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 prediction of protein interactions (CPIs) is crucial for the in-silicoscreening step in drug discovery. Recently, many end-to-end representationlearning methods using deep neural networks have achieved significantly betterperformance than traditional machine learning algorithms. Much effort hasfocused on the compound representation or the information extraction from thecompound-protein interaction to improve the model capability by taking theadvantage of the neural attention mechanism. However, previous studies havepaid little attention to representing the protein sequences, in which thelong-range interactions of residue pairs are essential for characterizing thestructural properties arising from the protein folding. We incorporate theself-attention mechanism into the protein representation module for CPImodeling, which aims at capturing the long-range interaction information withinproteins. The proposed module concerning protein representation, called ProteinTransformer, with an integration with an existing CPI model, has shown asignificant improvement in the prediction performance when compared withseveral existing CPI models.

GNN-PT: Enhanced Prediction of Compound-protein Interactions by Integrating Protein Transformer