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

The prediction of quantum mechanical properties is historically plagued by atrade-off between accuracy and speed. Machine learning potentials havepreviously shown great success in this domain, reaching increasingly betteraccuracy while maintaining computational efficiency comparable with classicalforce fields. In this work we propose TorchMD-NET, a novel equivarianttransformer (ET) architecture, outperforming state-of-the-art on MD17, ANI-1,and many QM9 targets in both accuracy and computational efficiency. Through anextensive attention weight analysis, we gain valuable insights into the blackbox predictor and show differences in the learned representation of conformersversus conformations sampled from molecular dynamics or normal modes.Furthermore, we highlight the importance of datasets including off-equilibriumconformations for the evaluation of molecular potentials.

TorchMD-NET: Equivariant Transformers for Neural Network based Molecular Potentials