Toward an Integrated Machine Learning Model of a Proteomics Experiment

Journal of Proteome Research, vol. 22, pp. 681–696

Abstract

In recent years machine learning has made extensive progress in modeling many aspects of mass spectrometry data. We brought together proteomics data generators, repository managers, and machine learning experts in a workshop with the goals to evaluate and explore machine learning applications for realistic modeling of data from multidimensional mass spectrometry-based proteomics analysis of any sample or organism. Following this sample-to-data roadmap helped identify knowledge gaps and define needs. Being able to generate bespoke and realistic synthetic data has legitimate and important uses in system suitability, method development, and algorithm benchmarking, while also posing critical ethical questions. The interdisciplinary nature of the workshop informed discussions of what is currently possible and future opportunities and challenges. In the following perspective we summarize these discussions in the hope of conveying our excitement about the potential of machine learning in proteomics and to inspire future research.

Authors 18

1. Benjamin A. Neely corresponding

   National Institute of Standards and Technology

   Affiliation as printed

   National Institute of Standards and Technology, Charleston, South Carolina 29412, United States

2. Viktoria Dorfer corresponding

   University of Applied Sciences Upper Austria

   Affiliation as printed

   Bioinformatics Research Group, University of Applied Sciences Upper Austria, Softwarepark 11, 4232 Hagenberg, Austria

3. Lennart Martens corresponding

   Ghent University · VIB-UGent Center for Medical Biotechnology

   Affiliation as printed

   Department of Biomolecular Medicine, Faculty of Health Sciences and Medicine, Ghent University, 9000 Ghent, Belgium

   VIB-UGent Center for Medical Biotechnology, VIB, 9000 Ghent, Belgium

4. Isabell Bludau

   Max Planck Institute of Biochemistry

   Affiliation as printed

   Department of Proteomics and Signal Transduction, Max Planck Institute of Biochemistry, 82152 Martinsried, Germany

5. Robbin Bouwmeester

   Ghent University · VIB-UGent Center for Medical Biotechnology

   Affiliation as printed

   Department of Biomolecular Medicine, Faculty of Health Sciences and Medicine, Ghent University, 9000 Ghent, Belgium

   VIB-UGent Center for Medical Biotechnology, VIB, 9000 Ghent, Belgium

6. Sven Degroeve

   Ghent University · VIB-UGent Center for Medical Biotechnology

   Affiliation as printed

   Department of Biomolecular Medicine, Faculty of Health Sciences and Medicine, Ghent University, 9000 Ghent, Belgium

   VIB-UGent Center for Medical Biotechnology, VIB, 9000 Ghent, Belgium

7. Eric W. Deutsch

   Institute for Systems Biology

   Affiliation as printed

   Institute for Systems Biology, Seattle, Washington 98109, United States

8. Siegfried Gessulat
   Affiliation as printed

   MSAID GmbH, 10559 Berlin, Germany

9. Lukas Käll

   Science for Life Laboratory · KTH Royal Institute of Technology

   Affiliation as printed

   Science for Life Laboratory, KTH - Royal Institute of Technology, 171 21 Solna, Sweden

10. Pawel Palczynski

    University of Southern Denmark

    Affiliation as printed

    Department of Biochemistry and Molecular Biology, University of Southern Denmark, 5230 Odense, Denmark

11. Samuel Payne

    Brigham Young University

    Affiliation as printed

    Department of Biology, Brigham Young University, Provo, Utah 84602, United States

12. Tobias Greisager Rehfeldt

    University of Southern Denmark

    Affiliation as printed

    Institute for Mathematics and Computer Science, University of Southern Denmark, 5230 Odense, Denmark

13. Tobias Schmidt
    Affiliation as printed

    MSAID GmbH, 85748 Garching, Germany

14. Veit Schwämmle

    University of Southern Denmark

    Affiliation as printed

    Department of Biochemistry and Molecular Biology, University of Southern Denmark, 5230 Odense, Denmark

15. Julian Uszkoreit

    Ruhr University Bochum

    Affiliation as printed

    Medical Proteome Analysis, Center for Protein Diagnostics (ProDi), Ruhr University Bochum, 44801 Bochum, Germany

    Medizinisches Proteom-Center, Medical Faculty, Ruhr University Bochum, 44801 Bochum, Germany

16. Juan Antonio Vizcaíno

    European Bioinformatics Institute

    Affiliation as printed

    European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, United Kingdom

17. Mathias Wilhelm

    Technical University of Munich

    Affiliation as printed

    Computational Mass Spectrometry, Technical University of Munich (TUM), 85354 Freising, Germany

18. Magnus Palmblad corresponding Aachen

    Leiden University Medical Center

    Affiliation as printed

    Leiden University Medical Center, Postbus 9600, 2300 RC Leiden, The Netherlands