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

The present gap between the amount of available protein sequence due to thedevelopment of next generation sequencing technology (NGS) and slow andexpensive experimental extraction of useful information like annotation ofprotein sequence in different functional aspects, is ever widening, which canbe reduced by employing automatic function prediction (AFP) approaches. GeneOntology (GO), comprising of more than 40, 000 classes, defines three aspectsof protein function names Biological Process (BP), Cellular Component (CC),Molecular Function (MF). Multiple functions of a single protein, has madeautomatic function prediction a large-scale, multi-class, multi-label task. Inthis paper, we present DEEPGONET, a novel cascaded convolutional and recurrentneural network, to predict the top-level hierarchy of GO ontology. The networktakes the primary sequence of protein as input which makes it more useful thanother prevailing state-of-the-art deep learning based methods with multi-modalinput, making them less applicable for proteins where only primary sequence isavailable. All predictions of different protein functions of our network areperformed by the same architecture, a proof of better generalization asdemonstrated by promising performance on a variety of organisms while trainedon Homo sapiens only, which is made possible by efficient exploration of vastoutput space by leveraging hierarchical relationship among GO classes. Thepromising performance of our model makes it a potential avenue for directingexperimental protein functions exploration efficiently by vastly eliminatingpossible routes which is done by the exploring only the suggested routes fromour model. Our proposed model is also very simple and efficient in terms ofcomputational time and space compared to other architectures in literature.

DEEPGONET: Multi-label Prediction of GO Annotation for Protein from Sequence Using Cascaded Convolutional and Recurrent Network