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

Recent advances in applying Graph Neural Networks (GNNs) to molecular sciencehave showcased the power of learning three-dimensional (3D) structurerepresentations with GNNs. However, most existing GNNs suffer from thelimitations of insufficient modeling of diverse interactions, computationalexpensive operations, and ignorance of vectorial values. Here, we tackle theselimitations by proposing a novel GNN model, Physics-aware Multiplex GraphNeural Network (PaxNet), to efficiently and accurately learn therepresentations of 3D molecules for both small organic compounds andmacromolecule complexes. PaxNet separates the modeling of local and non-localinteractions inspired by molecular mechanics, and reduces the expensiveangle-related computations. Besides scalar properties, PaxNet can also predictvectorial properties by learning an associated vector for each atom. Toevaluate the performance of PaxNet, we compare it with state-of-the-artbaselines in two tasks. On small molecule dataset for predicting quantumchemical properties, PaxNet reduces the prediction error by 15% and uses 73%less memory than the best baseline. On macromolecule dataset for predictingprotein-ligand binding affinities, PaxNet outperforms the best baseline whilereducing the memory consumption by 33% and the inference time by 85%. Thus,PaxNet provides a universal, robust and accurate method for large-scale machinelearning of molecules. Our code is available athttps://github.com/zetayue/Physics-aware-Multiplex-GNN.

Efficient and Accurate Physics-aware Multiplex Graph Neural Networks for 3D Small Molecules and Macromolecule Complexes