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

Geometric deep learning has been revolutionizing the molecular modelingfield. Despite the state-of-the-art neural network models are approaching abinitio accuracy for molecular property prediction, their applications, such asdrug discovery and molecular dynamics (MD) simulation, have been hindered byinsufficient utilization of geometric information and high computational costs.Here we propose an equivariant geometry-enhanced graph neural network calledViSNet, which elegantly extracts geometric features and efficiently modelsmolecular structures with low computational costs. Our proposed ViSNetoutperforms state-of-the-art approaches on multiple MD benchmarks, includingMD17, revised MD17 and MD22, and achieves excellent chemical propertyprediction on QM9 and Molecule3D datasets. Additionally, ViSNet achieved thetop winners of PCQM4Mv2 track in the OGB-LCS@NeurIPS2022 competition.Furthermore, through a series of simulations and case studies, ViSNet canefficiently explore the conformational space and provide reasonableinterpretability to map geometric representations to molecular structures.

ViSNet: an equivariant geometry-enhanced graph neural network with vector-scalar interactive message passing for molecules