Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

Repositorio Digital de la UPF
Publication Artículo científico (JournalArticle)

Koina: Democratizing machine learning for proteomics research

  • Lautenbacher, Ludwig
  • Sabidó Aguadé, Eduard, 1981-
  • Wilhelm, Mathias
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., This research was in part funded by the Munich Data Science Institute (L.L.); European Union¿s Horizon 2020 Program under Grant Agreement 823839 [H2020-INFRAIA-2018-1; EPIC-XS] (W.G.); an ERC Starting Grant [101077037] (E.K., M.W., W.G.); National Institutes of Health grants R01-GM094231, 1U01CA288888, and U24-CA271037 (K.L.Y., F.Y., K.L., A.I.N.); R35-GM150723 (B.C.S.); R35-GM150583 and R00-HD090201 (D.B.W.); the University of Michigan Rackham Predoctoral Fellowship (K.L.Y.); the Research Foundation Flanders (FWO) [12B7123N, 12A6L24N, 1SH9O24N] (R.G., R.B., R.D.); National Science Foundation (NSF) Grant No. DBI-2011271 (H.T., Y.H.); the Spanish Ministry of Science and Innovation [PID2020-115092GB-I00] (E.S.); and NIH grants 5U24DK133658-02 (Mi.W., M.S).
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Koina: Democratizing machine learning for proteomics research

  • Lautenbacher, Ludwig
  • Sabidó Aguadé, Eduard, 1981-
  • Wilhelm, Mathias
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., This research was in part funded by the Munich Data Science Institute (L.L.); European Union¿s Horizon 2020 Program under Grant Agreement 823839 [H2020-INFRAIA-2018-1; EPIC-XS] (W.G.); an ERC Starting Grant [101077037] (E.K., M.W., W.G.); National Institutes of Health grants R01-GM094231, 1U01CA288888, and U24-CA271037 (K.L.Y., F.Y., K.L., A.I.N.); R35-GM150723 (B.C.S.); R35-GM150583 and R00-HD090201 (D.B.W.); the University of Michigan Rackham Predoctoral Fellowship (K.L.Y.); the Research Foundation Flanders (FWO) [12B7123N, 12A6L24N, 1SH9O24N] (R.G., R.B., R.D.); National Science Foundation (NSF) Grant No. DBI-2011271 (H.T., Y.H.); the Spanish Ministry of Science and Innovation [PID2020-115092GB-I00] (E.S.); and NIH grants 5U24DK133658-02 (Mi.W., M.S).