Foundation model enables interpretable open and error-tolerant searching for mass spectrometry-based proteomics
5 affiliations
- 1Department of Pathology, Boston Children’s Hospital and Harvard Medical School, Boston, MA 02115,
- 2Hasso Plattner Institute, Digital Engineering Faculty, University of Potsdam, Potsdam, 14482,
- 3Data Competence Center (MF 2), Robert Koch Institute, Berlin, 13353,
- 4Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, New York, NY 10029,
- 5Windreich Department of Artificial Intelligence & Human Health, Icahn School of Medicine at Mount Sinai, New York, NY 10029,
Abstract
MOTIVATION: Mass spectrometry-based proteomics allows studying all proteins of a sample on a molecular level. However, mass spectra are noisy and contain complex patterns, making them inherently challenging to analyze with algorithmic approaches. In terms of the protein sequence landscape, most recent bottom-up MS-based proteomics studies consider either a diverse pool of post-translational modifications, employ large databases-as in metaproteomics or proteogenomics, study multiple isoforms of proteins, include unspecific cleavage sites or even combinations thereof. All this makes peptide and protein identifications challenging. RESULTS: Here, we present a foundation model, called yHydra, that jointly embeds spectra and peptides. This allows us to implement various downstream tasks and search modes in Euclidean space. We implement an open search which allows querying multiple ten-thousands of spectra against millions of peptides. Furthermore, we implement an error-tolerant search for identifying additional proteoforms that are not included in off-the-shelf reference proteomes. Our foundation model provides meaningful embeddings, as we interpret learned peptide embeddings in comparison to the peptide's physico-chemical properties. Hydra's open search, assigns delta masses to each identification which allows to unrestrictedly characterize post-translational modifications. The error-tolerant mode of yHydra can be used as post-processing to existing search engines or as a standalone. yHydra is evaluated on several real life data sets for the identification of modified peptide sequences and shows up to 25% increase in peptide identification at constant false discovery rate compared to the current state-of-the-art. AVAILABILITY AND IMPLEMENTATION: Code is available on Gitlab: https://gitlab.com/dacs-hpi/yHydra, and https://gitlab.com/dacs-hpi/yHydra_train.
Related
- Mass Spectrometry-Based Structural Proteomics and Analytical Ultracentrifugation Characterize the Structures of Oligomeric Apolipoprotein E4 and its Variants
- Tesorai Search: Cloud-based Database Search Engine Boosts Identifications for Mass Spectrometry Proteomics With a Pretrained Peptide-spectrum Deep-learning Model
- Cross-Platform Evaluation Reveals Sample Preparation-Driven Biological Biases despite Advances in Mass Spectrometry Performance in Serum Proteomics.
- Pretrained spectrum representations for diverse tandem mass spectrometry proteomics tasks
- Data processing in proteomics and metabolomics: liquid chromatography-mass spectrometry-based omics with divergent computational paradigms.
BibTeX
@article{altenburg2026foundation,
title = {{Foundation model enables interpretable open and error-tolerant searching for mass spectrometry-based proteomics}},
author = {Tom Altenburg and Thilo Muth and Patrick van Zalm and Hanno Steen and Bernhard Y. Renard},
journal = {Bioinformatics},
year = {2026},
month = jul,
doi = {10.1093/bioinformatics/btag297},
url = {https://doi.org/10.1093/bioinformatics/btag297},
note = {CC BY},
}
RIS
TY - JOUR
TI - Foundation model enables interpretable open and error-tolerant searching for mass spectrometry-based proteomics
AU - Tom Altenburg
AU - Thilo Muth
AU - Patrick van Zalm
AU - Hanno Steen
AU - Bernhard Y. Renard
PY - 2026
DA - 2026/07/01
JO - Bioinformatics
DO - 10.1093/bioinformatics/btag297
UR - https://doi.org/10.1093/bioinformatics/btag297
AB - MOTIVATION: Mass spectrometry-based proteomics allows studying all proteins of a sample on a molecular level. However, mass spectra are noisy and contain complex patterns, making them inherently challenging to analyze with algorithmic approaches. In terms of the protein sequence landscape, most recent bottom-up MS-based proteomics studies consider either a diverse pool of post-translational modifications, employ large databases-as in metaproteomics or proteogenomics, study multiple isoforms of proteins, include unspecific cleavage sites or even combinations thereof. All this makes peptide and protein identifications challenging. RESULTS: Here, we present a foundation model, called yHydra, that jointly embeds spectra and peptides. This allows us to implement various downstream tasks and search modes in Euclidean space. We implement an open search which allows querying multiple ten-thousands of spectra against millions of peptides. Furthermore, we implement an error-tolerant search for identifying additional proteoforms that are not included in off-the-shelf reference proteomes. Our foundation model provides meaningful embeddings, as we interpret learned peptide embeddings in comparison to the peptide's physico-chemical properties. Hydra's open search, assigns delta masses to each identification which allows to unrestrictedly characterize post-translational modifications. The error-tolerant mode of yHydra can be used as post-processing to existing search engines or as a standalone. yHydra is evaluated on several real life data sets for the identification of modified peptide sequences and shows up to 25% increase in peptide identification at constant false discovery rate compared to the current state-of-the-art. AVAILABILITY AND IMPLEMENTATION: Code is available on Gitlab: https://gitlab.com/dacs-hpi/yHydra, and https://gitlab.com/dacs-hpi/yHydra_train.
SN - 1367-4803
SN - 1367-4811
ER -