English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Predicting quantum chemical properties is a fundamental challenge forcomputational chemistry. While the development of graph neural networks hasadvanced molecular representation learning and property prediction, theirperformance could be further enhanced by incorporating 3D structural geometryinto 2D molecular graph representation. In this study, we introduce thePointGAT model for quantum molecular property prediction, which integrates 3Dmolecular coordinates with graph-attention modeling. Comparison with othercurrent models in molecular prediction tasks showed that PointGAT could providehigher predictive accuracy in various benchmark datasets from MoleculeNet,including ESOL, FreeSolv, Lipop, HIV, and 10 out of 12 tasks of the QM9dataset. To further examine PointGAT prediction of quantum mechanical (QM)energies, we constructed a C10 dataset comprising 11,841 charged and chiralcarbocation intermediates with QM energies calculated at theDM21/6-31G*//B3LYP/6-31G* levels. Notably, PointGAT achieved an R2 value of0.950 and an MAE of 1.616 kcal/mol, outperforming other models. Additionalablation studies indicated that incorporating molecular geometry into the modelresulted in markedly higher predictive accuracy, reducing the MAE value from1.802 kcal/mol to 1.616 kcal/mol. Moreover, visualization of PointGAT atomicattention weights suggested its predictions were interpretable. Findings inthis study support the application of PointGAT as a powerful and versatile toolfor quantum chemical property prediction that can facilitate high-accuracymodeling for fundamental exploration of chemical space as well as drug designand molecular engineering.

PointGAT: A quantum chemical property prediction model integrating graph attention and 3D geometry