Elucidation of DNA methylation on N6-adenine with deep learning


Research on DNA methylation on N6-adenine (6mA) in eukaryotes has received much recent attention. Recent studies have generated a large amount of 6mA genomic data, yet the role of DNA 6mA in eukaryotes remains elusive, or even controversial. We argue that the sparsity of DNA 6mA in eukaryotes, the limitations of current biotechnologies for 6mA detection and the sophistication of the 6mA regulatory mechanism together pose great challenges for elucidation of DNA 6mA. To exploit existing 6mA genomic data and address this challenge, here we develop a deep-learning-based algorithm for predicting potential DNA 6mA sites de novo from sequence at single-nucleotide resolution, with application to three representative model organisms, Arabidopsis thaliana, Drosophila melanogaster and Escherichia coli. Extensive experiments demonstrate the accuracy of our algorithm and its superior performance compared with conventional k-mer-based approaches. Furthermore, our saliency maps-based context analysis protocol reveals interesting cis-regulatory patterns around the 6mA sites that are missed by conventional motif analysis. Our proposed analytical tools and findings will help to elucidate the regulatory mechanisms of 6mA and benefit the in-depth exploration of their functional effects. Finally, we offer a complete catalogue of potential 6mA sites based on in silico whole-genome prediction.

Access options

Rent or Buy article

Get time limited or full article access on ReadCube.


All prices are NET prices.

Fig. 1: DNA 6mA site prediction.
Fig. 2: t-SNE visualization of the last hidden layer representations of methylations.
Fig. 3: ROC curves for D. melanogaster embryos in different developmental stages.
Fig. 4: DNA motifs and loci revealed by SM-CAP.
Fig. 5: Comparison of DeepM6A-based predictive probability of peak regions and randomly selected adenines.

Data availability

The SMART-seq data that support the findings of this study are available from GitHub (https://github.com/tanfei2007/DeepM6A/tree/master/Data). The sequencing data for A. thaliana are available on the GEO database under accession no. GSE149060. The data for different stages of D. melanogaster embryos are available on the GEO database under accession no. GSE86795. The raw data for 6mA-DNA-IP-Seq of D. melanogaster are available from https://trace.ddbj.nig.ac.jp/DRASearch/study?acc=SRP055483.

Code availability

The custom computer code is available from GitHub (https://github.com/tanfei2007/DeepM6A/tree/master/Code) under https://doi.org/10.5281/zenodo.3887349.


  1. 1.

    Heyn, H. & Esteller, M. An adenine code for DNA: a second life for N 6-methyladenine. Cell 161, 710–713 (2015).

    Article  Google Scholar 

  2. 2.

    Luo, G.-Z., Blanco, M. A., Greer, E. L., He, C. & Shi, Y. DNA N 6-methyladenine: a new epigenetic mark in eukaryotes? Nat. Rev. Mol. Cell Biol. 16, 705–710 (2015).

    Article  Google Scholar 

  3. 3.

    Zeng, H. & Gifford, D. K. Predicting the impact of non-coding variants on DNA methylation. Nucleic Acids Res 45, e99 (2017).

    Article  Google Scholar 

  4. 4.

    Feng, S. et al. Conservation and divergence of methylation patterning in plants and animals. Proc. Natl Acad. Sci. USA 107, 8689–8694 (2010).

    Article  Google Scholar 

  5. 5.

    Wu, T. P. et al. DNA methylation on N 6-adenine in mammalian embryonic stem cells. Nature 532, 329–333 (2016).

    Article  Google Scholar 

  6. 6.

    Fu, Y. et al. N 6-methyldeoxyadenosine marks active transcription start sites in Chlamydomonas. Cell 161, 879–892 (2015).

    Article  Google Scholar 

  7. 7.

    Greer, E. L. et al. DNA methylation on N 6-adenine in C. elegans. Cell 161, 868–878 (2015).

    Article  Google Scholar 

  8. 8.

    Liu, J. et al. Abundant DNA 6mA methylation during early embryogenesis of zebrafish and pig. Nat. Commun. 7, 13052 (2016).

    Article  Google Scholar 

  9. 9.

    Zhang, G. et al. N 6-methyladenine DNA modification in Drosophila. Cell 161, 893–906 (2015).

    Article  Google Scholar 

  10. 10.

    Barras, F. & Marinus, M. G. The great GATC: DNA methylation in E. coli. Trends Genet. 5, 139–143 (1989).

    Article  Google Scholar 

  11. 11.

    Heinz, S. et al. Simple combinations of lineage-determining transcription factors prime cis-regulatory elements required for macrophage and B cell identities. Mol. Cell 38, 576–589 (2010).

    Article  Google Scholar 

  12. 12.

    Alipanahi, B., Delong, A., Weirauch, M. T. & Frey, B. J. Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning. Nat. Biotechnol. 33, 831–838 (2015).

    Article  Google Scholar 

  13. 13.

    Krizhevsky, A., Sutskever, I. & Hinton, G. E. ImageNet classification with deep convolutional neural networks. In Proceedings of the 25th International Conference on Neural Information Processing Systems 1097–1105 (NIPS, 2012).

  14. 14.

    Lee, D. et al. A method to predict the impact of regulatory variants from DNA sequence. Nat. Genet. 47, 955–961 (2015).

    Article  Google Scholar 

  15. 15.

    Ji, G., Wu, X., Shen, Y., Huang, J. & Li, Q. Q. A classification-based prediction model of messenger RNA polyadenylation sites. J. Theor. Biol. 265, 287–296 (2010).

    Article  Google Scholar 

  16. 16.

    Zhou, J. & Troyanskaya, O. G. Predicting effects of noncoding variants with deep learning-based sequence model. Nat. Methods 12, 931–934 (2015).

    Article  Google Scholar 

  17. 17.

    Rosenblatt, F. Principles of Neurodynamics. Perceptrons and the Theory of Brain Mechanisms (Cornell Aeronautical Lab, 1961).

  18. 18.

    Maaten, Lvd & Hinton, G. Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579–2605 (2008).

    MATH  Google Scholar 

  19. 19.

    He, S. et al. 6mA-DNA-binding factor Jumu controls maternal-to-zygotic transition upstream of Zelda. Nat. Commun. 10, 2219 (2019).

    Article  Google Scholar 

  20. 20.

    D’haeseleer, P. What are DNA sequence motifs? Nat. Biotechnol. 24, 423–425 (2006).

    Article  Google Scholar 

  21. 21.

    Bailey, T. L. & Elkan, C. Unsupervised learning of multiple motifs in biopolymers using expectation maximization. Mach. Learn. 21, 51–80 (1995).

    Google Scholar 

  22. 22.

    Liang, Z. et al. DNA N 6-adenine methylation in Arabidopsis thaliana. Dev. Cell 45, 406–416 (2018).

    Article  Google Scholar 

  23. 23.

    Feng, J., Liu, T., Qin, B., Zhang, Y. & Liu, X. S. Identifying ChIP-seq enrichment using MACS. Nat. Protoc. 7, 1728–1740 (2012).

    Article  Google Scholar 

  24. 24.

    Langmead, B. & Salzberg, S. L. Fast gapped-read alignment with Bowtie 2. Nat. Methods 9, 357–359 (2012).

    Article  Google Scholar 

  25. 25.

    Li, Z., Zhao, P. & XiaQ. Epigenetic methylations on N 6-adenine and N 6-adenosine with the same input but different output. Int. J. Mol. Sci. 20, 2931 (2019).

    Article  Google Scholar 

  26. 26.

    Musheev, M. U., Baumgartner, A., Krebs, L. & Niehrs, C. The origin of genomic N6-methyl-deoxyadenosine in mammalian cells. Nat. Chem. Biol. 16, 630–634 (2020).

    Article  Google Scholar 

  27. 27.

    He, K., Zhang, X., Ren, S. & Sun, J. Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In 2015 International Conference on Computer Vision 1026–1034 (IEEE, 2015)

  28. 28.

    Srivastava, N., Hinton, G. E., Krizhevsky, A., Sutskever, I. & Salakhutdinov, R. Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929–1958 (2014).

    MathSciNet  MATH  Google Scholar 

  29. 29.

    Zhang, Y. et al. Model-based analysis of ChIP-Seq (MACS). Genome Biol. 9, R137 (2008).

    Article  Google Scholar 

  30. 30.

    Simonyan, K., Vedaldi, A. & Zisserman, A. Deep inside convolutional networks: visualising image classification models and saliency maps. Workshop at International Conference on Learning Representations (2014).

Download references


We thank H. Liu for the partial data preprocessing. This study was supported by The Children’s Hospital of Philadelphia Endowed Chair in Genomic Research to H.H. and an Institutional Development Award to the Center for Applied Genomics from The Children’s Hospital of Philadelphia. This work was supported by Extreme Science and Engineering Discovery Environment (XSEDE) through allocation CIE160021 and CIE170034 (supported by National Science Foundation grant no. ACI-1548562).

Author information




Z.W. and H.H. conceived and supervised the project. F.T., T.T. and X.H. designed the methods and conducted the experiments with input from L.G. T.T., X.Y., B.D.G., F.M. and F.T. conducted the validation experiments. F.T., T.T., Z.W. and H.H. wrote the manuscript. All authors approved the manuscript.

Corresponding authors

Correspondence to Zhi Wei or Hakon Hakonarson.

Ethics declarations

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Supplementary Information

Supplementary Figs. 1–19, Discussion and Tables 11–13.

Reporting Summary

Supplementary Tables

Supplementary Tables 1–10 and 14–21.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Tan, F., Tian, T., Hou, X. et al. Elucidation of DNA methylation on N6-adenine with deep learning. Nat Mach Intell 2, 466–475 (2020). https://doi.org/10.1038/s42256-020-0211-4

Download citation


Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing