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 study of molecule-target interaction is quite important for drugdiscovery in terms of target identification, hit identification, pathway study,drug-drug interaction, etc. Most existing methodologies utilize eitherbiomedical network information or molecule structural features to predictpotential interaction link. However, the biomedical network information basedmethods usually suffer from cold start problem, while structure based methodsoften give limited performance due to the structure/interaction assumption anddata quality. To address these issues, we propose a pseudo-siamese Graph NeuralNetwork method, namely MTINet+, which learns both biomedical networktopological and molecule structural/chemical information as representations topredict potential interaction of given molecule and target pair. In MTINet+,1-hop subgraphs of given molecule and target pair are extracted from knowninteraction of biomedical network as topological information, meanwhile themolecule structural and chemical attributes are processed as moleculeinformation. MTINet+ learns these two types of information as embeddingfeatures for predicting the pair link. In the experiments of differentmolecule-target interaction tasks, MTINet+ significantly outperforms over thestate-of-the-art baselines. In addition, in our designed network sparsityexperiments , MTINet+ shows strong robustness against different sparsebiomedical networks.

Predicting Molecule-Target Interaction by Learning Biomedical Network and Molecule Representations