Prosit: proteome-wide prediction of peptide tandem mass spectra by deep learning
peer-reviewed · Nature Methods · 2019
peer-reviewed · Nature Methods · 2019. Siegfried Gessulat et al. In mass-spectrometry-based proteomics, the identification and quantification of peptides and proteins heavily…
| Date | 2019-05-27 |
| Type | peer-reviewed |
| Venue | Nature Methods |
| Publisher | Springer Science and Business Media LLC |
| Contribution | adjacent |
| DOI | 10.1038/s41592-019-0426-7 |
| Citations (OpenAlex) | 888 |
| Venue 2-year citedness | 22.29 |
Abstract
In mass-spectrometry-based proteomics, the identification and quantification of peptides and proteins heavily rely on sequence database searching or spectral library matching. The lack of accurate predictive models for fragment ion intensities impairs the realization of the full potential of these approaches. Here, we extended the ProteomeTools synthetic peptide library to 550,000 tryptic peptides and 21 million high-quality tandem mass spectra. We trained a deep neural network, termed Prosit, resulting in chromatographic retention time and fragment ion intensity predictions that exceed the quality of the experimental data. Integrating Prosit into database search pipelines led to more identifications at >10× lower false discovery rates. We show the general applicability of Prosit by predicting spectra for proteases other than trypsin, generating spectral libraries for data-independent acquisition and improving the analysis of metaproteomes. Prosit is integrated into ProteomicsDB, allowing search result re-scoring and custom spectral library generation for any organism on the basis of peptide sequence alone.
Methods and tools
- Prosit: Deep-learning (bidirectional RNN + attention) predictor of peptide fragment-ion intensities and retention times: widely used to validate and rescore de novo sequencing candidates against predicted spectra.
Data used
- Expanding proteome coverage with CHarge Ordered Parallel Ion aNalysis (CHOPIN) combined with broad specificity proteolys (as deposited) · PXD003977
- HeLa proteome of 12,250 protein-coding genes (as deposited) · PXD004452
- Optimization of Experimental Parameters in Data-Independent Mass Spectrometry Significantly Increases Depth and Reproduc (as deposited) · PXD005573
- ProteomeTools (Parts I-III) · PXD004732, PXD010595, PXD021013
Cited by (39)
- Learning from tandem mass spectra at scale with a self-supervised foundation model for proteomics (2026) crossref
- CasanovoGUI: a cross-platform desktop application for deep learning-based de novo peptide sequencing with Casanovo (2026) both
- A large-scale unified deep learning model for peptide mass spectrum interpretation trained on multimodal data (2026) crossref
- A Framework for Database Search with AI Models in Mass Spectrometry-Based Proteomics (2026) both
- π-MSNet: A billion-scale, AI-ready living proteomics data portal (2026) crossref
- Improvements to Casanovo, a Deep Learning De Novo Peptide Sequencer (2025) crossref
- Modanovo: A Unified Model for Post-translational Modification-Aware De Novo Sequencing Using Experimental Spectra From In Vivo and Synthetic Peptides (2025) both
- Optimizing Mirror-Image Peptide Sequence Design for Data Storage via Peptide Bond Cleavage Prediction (2025) both
- Modanovo: A Unified Model for Post-Translational Modification-Aware de Novo Sequencing Using Experimental Spectra from In Vivo and Synthetic Peptides (2025) crossref
- Limitations of de novo sequencing in resolving sequence ambiguity (2025) crossref
- Improvements to CasaNovo, a deep learning de novo peptide sequencer (2025) crossref
- pUniFind: a unified large pre-trained deep learning model pushing the limit of mass spectra interpretation (2025) semanticscholar
- MassNet: billion-scale AI-friendly mass spectral corpus enables robust de novo peptide sequencing (2025) crossref
- Enamel proteins reveal biological sex and genetic variability in southern African Paranthropus (2025) both
- PSMtags improve peptide sequencing and throughput in sensitive proteomics (2025) crossref
- InstaNovo enables diffusion-powered de novo peptide sequencing in large-scale proteomics experiments (2025) both
- PepGo: a deep learning and tree search-based model for de novo peptide sequencing (2025) crossref
- Deep Learning Methods for De Novo Peptide Sequencing (2024) crossref
- Sequence-to-sequence translation from mass spectra to peptides with a transformer model (2024) both
- pXg: Comprehensive Identification of Noncanonical MHC-I-Associated Peptides From De Novo Peptide Sequencing Using RNA-Seq Reads (2024) both
- MARS an improved de novo peptide candidate selection method for non-canonical antigen target discovery in cancer (2024) both
- Deep learning-driven fragment ion series classification enables highly precise and sensitive de novo peptide sequencing (2024) both
- De novo peptide sequencing with InstaNovo: Accurate, database-free peptide identification for large scale proteomics experiments (2023) both
- Application of a Novel Hybrid CNN-GNN for Peptide Ion Encoding (2023) both
- Deep learning-driven fragment ion series classification enables highly precise and sensitive de novo peptide sequencing (2023) crossref
- Sequence-to-sequence translation from mass spectra to peptides with a transformer model (2023) crossref
- Critical evaluation of the use of artificial data for machine learning based de novo peptide identification (2023) both
- Discovering and Validating Neoantigens by Mass Spectrometry-based Immunopeptidomics and Deep Learning (2022) crossref
- A streamlined platform for analyzing tera-scale DDA and DIA mass spectrometry data enables highly sensitive immunopeptidomics (2022) both
- The impact of noise and missing fragmentation cleavages on de novo peptide identification algorithms (2022) both
- Affinity Selection from Synthetic Peptide Libraries Enabled by De Novo MS/MS Sequencing (2022) both
- The Choice of Search Engine Affects Sequencing Depth and HLA Class I Allele-Specific Peptide Repertoires (2021) both
- ProAlanase is an Effective Alternative to Trypsin for Proteomics Applications and Disulfide Bond Mapping (2020) both
- Parallel Factor Analysis Enables Quantification and Identification of Highly Convolved Data-Independent-Acquired Protein Spectra (2020) both
- Deep Learning in Proteomics (2020) both
- Parallel factor analysis enables quantification and identification of highly-convolved data independent-acquired protein spectra (2020) crossref
- Uncovering Thousands of New Peptides with Sequence-Mask-Search Hybrid De Novo Peptide Sequencing Framework (2019) both
- 2018 YPIC Challenge: A Case Study in Characterizing an Unknown Protein Sample (2019) both
- Uncovering thousands of new HLA antigens and phosphopeptides with deep learning-based sequence-mask-search de novo peptide sequencing framework (2019) both