Bidirectional de novo peptide sequencing using a transformer model

Lee, Sangjeong; Kim, Hyunwoo

doi:10.1371/journal.pcbi.1011892

Cited by 4 publications

(1 citation statement)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In these settings, the alternative solution to the peptide assignment problem is de novo peptide sequencing, in which the peptide sequence is inferred directly from the observed spectrum without the use of a peptide database. Recently, deep learning methods have achieved state-of-the-art performance on this de novo sequencing task ( Tran et al 2017 , Karunratanakul et al 2019 , Yang et al 2019 , Qiao et al 2021 , Ge et al 2022 , Yilmaz et al 2022 , Eloff et al 2023 , Jin et al 2023 , Klaproth-Andrade et al 2024 , Lee and Kim 2024 , Liu et al 2023 , Mao et al 2023 , Xu et al 2023 , Yang et al 2024 ). These models are trained in a supervised fashion to predict a peptide sequence given an observed spectrum.…”

Section: Introductionmentioning

confidence: 99%

A learned score function improves the power of mass spectrometry database search

Ananth,

Sanders,

Yilmaz

et al. 2024

Bioinformatics

View full text Add to dashboard Cite

Motivation One of the core problems in the analysis of protein tandem mass spectrometry data is the peptide assignment problem: determining, for each observed spectrum, the peptide sequence that was responsible for generating the spectrum. Two primary classes of methods are used to solve this problem: database search and de novo peptide sequencing. State-of-the-art methods for de novo sequencing use machine learning methods, whereas most database search engines use hand-designed score functions to evaluate the quality of a match between an observed spectrum and a candidate peptide from the database. We hypothesized that machine learning models for de novo sequencing implicitly learn a score function that captures the relationship between peptides and spectra, and thus may be re-purposed as a score function for database search. Because this score function is trained from massive amounts of mass spectrometry data, it could potentially outperform existing, hand-designed database search tools. Results To test this hypothesis, we re-engineered Casanovo, which has been shown to provide state-of-the-art de novo sequencing capabilities, to assign scores to given peptide-spectrum pairs. We then evaluated the statistical power of this Casanovo score function, Casanovo-DB, to detect peptides on a benchmark of three mass spectrometry runs from three different species. In addition, we show that re-scoring with the Percolator post-processor benefits Casanovo-DB more than other score functions, further increasing the number of detected peptides.

show abstract

Section: Introductionmentioning

confidence: 99%

A learned score function improves the power of mass spectrometry database search

Ananth,

Sanders,

Yilmaz

et al. 2024

Bioinformatics

View full text Add to dashboard Cite

show abstract

Sequence-to-sequence translation from mass spectra to peptides with a transformer model

Yilmaz,

Fondrie,

Bittremieux

et al. 2024

Nat Commun

View full text Add to dashboard Cite

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.

show abstract

Sequence-to-sequence translation from mass spectra to peptides with a transformer model

Fondrie

Yilmaz

Bittremieux

et al. 2023

Preprint

View full text Add to dashboard Cite

A fundamental challenge for any mass spectrometry-based proteomics experiment is the identification of the peptide that generated each acquired tandem mass spectrum. Although approaches that leverage known peptide sequence databases are widely used and effective for well-characterized model organisms, such methods cannot detect unexpected peptides and can be impractical or impossible to apply in some settings. Thus, the ability to assign peptide sequences to the acquired tandem mass spectra without prior information -- de novo peptide sequencing -- is valuable for gaining biological insights for tasks including antibody sequencing, immunopeptidomics, and metaproteomics. Although many methods have been developed to address this de novo sequencing 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 immunopeptideomics and metaproteomics experiments and allows us to delve deeper into the dark proteome.

show abstract

Bidirectional de novo peptide sequencing using a transformer model

Cited by 4 publications

References 31 publications

A learned score function improves the power of mass spectrometry database search

A learned score function improves the power of mass spectrometry database search

Sequence-to-sequence translation from mass spectra to peptides with a transformer model

Sequence-to-sequence translation from mass spectra to peptides with a transformer model

Contact Info

Product

Resources

About