CoChat
Sign Up
PreprintCited by 20RNA and protein synthesis mechanismsProtein Structure and DynamicsDNA and Nucleic Acid Chemistry

The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.

Designing Molecular RNA Switches with Restricted Boltzmann Machines

Open access
Fernandez-de-Cossio-Diaz, Jorge, Hardouin, Pierre, du Moutier, Francois-Xavier Lyonnet, Di Gioacchino, Andrea, Marchand, Bertrand, Ponty, Yann, Sargueil, Bruno, Monasson, Rémi, Cocco, Simona·2023·Nature Communications
DOI 10.1101/2023.05.10.540155PMC PMC12714719

Preprint — published as 10.1038/s41467-025-66265-y · Paper page

Open this paper in CoChat — free accountOpen PDF

Abstract

Riboswitches are structured allosteric RNA molecules that change conformation upon metabolite binding, triggering a regulatory response. Here we focus on the de novo design of riboswitch-like aptamers, the core part of the riboswitch undergoing structural changes. We use Restricted Boltzmann machines (RBM) to learn generative models from homologous sequence data. We first verify, on four different riboswitch families, that RBM-generated sequences correctly capture the conservation, covariation and diversity of natural aptamers. The RBM model is then used to design new SAM-I riboswitch aptamers. To experimentally validate the properties of the structural switch in designed molecules, we resort to chemical probing (SHAPE and DMS), and develop a tailored analysis pipeline adequate for high-throughput tests of diverse sequences. We probe a total of 476 RBM-designed and 201 natural sequences. Designed molecules with high RBM scores, with 20% to 40% divergence from any natural sequence, display ≈ 30% success rate of responding to SAM with a structural switch similar to their natural counterparts. We show how the capability of the designed molecules to switch conformation is connected to fine energetic features of their structural components.

Overview

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

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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

Integrity signals

Registry

Crossref · 10.1101/2023.05.10.540155

Cites

1 of 1 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.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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

Flagged first, then by citations

Research works printed but not linked: 90

  1. 2020, A deep learning approach to programmable rna switches, Nature communications, 11, 5057, 10.1038/s41467-020-18677-1 · DOI
  2. 10.1073/pnas.0308014101 · DOI
  3. 2011, Recognition of S-adenosylmethionine by riboswitches, Wiley Interdisciplinary Reviews: RNA, 2, 299, 10.1002/wrna.63 · DOI
  4. 10.1261/rna.079427.122 · DOI
  5. 10.1137/141000671. arXiv:1411.1607v4 · DOI · Paper page
  6. 10.1093/nar/gkz216 · DOI
  7. 10.7554/eLife.85126 · DOI
  8. 2021, RBM-MHC: A semi-supervised machine-learning method for sample-specific prediction of antigen presentation by HLA-I alleles, Cell systems, 12, 195, 10.1016/j.cels.2020.11.005 · DOI
  9. 10.1261/rna.061945.117 · DOI
  10. 10.1093/nar/gkae289 · DOI
  11. 10.1186/1471-2105-3-1 · DOI
  12. 2015, Creating small transcription activating rnas, Nature chemical biology, 11, 214, 10.1038/nchembio.1737 · DOI
  13. 2022, Statistical-physics approaches to rna molecules, families and networks, arXiv preprint
  14. 10.1088/1361-6633/aa9965 · DOI
  15. 2021, Makie.jl: Flexible high-performance data visualization for julia, Journal of Open Source Software, 6, 3349, 10.21105/joss.03349 · DOI
  16. 10.1093/bioinformatics/btp250 · DOI
  17. 2021, Progress toward shape constrained computational prediction of tertiary interactions in rna structure, Non-coding RNA, 7, 71, 10.3390/ncrna7040071 · DOI
  18. 10.1093/nar/gkv932 · DOI
  19. 10.1016/j.biochi.2012.02.009 · DOI
  20. 2022, Generative and interpretable machine learning for aptamer design and analysis of in vitro sequence selection, PLoS computational biology, 18, e1010561, 10.1371/journal.pcbi.1010561 · DOI · Paper page
  21. R. Durbin , S. R. Eddy , A. Krogh , and G. Mitchison . Biological sequence analysis: probabilistic models of proteins and nucleic acids. Cambridge university press, 1998. · DOI
  22. 2014, Computational analysis of conserved rna secondary structure in transcriptomes and genomes, Annual review of biophysics, 43, 433, 10.1146/annurev-biophys-051013-022950 · DOI
  23. 10.1093/molbev/msaa204 · DOI
  24. 10.1017/S1355838201000863 · DOI
  25. 2018, Tuning the performance of synthetic riboswitches using machine learning, ACS synthetic biology, 8, 34
  26. 10.1046/j.1365-2958.1998.01105.x · DOI
  27. 10.1016/S0959-440X(02)00339-1 · DOI · Paper page
  28. 10.1073/pnas.1219988110 · DOI
  29. 10.1261/rna.079926.123 · DOI
  30. 10.1021/ar200035g · DOI
  31. P. Hardouin , F.-X. Lyonnet du Moutier , and B. Sargueil . SHAPE Probing to Screen Computationally Designed RNA, pages 177–191. Springer US, New York, NY, 2025. · DOI
  32. 10.1093/nar/gks978 · DOI
  33. 2011, Molecular insights into the ligand-controlled organization of the sam-i riboswitch, Nature chemical biology, 7, 384, 10.1038/nchembio.563 · DOI
  34. G. E. Hinton . A practical guide to training restricted boltzmann machines. In Neural networks: Tricks of the trade, pages 599–619. Springer, 2012. · DOI · Paper page
  35. 10.1016/j.jmb.2022.167631 · DOI
  36. 2022, Generative aptamer discovery using raptgen, Nature Computational Science, 2, 378, 10.1038/s43588-022-00249-6 · DOI
  37. 2021, Rna diversification by a self-reproducing ribozyme revealed by deep sequencing and kinetic modelling, Chemical Communications, 57, 7517, 10.1039/D1CC02290C · DOI
  38. 2018, Non-coding rna analysis using the rfam database, Current protocols in bioinformatics, 62, e51, 10.1002/cpbi.51 · DOI
  39. 10.1093/NAR/GKAA1047 · DOI
  40. 10.1016/j.tibs.2022.08.009 · DOI
  41. 10.1073/pnas.1313039111 · DOI
  42. 10.1186/1748-7188-6-1 · DOI
  43. 10.1016/j.jmb.2010.09.059 · DOI
  44. D. J. MacKay . Information theory, inference and learning algorithms. Cambridge university press, 2003.
  45. 2023, Computational design of novel cas9 pam-interacting domains using evolution-based modelling and structural quality assessment, PLOS Computational Biology, 19, e1011621, 10.1371/journal.pcbi.1011621 · DOI · Paper page
  46. 10.1126/science.1100829 · DOI
  47. 2015, In vitro selection for small-molecule-triggered strand displacement and riboswitch activity, ACS Synthetic Biology, 4, 1144, 10.1021/acssynbio.5b00054 · DOI
  48. 10.1016/j.immuno.2023.100024 · DOI
  49. 10.1016/0022-2836(90)90386-Z · DOI
  50. 10.1093/nar/gkad522 · DOI
  51. 10.1038/nature04819 · DOI
  52. 10.1073/pnas.1111471108 · DOI · Paper page
  53. 10.1093/bioinformatics/btt509 · DOI
  54. 10.1093/bioinformatics/btt509 · DOI
  55. 2024, Mechanistic analysis of riboswitch lig- and interactions provides insights into pharmacological control over gene expression, Nature Communications, 15, 8173, 10.1038/s41467-024-52235-3 · DOI
  56. R. Pearce , G. S. Omenn , and Y. Zhang . De novo rna tertiary structure prediction at atomic resolution using geometric potentials from deep learning. bioRxiv, pages 2022–05, 2022. · DOI
  57. 2014, Common themes and differences in SAM recognition among SAM riboswitches, Biochimica et Biophysica Acta (BBA)-Gene Regulatory Mechanisms, 1839, 931, 10.1016/j.bbagrm.2014.05.013 · DOI
  58. 2023, Sequence similarity governs generalizability of de novo deep learning models for rna secondary structure prediction, PLOS Computational Biology, 19, e1011047, 10.1371/journal.pcbi.1011047 · DOI
  59. 2014, In Methods in enzymology, 549, 165
  60. 2020, Rna structure prediction using positive and negative evolutionary information, PLoS computational biology, 16, e1008387, 10.1371/journal.pcbi.1008387 · DOI
  61. 10.1261/rna.030049.111 · DOI · Paper page
  62. 2023, How flexibility can enhance catalysis, Physical Review Letters, 131, 088401, 10.1103/PhysRevLett.131.088401 · DOI
  63. 10.1186/gb-2004-5-2-r12 · DOI · Paper page
  64. 2017, Cooperation between magnesium and metabolite controls collapse of the sam-i riboswitch, Biophysical journal, 113, 348, 10.1016/j.bpj.2017.06.044 · DOI
  65. 10.1126/science.aba3304 · DOI · Paper page
  66. 2020, IPANEMAP: integrative probing analysis of nucleic acids empowered by multiple accessibility profiles, Nucleic acids research, 48, 8276, 10.1093/nar/gkaa607 · DOI
  67. D. H. Sanduni Deenalattha , C. P. Jurich , B. Lange , D. Armstrong , K. Nein , and J. D. Yesselman . Characterizing 3d rna structural features from dms reactivity. bioRxiv, 2025. · DOI
  68. 10.1021/ja805203w · DOI
  69. 2019, Selection of sequence motifs and generative hopfield-potts models for protein families, Physical Review E, 100, 032128, 10.1103/PhysRevE.100.032128 · DOI
  70. 2014, Rna motif discovery by shape and mutational profiling (shape-map), Nature methods, 11, 959, 10.1038/nmeth.3029 · DOI
  71. B. W. Silverman . Density estimation for statistics and data analysis, volume 26. CRC press, 1986.
  72. C. D. Stoddard and R. T. Batey . Mix-and-match riboswitches, 2006. · DOI
  73. 10.1016/j.str.2010.04.006 · DOI
  74. 10.1126/science.1130716 · DOI
  75. 10.1126/science.1159519 · DOI
  76. 10.1093/nar/gks1283 · DOI
  77. S. Sumi , M. Hamada , and H. Saito . Deep generative design of rna family sequences. Nature Methods, pages 1–9, 2024. · DOI
  78. 10.1093/bioinformatics/btac415 · DOI
  79. 10.1093/BIOINFORMATICS/BTZ921 · DOI
  80. 2007, Dms footprinting of structured rnas and rna–protein complexes, Nature protocols, 2, 2608, 10.1038/nprot.2007.380 · DOI
  81. 10.1126/science.abe5650 · DOI
  82. 10.1073/pnas.1312918111 · DOI
  83. 10.7554/eLife.39397 · DOI
  84. 10.1093/nar/gkp892 · DOI · Paper page
  85. 10.1073/pnas.2112677119 · DOI
  86. 10.1016/j.str.2020.05.011 · DOI
  87. 10.1093/nar/gkq946 · DOI
  88. 10.1073/pnas.0805923106 · DOI · Paper page
  89. 10.1016/j.cell.2016.03.030 · DOI · Paper page
  90. 10.1007/BF02459506 · DOI

Metadata

Authors
Fernandez-de-Cossio-Diaz, J., Hardouin, P., du Moutier, F.-X. L., Di Gioacchino, A., Marchand, B., Ponty, Y., Sargueil, B., Monasson, R., & Cocco, S.
Affiliations
Centre National de la Recherche Scientifique (FR)
Corresponding author
  • Sargueil, Bruno
  • Monasson, Rémi
  • Cocco, Simona
ORCID
Venue
Nature Communications
Publisher
openRxiv
Published
2023-05-12
Volume
16
Issue
1
Pages
11223-11223
ISSN
2041-1723 (ISSN-L)
DOI
10.1101/2023.05.10.540155
PMC
PMC12714719
OpenAlex
W4417464481
Cited by
20
References
1
Citations by year
2026: 10 · 2025: 4 · 2024: 5 · 2023: 1
FWCI
4.21
Type
journal article
Language
en
Open access
Licence
Locations
  • Nature Communications (publishedVersion, cc-by-nc-nd)
  • bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by)
  • Research Square (acceptedVersion, cc-by)
  • PubMed (publishedVersion)
  • PubMed Central (publishedVersion, cc-by-nc-nd)
  • HAL (submittedVersion, other-oa)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • Greater South Information System
Funders
ANR (19-CE30-0021-01, 19-CE30-0021-03, 20-CE12-0026-02, 19-CE45-0023-02, 21-CE45-0034-03)
Topics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › RNA and protein synthesis mechanisms
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Protein Structure and Dynamics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › DNA and Nucleic Acid Chemistry
Keywords
riboswitches, restricted Boltzmann machine, generative models, SAM-I riboswitch, SHAPE probing, covariation analysis
MeSH terms
Models, Molecular, Nucleic Acid Conformation, RNA, Aptamers, Nucleotide, Riboswitch

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