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 field of protein folding research has been greatly advanced by deeplearning methods, with AlphaFold2 (AF2) demonstrating exceptional performanceand atomic-level precision. As co-evolution is integral to protein structureprediction, AF2's accuracy is significantly influenced by the depth of multiplesequence alignment (MSA), which requires extensive exploration of a largeprotein database for similar sequences. However, not all protein sequencespossess abundant homologous families, and consequently, AF2's performance candegrade on such queries, at times failing to produce meaningful results. Toaddress this, we introduce a novel generative language model, MSA-Augmenter,which leverages protein-specific attention mechanisms and large-scale MSAs togenerate useful, novel protein sequences not currently found in databases.These sequences supplement shallow MSAs, enhancing the accuracy of structuralproperty predictions. Our experiments on CASP14 demonstrate that MSA-Augmentercan generate de novo sequences that retain co-evolutionary information frominferior MSAs, thereby improving protein structure prediction quality on top ofstrong AF2.

Enhancing the Protein Tertiary Structure Prediction by Multiple Sequence Alignment Generation