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 years have seen a rapid growth of utilizing graph neural networks(GNNs) in the biomedical domain for tackling drug-related problems. However,like any other deep architectures, GNNs are data hungry. While requiring labelsin real world is often expensive, pretraining GNNs in an unsupervised mannerhas been actively explored. Among them, graph contrastive learning, bymaximizing the mutual information between paired graph augmentations, has beenshown to be effective on various downstream tasks. However, the current graphcontrastive learning framework has two limitations. First, the augmentationsare designed for general graphs and thus may not be suitable or powerful enoughfor certain domains. Second, the contrastive scheme only learns representationsthat are invariant to local perturbations and thus does not consider the globalstructure of the dataset, which may also be useful for downstream tasks.Therefore, in this paper, we study graph contrastive learning in the context ofbiomedical domain, where molecular graphs are present. We propose a novelframework called MoCL, which utilizes domain knowledge at both local- andglobal-level to assist representation learning. The local-level domainknowledge guides the augmentation process such that variation is introducedwithout changing graph semantics. The global-level knowledge encodes thesimilarity information between graphs in the entire dataset and helps to learnrepresentations with richer semantics. The entire model is learned through adouble contrast objective. We evaluate MoCL on various molecular datasets underboth linear and semi-supervised settings and results show that MoCL achievesstate-of-the-art performance.

MoCL: Data-driven Molecular Fingerprint via Knowledge-aware Contrastive Learning from Molecular Graph