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

Motivation: Predicting the drug-target interaction is crucial for drugdiscovery as well as drug repurposing. Machine learning is commonly used indrug-target affinity (DTA) problem. However, machine learning model faces thecold-start problem where the model performance drops when predicting theinteraction of a novel drug or target. Previous works try to solve the coldstart problem by learning the drug or target representation using unsupervisedlearning. While the drug or target representation can be learned in anunsupervised manner, it still lacks the interaction information, which iscritical in drug-target interaction. Results: To incorporate the interactioninformation into the drug and protein interaction, we proposed using transferlearning from chemical-chemical interaction (CCI) and protein-proteininteraction (PPI) task to drug-target interaction task. The representationlearned by CCI and PPI tasks can be transferred smoothly to the DTA task due tothe similar nature of the tasks. The result on the drug-target affinitydatasets shows that our proposed method has advantages compared to otherpretraining methods in the DTA task.

Mitigating cold start problems in drug-target affinity prediction with interaction knowledge transferring