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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Automatic protein function prediction (AFP) is classified as a large-scalemulti-label classification problem aimed at automating protein enrichmentanalysis to eliminate the current reliance on labor-intensive wet-lab methods.Currently, popular methods primarily combine protein-related information andGene Ontology (GO) terms to generate final functional predictions. For example,protein sequences, structural information, and protein-protein interactionnetworks are integrated as prior knowledge to fuse with GO term embeddings andgenerate the ultimate prediction results. However, these methods are limited bythe difficulty in obtaining structural information or network topologyinformation, as well as the accuracy of such data. Therefore, more and moremethods that only use protein sequences for protein function prediction havebeen proposed, which is a more reliable and computationally cheaper approach.However, the existing methods fail to fully extract feature information fromprotein sequences or label data because they do not adequately consider theintrinsic characteristics of the data itself. Therefore, we propose asequence-based hierarchical prediction method, DeepGATGO, which processesprotein sequences and GO term labels hierarchically, and utilizes graphattention networks (GATs) and contrastive learning for protein functionprediction. Specifically, we compute embeddings of the sequence and label datausing pre-trained models to reduce computational costs and improve theembedding accuracy. Then, we use GATs to dynamically extract the structuralinformation of non-Euclidean data, and learn general features of the labeldataset with contrastive learning by constructing positive and negative examplesamples. Experimental results demonstrate that our proposed model exhibitsbetter scalability in GO term enrichment analysis on large-scale datasets.

DeepGATGO: A Hierarchical Pretraining-Based Graph-Attention Model for Automatic Protein Function Prediction