Koina: Democratizing machine learning for proteomics research
Recent developments in machine learning (ML) and deep learning have immense potential for applications in proteomics, such as generating spectral libraries, improving peptide identification, and optimizing targeted acquisition modes. Although new ML models are regularly published, the rate at which the community adopts these models is slow. This is in part due to a lack of findability and accessibility of these models as well as the technical challenges involved in incorporating these models into data analysis pipelines and demonstrating their reusability for end-users. Here we show Koina, an open-source decentralized and online-accessible model repository to facilitate publication of ML models. Koina enables ML model usage via an easy-to-use online interface, facilitating the integration of ML models in data analysis pipelines. Using the widely used FragPipe computational platform as an example, we demonstrate how Koina can be integrated with existing proteomics software tools and how these integrations improve data analysis.
Authors
- Christian Panse (ORCID: https://orcid.org/0000-0003-1975-3064)
- Ludwig Lautenbacher (ORCID: https://orcid.org/0000-0002-1540-5911)
- Fengchao Yu (ORCID: https://orcid.org/0000-0002-7695-3698)
- Damien B. Wilburn (ORCID: https://orcid.org/0000-0002-1255-9982)
- Mohammad Reza Zare Shahneh (ORCID: https://orcid.org/0000-0002-5760-3190)
- Mathias Wilhelm (ORCID: https://orcid.org/0000-0002-9224-3258)
- Brendan MacLean (ORCID: https://orcid.org/0000-0002-9575-0255)
- Brian C. Searle (ORCID: https://orcid.org/0000-0001-8760-6731)
- Matthew Chambers (ORCID: https://orcid.org/0000-0001-8085-373X)
- Eduard Sabidó (ORCID: https://orcid.org/0000-0001-6506-7714)
- Ralf Gabriels (ORCID: https://orcid.org/0000-0002-1679-1711)
- Mingxun Wang (ORCID: https://orcid.org/0000-0001-7647-6097)
- Tobias Kockmann (ORCID: https://orcid.org/0000-0002-1847-885X)
- Wassim Gabriel (ORCID: https://orcid.org/0000-0001-6440-9794)
- Haixu Tang (ORCID: https://orcid.org/0000-0001-8963-8155)
- Kevin Yang (ORCID: https://orcid.org/0000-0002-8569-4579)
- Alexey I. Nesvizhskii (ORCID: https://orcid.org/0000-0002-2806-7819)
- Robbin Bouwmeester (ORCID: https://orcid.org/0000-0001-6807-7029)
- Tobias Schmidt (ORCID: https://orcid.org/0000-0002-1883-6514)
- Robbe Devreese (ORCID: https://orcid.org/0000-0002-3432-1502)
- Elias Kahl
- Kai Li (ORCID: https://orcid.org/0000-0002-0810-2437)
- Yuhui Hong (ORCID: https://orcid.org/0000-0002-5647-9714)
- Del Bold
- Jesse Angelis (ORCID: https://orcid.org/0009-0004-8209-3112)
Institutions
- University of California, Riverside (US)
- SIB Swiss Institute of Bioinformatics (CH)
- Universitat Pompeu Fabra (ES)
- ZHAW Zurich University of Applied Sciences (CH)
- University of Washington (US)
- University of Zurich (CH)
- University of Michigan (US)
- Ghent University (BE)
- Michigan Medicine (US)
- Indiana University Bloomington (US)
- Centre for Genomic Regulation (ES)
- VIB-UGent Center for Medical Biotechnology (BE)
- Virtual Technology (United States) (US)
- The Ohio State University (US)
- Technical University of Munich (DE)
Publication Details
- Journal
- Nature Communications
- Published
- 2025-11-11
- DOI
- https://doi.org/10.1038/s41467-025-64870-5
- Citations
- 5
- Primary Topic
- Advanced Proteomics Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 3.78
Funders
- National Science Foundation
- European Commission
- Branco Weiss Fellowship – Society in Science
- Fonds Wetenschappelijk Onderzoek
- Ministerio de Ciencia e Innovación
- Vlaamse regering
- National Institutes of Health
- Horizon 2020 Framework Programme
- Functional Genomics Center Zurich