Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

PROTEOMICS

Deep learning adds an extra dimension to peptide fragmentation

Nature Methods volume 16, pages 469–470 (2019)Cite this article

Subjects

The interpretation of fragmentation patterns in tandem mass spectrometry is crucial for peptide sequencing, but the relative intensities of these patterns are difficult to predict computationally. Two groups have applied deep neural networks to address this long-standing problem in the proteomics field, extending theoretical spectra with an additional dimension of high-accuracy fragment ion intensities.

Liquid chromatography coupled with tandem mass spectrometry (LC-MS/MS) is a workhorse in bottom-up proteomics studies, capable of sequencing tens of thousands of peptide precursors per hour. All of MS-based proteomics rests on the interpretability of peptide fragmentation; however, understanding and predictive ability of peptide fragmentation have been severely lacking so far. In this issue, Tiwary et al.1 and Gessulat et al.2 report substantial improvements in the accurate prediction of fragment ion spectra by deep neural networks. Although more work is required to extend these models and to clarify how they might best be applied, it is likely that they will soon become a standard component of the proteomics data analysis pipeline.

This is a preview of subscription content, access via your institution

Relevant articles

Open Access articles citing this article.

Access options

Buy article

Get time limited or full article access on ReadCube.

$32.00

Buy

All prices are NET prices.

Fig. 1: Deep neural networks can predict the fragmentation pattern of a peptide from its amino acid sequence alone.

References

  1. Tiwary, S. et al. Nat. Methods https://doi.org/10.1038/s41592-019-0427-6 (2019).

  2. Gessulat, S. et al. Nat. Methods https://doi.org/10.1038/s41592-019-0426-7 (2019).

  3. Aebersold, R. & Mann, M. Nature 537, 347–355 (2016).

    Article  CAS  Google Scholar 

  4. Elias, J. E., Gibbons, F. D., King, O. D., Roth, F. P. & Gygi, S. P. Nat. Biotechnol. 22, 214–219 (2004).

    Article  CAS  Google Scholar 

  5. Degroeve, S. & Martens, L. Bioinformatics 29, 3199–3203 (2013).

    Article  CAS  Google Scholar 

  6. Zhou, X.-X. et al. Anal. Chem. 89, 12690–12697 (2017).

    Article  CAS  Google Scholar 

  7. Tran, N. H., Zhang, X., Xin, L., Shan, B. & Li, M. Proc. Natl. Acad. Sci. USA 114, 8247–8252 (2017).

    Article  CAS  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Donnelly Centre, University of Toronto, Toronto, Ontario, Canada

    Hannes L. Röst

Authors
  1. Hannes L. Röst
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hannes L. Röst.

Ethics declarations

Competing interests

The author declares no competing interests.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Röst, H.L. Deep learning adds an extra dimension to peptide fragmentation. Nat Methods 16, 469–470 (2019). https://doi.org/10.1038/s41592-019-0428-5

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s41592-019-0428-5

This article is cited by

Search

Advanced search

Quick links

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