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 increasing number of protein sequences decoded from genomes is opening upnew avenues of research on linking protein sequence to function withtransformer neural networks. Recent research has shown that the number of knownprotein sequences supports learning useful, task-agnostic sequencerepresentations via transformers. In this paper, we posit that learning jointsequence-structure representations yields better representations forfunction-related prediction tasks. We propose a transformer neural network thatattends to both sequence and tertiary structure. We show that such jointrepresentations are more powerful than sequence-based representations only, andthey yield better performance on superfamily membership across various metrics.

Transformer Neural Networks Attending to Both Sequence and Structure for Protein Prediction Tasks