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

In drug discovery, identifying drug-target interactions (DTIs) viaexperimental approaches is a tedious and expensive procedure. Computationalmethods efficiently predict DTIs and recommend a small part of potentialinteracting pairs for further experimental confirmation, accelerating the drugdiscovery process. Although it has been shown that fusing heterogeneous drugand target similarities can improve the prediction ability, the existingsimilarity combination methods ignore the interaction consistency for neighbourentities which is more crucial for the DTI prediction model. Furthermore, areaunder the precision-recall curve (AUPR) that emphasizes the accuracy oftop-ranked pairs and area under the receiver operating characteristic curve(AUC) that heavily punishes the existence of low ranked interacting pairs aretwo widely used evaluation metrics in DTI prediction. However, the two metricsare seldom considered as losses within existing DTI prediction methods. Thispaper first proposes two matrix factorization (MF) methods that optimize AUPRand AUC using convex surrogate losses respectively, and then develops anensemble MF approach takes advantage of the two area under the curve metrics bycombining the two single metric based MF models. Both three proposed approachesincorporate a novel local interaction consistency aware similarity interactionmethod to generate fused drug and target similarities that preserve vitalinformation from the more reliable view. Experimental results over fivedatasets under different prediction settings show that the proposed methodsoutperform various competitors in terms of the metric(s) they optimize. Inaddition, the validation on the top ranked novel predictions confirms theability of our methods to discover potential new DTIs.

Optimizing Area Under the Curve Measures via Matrix Factorization for Predicting Drug-Target Interaction with Multiple Similarities