[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120519-en":3,"doc-seo-120519-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},120519,1374391974564,"Clementine","https://ap-avatar.wpscdn.com/avatar/14000253aa45c000a9e?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779874745381141002",8,"Research & Report","Koina - Democratizing machine learning for proteomics research","Recent developments in machine learning and deep learning have strong potential to accelerate proteomics workflows, including generating spectral libraries, improving peptide identification, and optimizing acquisition strategies. Despite frequent publication of new ML/DL models tailored to proteomics, community adoption remains limited due to poor findability and accessibility and technical barriers to integrating models into analysis pipelines. Koina is an open-source, decentralized, online-accessible model repository that provides an easy interface, enabling model reuse and pipeline integration, demonstrated with FragPipe.","UC Riverside  \nUC Riverside Previously Published Works  \nTitle  \nKoina: Democratizing machine learning for proteomics research.  \nPermalink  \n[https://escholarship.org/uc/item/9ng649rw](https://escholarship.org/uc/item/9ng649rw)  \nJournal  \nNature Communications, 16(1)  \nISSN  \n2041-1723  \nAuthors  \nLautenbacher, Ludwig  \nYang, Kevin Kockmann, Tobias et al.  \nPublication Date  \n2025-11-01  \nDOI  \n10.1038/s41467-025-64870-5  \nCopyright Information  \nThis work is made available under the terms of a Creative Commons Attribution License, available at [https://creativecommons.org/licenses/by/4.0/](https://creativecommons.org/licenses/by/4.0/)  \nPeer reviewed  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \nArticle [https://doi.org/10.1038/s41467-025-64870-5](https://doi.org/10.1038/s41467-025-64870-5)  \nKoina: Democratizing machine learning for proteomics research  \nReceived: 20 November 2024  \n\n| Accepted: 29 September 2025 |\n| --- |\n|  |\n| Check for updates |\n\nLudwig Lautenbacher 1,2,20, Kevin L. Yang 3,20, Tobias Kockmann 4  \n,  \nChristian Panse 4,5, Wassim Gabriel 1, Dulguun Bold1, Elias Kahl1, Matthew Chambers6, Brendan X. MacLean 6, Kai Li 3, Fengchao Yu  Brian C. Searle 8,9,10, Damien Beau Wilburn10,11,  \nMohammad Reza Zare Shahneh 12, Yuhui Hong 13, Haixu Tang 13, Mingxun Wang 12,14, Ralf Gabriels 15,16, Robbin Bouwmeester 15,16, Robbe Devreese 15,16, Jesse Angelis 1, Eduard Sabidó 17,18,  \nTobias K. Schmidt 19, Alexey I. Nesvizhskii 3,7  & Mathias Wilhelm   \n7  \n,  \n1,2   \nRecent 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 opensource 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.  \nRecent advancements in machine learning (ML) and deep learning dependent acquisition (DDA)2–6, data-independent acquisition (DL) hold substantial promise for numerous applications in pro- (DIA)7, and targeted acquisition modes8. Despite the frequent teomics, particularly in tasks such as generating optimized spec- publication of new ML/DL models (hereafter abbreviated to ML tral libraries1 and enhancing peptide identification in data- models) designed specifically for proteomics, their adoption  \n1Computational Mass Spectrometry, Technical University of Munich (TUM), Freising, Germany. 2Munich Data Science Institute, Technical University of Munich, Garching, Germany. 3Gilbert S. Omenn Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI, USA. 4Functional Genomics Center Zurich (FGCZ) -University of Zurich | ETH Zurich, Winterthurerstrasse 190, CH-, Zurich, Switzerland. 5Swiss Institute of Bioinformatics (SIB), Quartier Sorge-Batiment Amphipole, CH-, Lausanne, Switzerland. 6Department of Genome Sciences, University of Washington, Seattle, WA, USA. 7Department of Pathology, University of Michigan, Ann Arbor, MI, USA. 8Pelotonia Institute for Immuno-Oncology, The Ohio State University Comprehensive Cancer Center, Columbus, Ohio, USA. 9Department of Biomedical Informatics, The Ohio State University, Columbus, Ohio, USA. 10Department of C","cbCaihyniNE8Ng7w","https://ap.wps.com/l/cbCaihyniNE8Ng7w","pdf",2830750,1,14,"English","en",105,"# Background and problem statement\n## ML/DL potential for proteomics\n## Barriers to model adoption\n# Koina repository overview\n## Decentralized online-accessible model publishing\n## Online interface for model usage\n# Integration and demonstration\n## Example with FragPipe platform\n## Benefits for data analysis pipelines","[{\"question\":\"What problem does Koina address in proteomics machine learning adoption?\",\"answer\":\"Koina targets slow community adoption of proteomics ML models caused by limited findability/accessibility and difficulties integrating models into data analysis pipelines.\"},{\"question\":\"What is Koina in this work?\",\"answer\":\"Koina is an open-source, decentralized, online-accessible repository designed to facilitate publication and reuse of ML models for proteomics research.\"},{\"question\":\"How is Koina demonstrated in the paper?\",\"answer\":\"The authors demonstrate how Koina can be integrated with existing proteomics tools by using the FragPipe computational platform as an example, showing improvements to data analysis pipelines.\"}]","Koina - Democratizing machine learning for proteomics research | PDF",1785730460,35,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"koina-democratizing-machine-learning-for-proteomics-research","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/koina-democratizing-machine-learning-for-proteomics-research/120519/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does Koina address in proteomics machine learning adoption?","Question",{"text":75,"@type":76},"Koina targets slow community adoption of proteomics ML models caused by limited findability/accessibility and difficulties integrating models into data analysis pipelines.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is Koina in this work?",{"text":80,"@type":76},"Koina is an open-source, decentralized, online-accessible repository designed to facilitate publication and reuse of ML models for proteomics research.",{"name":82,"@type":73,"acceptedAnswer":83},"How is Koina demonstrated in the paper?",{"text":84,"@type":76},"The authors demonstrate how Koina can be integrated with existing proteomics tools by using the FragPipe computational platform as an example, showing improvements to data analysis pipelines.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]