Koina: Democratizing machine learning for proteomics research

Ludwig Lautenbacher, Kevin L. Yang, Tobias Kockmann, Christian Panse, Wassim Gabriel, Dulguun Bold, Elias Kahl, Matthew Chambers, Brendan X. MacLean, Kai Li, Fengchao Yu, Brian C. Searle, Damien Beau Wilburn, Mohammad Reza Zare Shahneh, Yuhui Hong, Haixu Tang, Mingxun Wang, Ralf Gabriels, Robbin Bouwmeester, Robbe Devreese, Jesse Angelis, Eduard Sabidó, Tobias K. Schmidt, Alexey I. Nesvizhskii () and Mathias Wilhelm ()
Additional contact information
Ludwig Lautenbacher: Technical University of Munich (TUM)
Kevin L. Yang: University of Michigan
Tobias Kockmann: CH-
Christian Panse: CH-
Wassim Gabriel: Technical University of Munich (TUM)
Dulguun Bold: Technical University of Munich (TUM)
Elias Kahl: Technical University of Munich (TUM)
Matthew Chambers: University of Washington
Brendan X. MacLean: University of Washington
Kai Li: University of Michigan
Fengchao Yu: University of Michigan
Brian C. Searle: Columbus
Damien Beau Wilburn: Columbus
Mohammad Reza Zare Shahneh: University of California Riverside
Yuhui Hong: Indiana University Bloomington
Haixu Tang: Indiana University Bloomington
Mingxun Wang: University of California Riverside
Ralf Gabriels: VIB
Robbin Bouwmeester: VIB
Robbe Devreese: VIB
Jesse Angelis: Technical University of Munich (TUM)
Eduard Sabidó: Dr. Aiguader 88
Tobias K. Schmidt: MSAID GmbH
Alexey I. Nesvizhskii: University of Michigan
Mathias Wilhelm: Technical University of Munich (TUM)

Nature Communications, 2025, vol. 16, issue 1, 1-13

Abstract: Abstract 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.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-025-64870-5 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:16:y:2025:i:1:d:10.1038_s41467-025-64870-5

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-025-64870-5

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().