Deep learning the collisional cross sections of the peptide universe from a million experimental values

Research output: Contribution to journal › Journal article › Research › peer-review

Standard

Deep learning the collisional cross sections of the peptide universe from a million experimental values. / Meier, Florian; Köhler, Niklas D.; Brunner, Andreas David; Wanka, Jean Marc H.; Voytik, Eugenia; Strauss, Maximilian T.; Theis, Fabian J.; Mann, Matthias.

In: Nature Communications, Vol. 12, 1185, 2021.

Research output: Contribution to journal › Journal article › Research › peer-review

Harvard

Meier, F, Köhler, ND, Brunner, AD, Wanka, JMH, Voytik, E, Strauss, MT, Theis, FJ & Mann, M 2021, 'Deep learning the collisional cross sections of the peptide universe from a million experimental values', Nature Communications, vol. 12, 1185. https://doi.org/10.1038/s41467-021-21352-8

APA

Meier, F., Köhler, N. D., Brunner, A. D., Wanka, J. M. H., Voytik, E., Strauss, M. T., Theis, F. J., & Mann, M. (2021). Deep learning the collisional cross sections of the peptide universe from a million experimental values. Nature Communications, 12, [1185]. https://doi.org/10.1038/s41467-021-21352-8

Vancouver

Meier F, Köhler ND, Brunner AD, Wanka JMH, Voytik E, Strauss MT et al. Deep learning the collisional cross sections of the peptide universe from a million experimental values. Nature Communications. 2021;12. 1185. https://doi.org/10.1038/s41467-021-21352-8

Author

Meier, Florian ; Köhler, Niklas D. ; Brunner, Andreas David ; Wanka, Jean Marc H. ; Voytik, Eugenia ; Strauss, Maximilian T. ; Theis, Fabian J. ; Mann, Matthias. / Deep learning the collisional cross sections of the peptide universe from a million experimental values. In: Nature Communications. 2021 ; Vol. 12.

Bibtex

@article{66c758af07734d93961d31aadae753f1,
title = "Deep learning the collisional cross sections of the peptide universe from a million experimental values",
abstract = "The size and shape of peptide ions in the gas phase are an under-explored dimension for mass spectrometry-based proteomics. To investigate the nature and utility of the peptide collisional cross section (CCS) space, we measure more than a million data points from whole-proteome digests of five organisms with trapped ion mobility spectrometry (TIMS) and parallel accumulation-serial fragmentation (PASEF). The scale and precision (CV < 1%) of our data is sufficient to train a deep recurrent neural network that accurately predicts CCS values solely based on the peptide sequence. Cross section predictions for the synthetic ProteomeTools peptides validate the model within a 1.4% median relative error (R > 0.99). Hydrophobicity, proportion of prolines and position of histidines are main determinants of the cross sections in addition to sequence-specific interactions. CCS values can now be predicted for any peptide and organism, forming a basis for advanced proteomics workflows that make full use of the additional information.",
author = "Florian Meier and K{\"o}hler, {Niklas D.} and Brunner, {Andreas David} and Wanka, {Jean Marc H.} and Eugenia Voytik and Strauss, {Maximilian T.} and Theis, {Fabian J.} and Matthias Mann",
year = "2021",
doi = "10.1038/s41467-021-21352-8",
language = "English",
volume = "12",
journal = "Nature Communications",
issn = "2041-1723",
publisher = "nature publishing group",

}

RIS

TY - JOUR

T1 - Deep learning the collisional cross sections of the peptide universe from a million experimental values

AU - Meier, Florian

AU - Köhler, Niklas D.

AU - Brunner, Andreas David

AU - Wanka, Jean Marc H.

AU - Voytik, Eugenia

AU - Strauss, Maximilian T.

AU - Theis, Fabian J.

AU - Mann, Matthias

PY - 2021

Y1 - 2021

N2 - The size and shape of peptide ions in the gas phase are an under-explored dimension for mass spectrometry-based proteomics. To investigate the nature and utility of the peptide collisional cross section (CCS) space, we measure more than a million data points from whole-proteome digests of five organisms with trapped ion mobility spectrometry (TIMS) and parallel accumulation-serial fragmentation (PASEF). The scale and precision (CV < 1%) of our data is sufficient to train a deep recurrent neural network that accurately predicts CCS values solely based on the peptide sequence. Cross section predictions for the synthetic ProteomeTools peptides validate the model within a 1.4% median relative error (R > 0.99). Hydrophobicity, proportion of prolines and position of histidines are main determinants of the cross sections in addition to sequence-specific interactions. CCS values can now be predicted for any peptide and organism, forming a basis for advanced proteomics workflows that make full use of the additional information.

AB - The size and shape of peptide ions in the gas phase are an under-explored dimension for mass spectrometry-based proteomics. To investigate the nature and utility of the peptide collisional cross section (CCS) space, we measure more than a million data points from whole-proteome digests of five organisms with trapped ion mobility spectrometry (TIMS) and parallel accumulation-serial fragmentation (PASEF). The scale and precision (CV < 1%) of our data is sufficient to train a deep recurrent neural network that accurately predicts CCS values solely based on the peptide sequence. Cross section predictions for the synthetic ProteomeTools peptides validate the model within a 1.4% median relative error (R > 0.99). Hydrophobicity, proportion of prolines and position of histidines are main determinants of the cross sections in addition to sequence-specific interactions. CCS values can now be predicted for any peptide and organism, forming a basis for advanced proteomics workflows that make full use of the additional information.

U2 - 10.1038/s41467-021-21352-8

DO - 10.1038/s41467-021-21352-8

M3 - Journal article

C2 - 33608539

AN - SCOPUS:85101297275

VL - 12

JO - Nature Communications

JF - Nature Communications

SN - 2041-1723

M1 - 1185

ER -

ID: 258499190