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/

Zendy Plus

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

Zendy Tools

Zendy Open

Diffusion-based network models are widely used for protein functionprediction using protein network data and have been shown to outperformneighborhood- and module-based methods. Recent studies have shown thatintegrating the hierarchical structure of the Gene Ontology (GO) datadramatically improves prediction accuracy. However, previous methods usuallyeither used the GO hierarchy to refine the prediction results of multipleclassifiers, or flattened the hierarchy into a function-function similaritykernel. No study has taken the GO hierarchy into account together with theprotein network as a two-layer network model.  We first construct a Bi-relational graph (Birg) model comprised of bothprotein-protein association and function-function hierarchical networks. Wethen propose two diffusion-based methods, BirgRank and AptRank, both of whichuse PageRank to diffuse information on this two-layer graph model. BirgRank isan application of traditional PageRank with fixed decay parameters. Incontrast, AptRank uses an adaptive mechanism to improve the performance ofBirgRank. We evaluate both methods in predicting protein function on yeast,fly, and human datasets, and compare with four previous methods: GeneMANIA,TMC, ProteinRank and clusDCA. We design three validation strategies: missingfunction prediction, de novo function prediction, and guided functionprediction to comprehensively evaluate all six methods. We find that bothBirgRank and AptRank outperform the others, especially in missing functionprediction when using only 10% of the data for training.  AptRank combines protein-protein associations and the GO function-functionhierarchy into a two-layer network model without flattening the hierarchy intoa similarity kernel. Introducing an adaptive mechanism to the traditional,fixed-parameter model of PageRank greatly improves the accuracy of proteinfunction prediction.

AptRank: An Adaptive PageRank Model for Protein Function Prediction on Bi-relational Graphs