.0 International (CC BY-NC 4.0)en_US
dc.titleAutomatic identification of chemical moietiesen_US
dc.typeJournal articleen_US
dc.typePeer revieweden_US

Tilhørende fil(er)


Denne innførselen finnes i følgende samling(er)

Vis enkel innførsel

Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)
Med mindre det står noe annet, er denne innførselens lisens beskrevet som Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)