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

RNA structure determination and prediction can promote RNA-targeted drugdevelopment and engineerable synthetic elements design. But due to theintrinsic structural flexibility of RNAs, all the three mainstream structuredetermination methods (X-ray crystallography, NMR, and Cryo-EM) encounterchallenges when resolving the RNA structures, which leads to the scarcity ofthe resolved RNA structures. Computational prediction approaches emerge ascomplementary to the experimental techniques. However, none of the \textit{denovo} approaches is based on deep learning since too few structures areavailable. Instead, most of them apply the time-consuming sampling-basedstrategies, and their performance seems to hit the plateau. In this work, wedevelop the first end-to-end deep learning approach, E2Efold-3D, to accuratelyperform the \textit{de novo} RNA structure prediction. Several novel componentsare proposed to overcome the data scarcity, such as a fully-differentiableend-to-end pipeline, secondary structure-assisted self-distillation, andparameter-efficient backbone formulation. Such designs are validated on theindependent, non-overlapping RNA puzzle testing dataset and reach an averagesub-4 \AA{} root-mean-square deviation, demonstrating its superior performancecompared to state-of-the-art approaches. Interestingly, it also achievespromising results when predicting RNA complex structures, a feat that none ofthe previous systems could accomplish. When E2Efold-3D is coupled with theexperimental techniques, the RNA structure prediction field can be greatlyadvanced.

E2Efold-3D: End-to-End Deep Learning Method for accurate de novo RNA 3D Structure Prediction