Improvements to Casanovo, a Deep Learning <i>De Novo</i> Peptide Sequencer
Casanovo is a state-of-the-art deep learning model for <i>de novo</i> peptide sequencing from mass spectrometry and proteomics data. Here, we report on a series of enhancements to Casanovo, aimed at improving the interpretability of the scores assigned to predicted peptides, generalizing the software for use in database searches, speeding up training and prediction runtimes, and providing workflows and visualization tools to facilitate adoption of Casanovo and interpretation of its results. Our goal is to make Casanovo accurate and easy to use for applications such as metaproteomics, antibody sequencing, immunopeptidomics, and the discovery of novel peptide sequences in standard proteomics analyses. Casanovo is available as open source at https://github.com/Noble-Lab/casanovo.
Authors
- Marina Pominova (ORCID: https://orcid.org/0009-0002-5449-3069)
- William E. Fondrie (ORCID: https://orcid.org/0000-0002-1554-3716)
- Michael J. MacCoss (ORCID: https://orcid.org/0000-0003-1853-0256)
- Justin J. Sanders (ORCID: https://orcid.org/0000-0001-8928-4051)
- Michael Riffle (ORCID: https://orcid.org/0000-0003-1633-8607)
- Chris Hsu (ORCID: https://orcid.org/0000-0002-0846-6126)
- Melih Yilmaz (ORCID: https://orcid.org/0000-0001-7473-4785)
- Daniela Klaproth-Andrade (ORCID: https://orcid.org/0009-0008-4223-2199)
- Gwenneth Straub
- Sewoong Oh
- William Stafford Noble
- Bo Wen
- Lingwen Xu
- Varun Ananth
Institutions
- University of Antwerp (BE)
- University of Washington (US)
- Technical University of Munich (DE)
Publication Details
- Journal
- Journal of Proteome Research
- Published
- 2025-12-30
- DOI
- https://doi.org/10.1021/acs.jproteome.5c00706
- Primary Topic
- Advanced Proteomics Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00