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

Messenger RNA-based medicines hold immense potential, as evidenced by theirrapid deployment as COVID-19 vaccines. However, worldwide distribution of mRNAmolecules has been limited by their thermostability, which is fundamentallylimited by the intrinsic instability of RNA molecules to a chemical degradationreaction called in-line hydrolysis. Predicting the degradation of an RNAmolecule is a key task in designing more stable RNA-based therapeutics. Here,we describe a crowdsourced machine learning competition ("StanfordOpenVaccine") on Kaggle, involving single-nucleotide resolution measurements on6043 102-130-nucleotide diverse RNA constructs that were themselves solicitedthrough crowdsourcing on the RNA design platform Eterna. The entire experimentwas completed in less than 6 months, and 41% of nucleotide-level predictionsfrom the winning model were within experimental error of the ground truthmeasurement. Furthermore, these models generalized to blindly predictingorthogonal degradation data on much longer mRNA molecules (504-1588nucleotides) with improved accuracy compared to previously published models.Top teams integrated natural language processing architectures and dataaugmentation techniques with predictions from previous dynamic programmingmodels for RNA secondary structure. These results indicate that such models arecapable of representing in-line hydrolysis with excellent accuracy, supportingtheir use for designing stabilized messenger RNAs. The integration of twocrowdsourcing platforms, one for data set creation and another for machinelearning, may be fruitful for other urgent problems that demand scientificdiscovery on rapid timescales.

Deep learning models for predicting RNA degradation via dual crowdsourcing