Sequence-to-sequence translation from mass spectra to peptides with a transformer model
Open accessThe DOI matches its Crossref record; 15 of the 15 references it cites were found in a registry or an index.
Abstract
A fundamental challenge in mass spectrometry-based proteomics is the identification of the peptide that generated each acquired tandem mass spectrum. Approaches that leverage known peptide sequence databases cannot detect unexpected peptides and can be impractical or impossible to apply in some settings. Thus, the ability to assign peptide sequences to tandem mass spectra without prior information—de novo peptide sequencing—is valuable for tasks including antibody sequencing, immunopeptidomics, and metaproteomics. Although many methods have been developed to address this problem, it remains an outstanding challenge in part due to the difficulty of modeling the irregular data structure of tandem mass spectra. Here, we describe Casanovo, a machine learning model that uses a transformer neural network architecture to translate the sequence of peaks in a tandem mass spectrum into the sequence of amino acids that comprise the generating peptide. We train a Casanovo model from 30 million labeled spectra and demonstrate that the model outperforms several state-of-the-art methods on a cross-species benchmark dataset. We also develop a version of Casanovo that is fine-tuned for non-enzymatic peptides. Finally, we demonstrate that Casanovo’s superior performance improves the analysis of immunopeptidomics and metaproteomics experiments and allows us to delve deeper into the dark proteome.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
Harris, C. R., Millman, K. J., van der Walt, S. J., Gommers, R., Virtanen, P., Cournapeau, D., Wieser, E., Taylor, J., Berg, S., Smith, N. J., et al. (2020) · Nature · doi:10.1038/s41586-020-2649-2 · Cited by 23,826
seaborn: statistical data visualization
Waskom, M. (2021) · Journal of Open Source Software · doi:10.21105/joss.03021 · Cited by 7,310
Eng, J. K., McCormack, A. L., & Yates, J. R. (1994) · Journal of the American Society for Mass Spectrometry · doi:10.1016/1044-0305(94)80016-2 · Cited by 6,484 · cited 1×
“For example, the antigenic peptides presented by major histocompatibility complex (MHC) proteins — the “ immunopeptidome ”— are often generated from their parent proteins in an unpredictable manner, requiring at minimum every possible protein subsequence to be considered 5 – 7 .”
Amino acid substitution matrices from protein blocks.
Henikoff, S., & Henikoff, J. G. (1992) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.89.22.10915 · Cited by 6,218
A Learning Algorithm for Continually Running Fully Recurrent Neural Networks
Williams, R. J., & Zipser, D. (1989) · Neural Computation · doi:10.1162/neco.1989.1.2.270 · Cited by 4,369 · cited 1×
“During training, the decoder is fed the amino acid pre fi x for the ground truth peptide following the teacher forcing paradigm 44 .”
Elias, J. E., & Gygi, S. P. (2007) · Nature Methods · doi:10.1038/nmeth1019 · Cited by 3,925
Rives, A., Meier, J., Sercu, T., Goyal, S., Lin, Z., Liu, J., Guo, D., Ott, M., Zitnick, C. L., Ma, J., et al. (2021) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2016239118 · Cited by 3,286
Rives, A., Meier, J., Sercu, T., Goyal, S., Lin, Z., Liu, J., Guo, D., Ott, M., Zitnick, C. L., Ma, J., et al. (2019) · doi:10.1101/622803 · Cited by 3,280 · cited 1×
“As such, the transformer architecture has found success in not only natural language processing, but also applications to biological sequences 24,25 .”
Semi-supervised learning for peptide identification from shotgun proteomics datasets
Käll, L., Canterbury, J. D., Weston, J., Noble, W. S., & MacCoss, M. J. (2007) · Nature Methods · doi:10.1038/nmeth1113 · Cited by 2,424
Self-citation
Cited by
Predicting glycan structure from tandem mass spectrometry via deep learning
Urban, J., Jin, C., Thomsson, K. A., Karlsson, N. G., Ives, C. M., Fadda, E., & Bojar, D. (2024) · Nature Methods · doi:10.1038/s41592-024-02314-6 · Cited by 79
Pairwise Attention: Leveraging Mass Differences to Enhance De Novo Sequencing of Mass Spectra
Lapin, J., Nilsson, A., Wilhelm, M., & Käll, L. (2025) · Journal of Proteome Research · doi:10.1021/acs.jproteome.5c00063 · Cited by 4
(2025) · doi:10.1016/j.mcpro.2025.101501 · Cited by 4
Metadata
- Authors
- Yilmaz, M., Fondrie, W. E., Bittremieux, W., Melendez, C. F., Nelson, R., Ananth, V., Oh, S., & Noble, W. S.
- Venue
- Nature Communications
- Published
- 2024-07-30
- Volume
- 15
- Issue
- 1
- Pages
- 6427-6427
- ISSN
- 2041-1723 (ISSN-L)
- OpenAlex
- W4401107218
- Cited by
- 114
- References
- 15
- FWCI
- 13.03
- Type
- journal article
- Language
- en
- Open access
- gold
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Sequence-to-sequence translation from mass spectra to peptides with a transformer model. https://app.cochat.ai/papers/10.1038/s41467-024-49731-x
- The paper
- Yilmaz, M., Fondrie, W. E., Bittremieux, W., Melendez, C. F., Nelson, R., Ananth, V., Oh, S., & Noble, W. S. (2024). Sequence-to-sequence translation from mass spectra to peptides with a transformer model. Nature Communications. https://doi.org/10.1038/s41467-024-49731-x
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.