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

Molecular property prediction (MPP) is a fundamental but challenging task inthe computer-aided drug discovery process. More and more recent works employdifferent graph-based models for MPP, which have made considerable progress inimproving prediction performance. However, current models often ignorerelationships between molecules, which could be also helpful for MPP. For thissake, in this paper we propose a graph structure learning (GSL) based MPPapproach, called GSL-MPP. Specifically, we first apply graph neural network(GNN) over molecular graphs to extract molecular representations. Then, withmolecular fingerprints, we construct a molecular similarity graph (MSG).Following that, we conduct graph structure learning on the MSG (i.e.,molecule-level graph structure learning) to get the final molecular embeddings,which are the results of fusing both GNN encoded molecular representations andthe relationships among molecules, i.e., combining both intra-molecule andinter-molecule information. Finally, we use these molecular embeddings toperform MPP. Extensive experiments on seven various benchmark datasets showthat our method could achieve state-of-the-art performance in most cases,especially on classification tasks. Further visualization studies alsodemonstrate the good molecular representations of our method.

Molecular Property Prediction Based on Graph Structure Learning