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

Predicting drug-target interactions (DTI) via reliable computational methodsis an effective and efficient way to mitigate the enormous costs and time ofthe drug discovery process. Structure-based drug similarities andsequence-based target protein similarities are the commonly used informationfor DTI prediction. Among numerous computational methods, neighborhood-basedchemogenomic approaches that leverage drug and target similarities to performpredictions directly are simple but promising ones. However, existingsimilarity-based methods need to be re-trained to predict interactions for anynew drugs or targets and cannot directly perform predictions for both newdrugs, new targets, and new drug-target pairs. Furthermore, a large amount ofmissing (undetected) interactions in current DTI datasets hinders most DTIprediction methods. To address these issues, we propose a new method denoted asWeighted k-Nearest Neighbor with Interaction Recovery (WkNNIR). Not only canWkNNIR estimate interactions of any new drugs and/or new targets without anyneed of re-training, but it can also recover missing interactions (falsenegatives). In addition, WkNNIR exploits local imbalance to promote theinfluence of more reliable similarities on the interaction recovery andprediction processes. We also propose a series of ensemble methods that employdiverse sampling strategies and could be coupled with WkNNIR as well as anyother DTI prediction method to improve performance. Experimental results overfive benchmark datasets demonstrate the effectiveness of our approaches inpredicting drug-target interactions. Lastly, we confirm the practicalprediction ability of proposed methods to discover reliable interactions thatwere not reported in the original benchmark datasets.

Drug-Target Interaction Prediction via an Ensemble of Weighted Nearest Neighbors with Interaction Recovery