CoChat
Sign Up
PreprintCited by 36Epigenetics and DNA MethylationGenomics and Phylogenetic StudiesRNA modifications and cancer

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

Rockfish: A Transformer-based Model for Accurate 5-Methylcytosine Prediction from Nanopore Sequencing

Open access
Stanojević, Dominik, Li, Zhe, Foo, Roger, Šikić, Mile·2022·Nature Communications
DOI 10.1101/2022.11.11.513492PMC PMC11222435

Preprint — published as 10.1038/s41467-024-49847-0 · Paper page

Open this paper in CoChat — free accountOpen PDF

Abstract

DNA methylation plays a crucial role in various biological processes, including cell differentiation, ageing, and cancer development. The most important methylation in mammals is 5-methylcytosine (5mC) which is present in the context of CpG dinucleotides. Sequencing methods such as whole-genome bisulfite sequencing (WGBS) successfully detect 5mC DNA modifications. However, they suffer from the serious drawbacks of short read lengths and might introduce an amplification bias. Here we present Rockfish, a deep learning algorithm that significantly improves read-level 5mC detection by using Nanopore sequencing. Compared to other methods based on Nanopore sequencing, there is an increase in the single-base accuracy and the F1 measure of up to 5% and 12%, respectively. Furthermore, Rockfish shows a high correlation with WGBS and requires lower read depth while being computationally efficient. We deem that Rockfish is broadly applicable to study 5mC methylation in diverse organisms and disease systems to yield biological insights.

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 · 10.1101/2022.11.11.513492

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: 72

  1. 1983, Tissue-specific differences in DNA methylation in various mammals, In: Biochimica et Biophysica Acta (BBA)-Gene Structure and Expression, 740, 212
  2. 1987, CpG islands in vertebrate genomes, In: Journal of molecular biology, 196, 261
  3. 2002, DNA methylation patterns and epigenetic memory, In: Genes & development, 16, 6
  4. 2005, Eukaryotic cytosine methyltransferases, In: Annual review of biochemistry, 74, 481
  5. 2012, Functions of DNA methylation: islands, start sites, gene bodies and beyond, In: Nature Reviews Genetics, 13, 484
  6. 2009, The human colon cancer methylome shows similar hypo-and hypermethylation at conserved tissue-specific CpG island shores, In: Nature genetics, 41, 178
  7. 2011, CTCF-promoted RNA polymerase II pausing links DNA methylation to splicing, In: Nature, 479, 74
  8. 2015, DNA methylation, its mediators and genome integrity, In: International journal of biological sciences, 11, 604
  9. 1975, X inactivation, differentiation, and DNA methylation, In: Cytogenetic and Genome Research, 14, 9
  10. 1997, Cytosine methylation and the ecology of intragenomic parasites, In: Trends in genetics, 13, 335
  11. 1993, Role for DNA methylation in genomic imprinting, In: Nature, 366, 362
  12. 2010, Interplay between DNA methylation and transcription factor availability: implications for developmental activation of the mouse Myogenin gene, In: Molecular and cellular biology, 30, 3805
  13. 2009, Cancer DNA methylation: molecular mechanisms and clinical implications, In: Clinical Cancer Research, 15, 3927
  14. 2018, Environmental influences on the epigenome: exposure-associated DNA methylation in human populations, In: Annu Rev Public Health, 39, 309
  15. 2009, Extensive demethylation of repetitive elements during seed development underlies gene imprinting, In: Science, 324, 1447
  16. 2008, High-resolution mapping of DNA hypermethylation and hypomethylation in lung cancer, In: Proceedings of the National Academy of Sciences, 105, 252
  17. 2008, A Bayesian deconvolution strategy for immunoprecipitation-based DNA methylome analysis, In: Nature biotechnology, 26, 779
  18. 2006, Evaluation of a quantitative DNA methylation analysis technique using methylation-sensitive/dependent restriction enzymes and real-time PCR, In: Epigenetics, 1, 146
  19. 2018, Profiling DNA methylation based on next-generation sequencing approaches: new insights and clinical applications, In: Genes, 9, 429
  20. 1992, A genomic sequencing protocol that yields a positive display of 5-methylcytosine residues in individual DNA strands, In: Proceedings of the National Academy of Sciences, 89, 1827
  21. 1980, Comparison of bisulfite modification of 5-methyldeoxycytidine and deoxycytidine residues, In: Nucleic acids research, 8, 4777
  22. 2011, High density DNA methylation array with single CpG site resolution, In: Genomics, 98, 288
  23. 2011, Repetitive elements may comprise over two-thirds of the human genome, In: PLoS genetics, 7, e1002384
  24. 2007, Degradation of DNA by bisulfite treatment, In: Bioorganic & medicinal chemistry letters, 17, 1912
  25. 2021, Genome-wide detection of cytosine methylation by single molecule realtime sequencing, In: Proceedings of the National Academy of Sciences, 118, e2019768118
  26. Peng Ni et al. “DNA 5-methylcytosine detection and methylation phasing using PacBio circular consensus sequencing”. In: bioRxiv (2022).
  27. 2020, Comparison of the two up-to-date sequencing technologies for genome assembly: HiFi reads of Pacific Biosciences Sequel II system and ultralong reads of Oxford Nanopore, In: Gigascience, 9, giaa123
  28. 2018, Nanopore sequencing and assembly of a human genome with ultra-long reads, In: Nature biotechnology, 36, 338
  29. 2016, Three decades of nanopore sequencing, In: Nature biotechnology, 34, 518
  30. 10.1038/nmeth.4184 · DOI
  31. 2022, Direct identification of A-to-I editing sites with nanopore native RNA sequencing, In: Nature Methods, 19, 833
  32. 10.1101/094672 · DOI
  33. 10.1186/s12864-018-5372-8 · DOI
  34. 10.1038/nmeth.4189 · DOI · Paper page
  35. 10.1093/bioinformatics/btz276 · DOI
  36. 10.1038/s41467-019-10168-2 · DOI
  37. Yang Liu et al. “DNA methylation calling tools for Oxford Nanopore sequencing: a survey and human epigenome-wide evaluation”. In: Genome Biology 22.295 (2021). doi: https://doi.org/10.1186/s13059-021-02510-z. · DOI
  38. 2004, The history of cancer epigenetics, In: Nature Reviews Cancer, 4, 143
  39. 2021, Megabase-scale methylation phasing using nanopore long reads and NanoMethPhase, In: Genome biology, 22, 1
  40. 2021, phasebook: haplotype-aware de novo assembly of diploid genomes from long reads, In: Genome biology, 22, 1
  41. 10.1186/S13059-020-02000-8/FIGURES/6 · DOI
  42. 2001, Genomic imprinting: parental influence on the genome, In:Nature Reviews Genetics, 2, 21
  43. 2015, Landscape of DNA methylation on the X chromosome reflects CpG density, functional chromatin state and X-chromosome inactivation, In: Human molecular genetics, 24, 1528
  44. 2018, Consistent inverse correlation between DNA methylation of the first intron and gene expression across tissues and species, In: Epigenetics & chromatin, 11, 1
  45. 2017, Cytosine modifications modulate the chromatin architecture of transcriptional enhancers, In: Genome research, 27, 947
  46. 2011, Epigenome-wide association studies for common human diseases, In: Nature Reviews Genetics, 12, 529
  47. 2021, Potential reversal of epigenetic age using a diet and lifestyle intervention: a pilot randomized clinical trial, In: Aging (Albany NY), 13, 9419
  48. 2011, Cognitive neuroepigenetics: a role for epigenetic mech-anisms in learning and memory, In: Neurobiology of learning and memory, 96, 2
  49. 2015, Exercise training and DNA methylation in humans, In: Acta Physiologica, 213, 39
  50. 10.1093/bioinformatics/bty191 · DOI · Paper page
  51. 10.1126/science.abj6987 · DOI · Paper page
  52. Ashish Vaswani et al. “Attention is All you Need”. In: Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA. Ed. by Isabelle Guyon et al. 2017, pp. 5998–6008. url: https://proceedings.neurips.cc/paper/2017/hash/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html.
  53. 2020, In: Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13-18 July 2020, Virtual Event, 119, 10524
  54. 2016, Layer Normalization, In: CoRR abs/1607.06450 · arXiv
  55. 2016, Bridging Nonlinearities and Stochastic Regularizers with Gaussian Error Linear Units, In: CoRR abs/1606.08415 · arXiv
  56. 2022, Formal Algorithms for Transformers, In: arXiv preprint
  57. 10.18653/v1/n19-1423 · DOI · Paper page
  58. Alexei Baevski et al. “wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations”. In: Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual. Ed. by Hugo Larochelle et al. 2020. url: https://proceedings.neurips.cc/paper/2020/hash/92d1e1eb1cd6f9fba3227870bb6d7f07-Abstract.html.
  59. Diederik P. Kingma and Jimmy Ba . “Adam: A Method for Stochastic Optimization”. In: 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings. Ed. by Yoshua Bengio and Yann LeCun. 2015. url: http://arxiv.org/abs/1412.6980. · arXiv
  60. Ilya Loshchilov and Frank Hutter . “Decoupled Weight Decay Regularization”. In: 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019. OpenReview.net, 2019. url: https://openreview.net/forum?id=Bkg6RiCqY7.
  61. 2011, Scikit-learn: Machine Learning in Python, In: Journal of Machine Learning Research, 12, 2825
  62. 2011, Bismark: a flexible aligner and methylation caller for Bisulfite-Seq applications, In: bioinformatics, 27, 1571
  63. 10.1093/bioinformatics/btq033 · DOI · Paper page
  64. 2011, Genomic DNA extraction from whole blood stored from 15-to 30-years at-20 C by rapid phenol–chloroform protocol: A useful tool for genetic epidemiology studies, In: Molecular and cellular probes, 25, 44
  65. 2018, A rapid and efficient DNA extraction protocol from fresh and frozen human blood samples, In: Journal of clinical laboratory analysis, 32, e22181
  66. Matthew Ackers-Johnson , Roger S Foo , and Davor Pavlovic . “Mouse cardiomyocyte isola-tion: Filling the age gaps”. In: Journal of molecular and cellular cardiology (2022), S0022–2828. · DOI
  67. Matthew Ackers-Johnson and Roger S Foo . “Langendorff-free isolation and propagation of adult mouse cardiomyocytes”. In: Mouse Cell Culture. Springer, 2019, pp. 193–204. · DOI
  68. 2015, Distilling the Knowledge in a Neural Network, In: CoRR abs/1503.02531 · arXiv
  69. 2018, Nanopore sequencing and assembly of a human genome with ultra-long reads, In: Nature Biotechnology, 36, 338
  70. Mark Chaisson et al. “Multi-platform discovery of haplotype-resolved structural variation in human genomes”. In: Nature Communications 10.1784 (2019). doi: https://doi.org/10.1038/s41467-018-08148-z. · DOI · Paper page
  71. Qian Liu et al. “Detection of DNA base modifications by deep recurrent neural network on Oxford Nanopore sequencing data”. In: Nature Communications 10.2449 (2019). doi: https://doi.org/10.1038/s41467-019-10168-2. · DOI
  72. 10.1093/nar/gkv1160 · DOI

Metadata

Authors
Stanojević, D., Li, Z., Foo, R., & Šikić, M.
Affiliations
  • Agency for Science, Technology and Research (SG)
  • National University of Singapore (SG)
Corresponding author
Šikić, Mile
ORCID
Venue
Nature Communications
Publisher
openRxiv
Published
2022-11-14
Volume
15
Issue
1
Pages
5580-5580
ISSN
2041-1723 (ISSN-L)
DOI
10.1101/2022.11.11.513492
PMC
PMC11222435
OpenAlex
W4400292335
Cited by
36
References
1
Citations by year
2026: 12 · 2025: 20 · 2024: 4
FWCI
4.90
Type
journal article
Language
en
Open access
Licence
cc-by
Locations
  • Nature Communications (publishedVersion, cc-by)
  • bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nd)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • RePEc: Research Papers in Economics (submittedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • Agency for Science, Technology and Research (C210812037)
  • Hrvatska Zaklada za Znanost (IP-2018, IP-2018-01-5886, IP-2018-01)
  • Genome Institute of Singapore
  • National Supercomputing Centre Singapore
Topics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Epigenetics and DNA Methylation
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Genomics and Phylogenetic Studies
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › RNA modifications and cancer
Keywords
DNA methylation, nanopore sequencing, transformer models, CpG methylation, promoter methylation, rockfish
MeSH terms
Whole Genome Sequencing, Deep Learning, Nanopore Sequencing, Algorithms, Animals, Humans, Sulfites, Sequence Analysis, DNA, CpG Islands, DNA Methylation, 5-Methylcytosine, Mice

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