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 combination of neural network potential (NNP) with molecular simulationsplays an important role in an efficient and thorough understanding of amolecular system's potential energy surface (PES). However, grasping theinterplay between input features and their local contribution to NNP isgrowingly evasive due to heavy featurization. In this work, we suggest anend-to-end model which directly predicts per-atom energy from the coordinatesof particles, avoiding expert-guided featurization of the network input.Employing self-attention as the main workhorse, our model is intrinsicallyequivariant under the permutation operation, resulting in the invariance of thetotal potential energy. We tested our model against several challenges inmolecular simulation problems, including periodic boundary condition (PBC),$n$-body interaction, and binary composition. Our model yielded stablepredictions in all tested systems with errors significantly smaller than thepotential energy fluctuation acquired from molecular dynamics simulations.Thus, our work provides a minimal baseline model that encodes complexinteractions in a condensed phase system to facilitate the data-driven analysisof physicochemical systems.

A2I Transformer: Permutation-equivariant attention network for pairwise and many-body interactions with minimal featurization