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

Graphs can be used to effectively represent complex data structures. Learningthese irregular data in graphs is challenging and still suffers from shallowlearning. Applying deep learning on graphs has recently showed good performancein many applications in social analysis, bioinformatics etc. A message passinggraph convolution network is such a powerful method which has expressive powerto learn graph structures. Meanwhile, circRNA is a type of non-coding RNA whichplays a critical role in human diseases. Identifying the associations betweencircRNAs and diseases is important to diagnosis and treatment of complexdiseases. However, there are limited number of known associations between themand conducting biological experiments to identify new associations is timeconsuming and expensive. As a result, there is a need of building efficient andfeasible computation methods to predict potential circRNA-disease associations.In this paper, we propose a novel graph convolution network framework to learnfeatures from a graph built with multi-source similarity information to predictcircRNA-disease associations. First we use multi-source information of circRNAsimilarity, disease and circRNA Gaussian Interaction Profile (GIP) kernelsimilarity to extract the features using first graph convolution. Then wepredict disease associations for each circRNA with second graph convolution.Proposed framework with five-fold cross validation on various experiments showspromising results in predicting circRNA-disease association and outperformsother existing methods.

Graph Convolution Networks Using Message Passing and Multi-Source Similarity Features for Predicting circRNA-Disease Association