Automatic identification of chemical moieties
Lederer, Jonas; Gastegger, Michael; Schütt, Kristof T.; Kampffmeyer, Michael Christian; Müller, Klaus-Robert; Unke, Oliver T.
Journal article, Peer reviewed
Published version
Permanent lenke
https://hdl.handle.net/11250/3105997Utgivelsesdato
2023Metadata
Vis full innførselOriginalversjon
Physical Chemistry, Chemical Physics - PCCP. 2023, 25 (38), 26370-26379. 10.1039/d3cp03845aSammendrag
In 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.