Deep learning adds an extra dimension to peptide fragmentation

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.

Access options

Rent or Buy article

Get time limited or full article access on ReadCube.


All prices are NET prices.

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


  1. 1.

    Tiwary, S. et al. Nat. Methods (2019).

  2. 2.

    Gessulat, S. et al. Nat. Methods (2019).

  3. 3.

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

    CAS  Article  Google Scholar 

  4. 4.

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

    CAS  Article  Google Scholar 

  5. 5.

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

    CAS  Article  Google Scholar 

  6. 6.

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

    CAS  Article  Google Scholar 

  7. 7.

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

    CAS  Article  Google Scholar 

Download references

Author information



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).

Download citation

Further reading