RNA molecules designed by citizen scientists and probed in high-throughput experiments highlighted discrepancies among RNA folding algorithms in their ability to predict RNA structure ensembles. These datasets were used to train a new algorithm that demonstrated improved performance in a collection of independent datasets, including viral genomic RNAs and mRNAs probed in cells.
This is a preview of subscription content, access via your institution
Access options
Access Nature and 54 other Nature Portfolio journals
Get Nature+, our best-value online-access subscription
$32.99 / 30 days
cancel any time
Subscribe to this journal
Receive 12 print issues and online access
$259.00 per year
only $21.58 per issue
Buy this article
- Purchase on SpringerLink
- Instant access to the full article PDF.
USD 39.95
Prices may be subject to local taxes which are calculated during checkout
References
Nussinov, R. et al. Algorithms for loop matchings. SIAM J. Appl. Math. 35, 68–82 (1978). This work presents a dynamic programming approach combined with energy weights to predict RNA base-pairing structures.
Andreasson, J. O. L. et al. Crowdsourced RNA design discovers diverse, reversible, efficient, self-contained molecular switches. Proc. Natl Acad. Sci. USA 119, e2112979119 (2022). This paper describes the Eterna riboswitch experiments, which formed the basis of our RNA folding evaluation using riboswitch protein affinities.
Lee, J. et al. RNA design rules from a massive open laboratory. Proc. Natl Acad. Sci. USA 111, 2122–2127 (2014). This paper describes the Eterna project and its initial results in uncovering new rules for RNA design.
Do, C. B. et al. CONTRAfold: RNA secondary structure prediction without physics-based models. Bioinformatics 22, e90–e98 (2006). This work describes the CONTRAfold algorithm, a conditional log-likelihood model with thermodynamic parameters inferred from their abundance in a natural RNA dataset.
Gao, J. et al. A survey on deep learning for multimodal data fusion. Neural Comput. 32, 829–864 (2020). This review discusses deep learning on combined multimodal data streams (text, images, video) and neural network architectures.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This is a summary of: Wayment-Steele, H. K. et al. RNA secondary structure packages evaluated and improved by high-throughput experiments. Nat. Methods https://doi.org/10.1038/s41592-022-01605-0 (2022).
Rights and permissions
About this article
Cite this article
Learning RNA structure prediction from crowd-designed RNAs. Nat Methods 19, 1181–1182 (2022). https://doi.org/10.1038/s41592-022-01607-y
Published:
Version of record:
Issue date:
DOI: https://doi.org/10.1038/s41592-022-01607-y
