CoChat

Ribonanza: deep learning of RNA structure through dual crowdsourcing

Open access
He, Shujun, Huang, Rui, Townley, Jill, Kretsch, Rachael C., Karagianes, Thomas G., Cox, David B.T., Blair, Hamish, Penzar, Dmitry, Vyaltsev, Valeriy, Aristova, Elizaveta, Zinkevich, Arsenii, Bakulin, Artemy, Sohn, Hoyeol, Krstevski, Daniel, Fukui, Takaaki, Tatematsu, Fumiya, Uchida, Yusuke, Jang, Donghoon, Lee, Jun Seong, Shieh, Roger, Ma, Tom, Martynov, Eduard, Shugaev, Maxim V., Bukhari, Habib S.T., Fujikawa, Kazuki, Onodera, Kazuki, Henkel, Christof, Ron, Shlomo, Romano, Jonathan, Nicol, John J., Nye, Grace P., Wu, Yuan, Choe, Christian, Reade, Walter, Eterna participants, Das, Rhiju · 2024 · bioRxiv (Cold Spring Harbor Laboratory)
PreprintCited by 34

The DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.

Abstract

Prediction of RNA structure from sequence remains an unsolved problem, and progress has been slowed by a paucity of experimental data. Here, we present Ribonanza, a dataset of chemical mapping measurements on two million diverse RNA sequences collected through Eterna and other crowdsourced initiatives. Ribonanza measurements enabled solicitation, training, and prospective evaluation of diverse deep neural networks through a Kaggle challenge, followed by distillation into a single, self-contained model called RibonanzaNet. When fine tuned on auxiliary datasets, RibonanzaNet achieves state-of-the-art performance in modeling experimental sequence dropout, RNA hydrolytic degradation, and RNA secondary structure, with implications for modeling RNA tertiary structure.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1101/2024.02.24.581671

Cites

14 of 14 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 14 references

Research works printed but not linked: 59

  1. 10.1126/science.abj8754 · doi:10.1126/science.abj8754 · Paper page
  2. 10.1038/s41467-023-42528-4 · DOI · Paper page
  3. 10.1038/s41592-023-02086-5 · DOI · Paper page
  4. 10.1126/sci-ence.adl2528 · doi:10.1126/sci-ence.adl2528
  5. 10.1038/s41576-018-0034-x · DOI · Paper page
  6. 2023, Assessment of three-dimensional RNA structure prediction in CASP15, Proteins, 91, 1747, 10.1002/prot.26602 · DOI · Paper page
  7. 2023, When will RNA get its AlphaFold moment?, Nucleic Acids Res, 51, 9522, 10.1093/nar/gkad726 · DOI · Paper page
  8. 10.1101/2023.12.13.571579 · DOI
  9. 10.1093/NAR/GKAA1047 · DOI · Paper page
  10. 10.1093/nar/gkx699 · DOI · Paper page
  11. 10.1038/s41565-019-0517-8 · DOI · Paper page
  12. 2021, RiboDraw: semiautomated two-dimensional drawing of RNA tertiary structure diagrams, NAR Genom Bioinform, 3, lqab091, 10.1093/nargab/lqab091 · DOI
  13. 9th Workshop on Statistical Machine Translation 2014: Baltimore, Maryland, USA, 26 - 27 June 2014; Held at ACL 2014, [the 52nd Annual Meeting of the Association for Computational Linguistics]. (2014).
  14. 2022, Deep learning models for predicting RNA degradation via dual crowdsourcing, Nat Mach Intell, 4, 1174, 10.1038/s42256-022-00571-8 · DOI
  15. 10.1073/pnas.1313039111 · DOI · Paper page
  16. 10.1093/nar/gkn806 · DOI
  17. 10.1038/s41592-022-01605-0 · DOI · Paper page
  18. 10.1016/0959-440X(92)90221-R · DOI
  19. Justyna, M. , Antczak, M. & Szachniuk, M. Machine learning for RNA 2D structure prediction benchmarked on experimental data. Brief. Bioinform. 24, (2023). · DOI · Paper page
  20. 10.1038/nmeth.4057 · DOI · Paper page
  21. 10.1093/nar/gkad522 · DOI
  22. 2021, A novel SHAPE reagent enables the analysis of RNA structure in living cells with unprecedented accuracy, Nucleic Acids Res, 49, e34, 10.1093/nar/gkaa1255 · DOI
  23. 10.1038/nmeth.3029 · DOI · Paper page
  24. 10.1371/journal.pbio.0030172 · DOI · Paper page
  25. 10.1261/rna.076141.120 · DOI · Paper page
  26. 10.1038/nchem.1176 · DOI · Paper page
  27. 10.1261/rna.060368.116 · DOI · Paper page
  28. 10.1261/rna.049502.114 · DOI · Paper page
  29. He, S. , Gao, B. , Sabnis, R. & Sun, Q. RNAdegformer: accurate prediction of mRNA degradation at nucleotide resolution with deep learning. Brief. Bioinform. 24, (2023). · DOI
  30. 10.48550/ARXIV.1706.03762 · DOI · Paper page
  31. 10.1073/pnas.2221324120 · DOI
  32. 2023, RNA target highlights in CASP15: Evaluation of predicted models by structure providers, Proteins, 91, 1600, 10.1002/prot.26550 · DOI · Paper page
  33. 10.48550/ARXIV.2204.00300 · arXiv · doi:10.48550/arxiv.2204.00300
  34. 2023, Advancing RNA 3D structure prediction: Exploring hierarchical and hybrid approaches in CASP15, Proteins, 91, 1779, 10.1002/prot.26583 · DOI
  35. 2023, RNA tertiary structure prediction using RNAComposer in CASP15, Proteins, 91, 1790, 10.1002/prot.26578 · DOI · Paper page
  36. 2023, RNA tertiary structure prediction in CASP15 by the GeneSilico group: Folding simulations based on statistical potentials and spatial restraints, Proteins, 91, 1800, 10.1002/prot.26575 · DOI
  37. 10.1038/s41467-019-13395-9 · DOI · Paper page
  38. 10.1002/bip.360290621 · DOI · Paper page
  39. 10.1002/jcc.10296 · DOI · Paper page
  40. 10.48550/ARXIV.1912.12796 · DOI
  41. 10.1093/bioinformatics/btl246 · DOI · Paper page
  42. 10.1261/rna.7284905 · DOI · Paper page
  43. 10.1093/bioinformatics/btr215 · DOI · Paper page
  44. 10.1186/1471-2105-15-147 · DOI
  45. 10.1093/bioinformatics/bty420 · DOI
  46. 10.1093/nar/gkm258 · DOI
  47. 10.1073/pnas.1219988110 · DOI · Paper page
  48. 10.1109/TAES.2016.140952 · DOI · Paper page
  49. 2020, Emulsion PCR made easy, Biotechniques, 69, 421
  50. 2021, Ultraplex: A rapid, flexible, all-in-one fastq demultiplexer, Wellcome Open Res, 6, 141, 10.12688/wellcomeopenres.16791.1 · DOI
  51. 10.1038/nmeth.1923 · DOI · Paper page
  52. 10.1093/nar/gky486 · DOI
  53. 10.1093/bioinformatics/btaa460 · DOI · Paper page
  54. 10.48550/ARXIV.2207.01586 · DOI
  55. 2018, Updates to the RNA mapping database (RMDB), version 2, Nucleic Acids Res, 46, D375, 10.1093/nar/gkx873 · DOI
  56. 10.48550/ARXIV.2106.13731 · DOI
  57. 10.1093/nar/gkt800 · DOI
  58. 10.1093/nar/gkac372 · DOI
  59. 10.1107/S0907444913007051 · DOI · Paper page

Cited by

See all 34

Metadata

Authors
He, S., Huang, R., Townley, J., Kretsch, R. C., Karagianes, T. G., Cox, D. B. T., Blair, H., Penzar, D., Vyaltsev, V., Aristova, E., Zinkevich, A., Bakulin, A., Sohn, H., Krstevski, D., Fukui, T., Tatematsu, F., Uchida, Y., Jang, D., Lee, J. S., Shieh, R., Ma, T., Martynov, E., Shugaev, M. V., Bukhari, H. S. T., Fujikawa, K., Onodera, K., Henkel, C., Ron, S., Romano, J., Nicol, J. J., Nye, G. P., Wu, Y., Choe, C., Reade, W., participants, E., & Das, R.
Venue
bioRxiv (Cold Spring Harbor Laboratory)
Publisher
openRxiv
Published
2024-02-27
OpenAlex
W4392236160
Cited by
34
References
14
Type
posted content
Language
en
Open access
green

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Ribonanza: deep learning of RNA structure through dual crowdsourcing. https://app.cochat.ai/papers/10.1101/2024.02.24.581671
The paper
He, S., Huang, R., Townley, J., Kretsch, R. C., Karagianes, T. G., Cox, D. B. T., Blair, H., Penzar, D., Vyaltsev, V., Aristova, E., Zinkevich, A., Bakulin, A., Sohn, H., Krstevski, D., Fukui, T., Tatematsu, F., Uchida, Y., Jang, D., Lee, J. S., . . . Das, R. (2024). Ribonanza: deep learning of RNA structure through dual crowdsourcing. bioRxiv (Cold Spring Harbor Laboratory). https://doi.org/10.1101/2024.02.24.581671

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.