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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

A molecule is a complex of heterogeneous components, and the spatialarrangements of these components determine the whole molecular properties andcharacteristics. With the advent of deep learning in computational chemistry,several studies have focused on how to predict molecular properties based onmolecular configurations. Message passing neural network provides an effectiveframework for capturing molecular geometric features with the perspective of amolecule as a graph. However, most of these studies assumed that allheterogeneous molecular features, such as atomic charge, bond length, or othergeometric features always contribute equivalently to the target prediction,regardless of the task type. In this study, we propose a dual-branched neuralnetwork for molecular property prediction based on message-passing framework.Our model learns heterogeneous molecular features with different scales, whichare trained flexibly according to each prediction target. In addition, weintroduce a discrete branch to learn single atom features without localaggregation, apart from message-passing steps. We verify that this novelstructure can improve the model performance with faster convergence in mosttargets. The proposed model outperforms other recent models with sparserrepresentations. Our experimental results indicate that in the chemicalproperty prediction tasks, the diverse chemical nature of targets should becarefully considered for both model performance and generalizability.

Flexible dual-branched message passing neural network for quantum mechanical property prediction with molecular conformation