R.ROSETTA: an interpretable machine learning framework.

Journal: BMC bioinformatics
Published Date: Mar 6, 2021

Abstract

BACKGROUND: Machine learning involves strategies and algorithms that may assist bioinformatics analyses in terms of data mining and knowledge discovery. In several applications, viz. in Life Sciences, it is often more important to understand how a prediction was obtained rather than knowing what prediction was made. To this end so-called interpretable machine learning has been recently advocated. In this study, we implemented an interpretable machine learning package based on the rough set theory. An important aim of our work was provision of statistical properties of the models and their components.

Authors

  • Mateusz Garbulowski
    Department of Cell and Molecular Biology, Uppsala University, Uppsala, Sweden.
  • Klev Diamanti
    Department of Cell and Molecular Biology, Uppsala University, Uppsala, Sweden.
  • Karolina Smolinska
    Institute of Automatic Control, Silesian University of Technology, Akademicka 16, 44-100, Gliwice, Poland.
  • Nicholas Baltzer
    Department of Cell and Molecular Biology, Uppsala University, Uppsala, Sweden.
  • Patricia Stoll
    Department of Cell and Molecular Biology, Uppsala University, Uppsala, Sweden.
  • Susanne Bornelöv
    Department of Cell and Molecular Biology, Uppsala University, Uppsala, Sweden.
  • Aleksander Øhrn
    Department of Informatics, University of Oslo, Oslo, Norway.
  • Lars Feuk
    Department of Immunology, Genetics and Pathology, Science for Life Laboratory, Uppsala University, Uppsala, Sweden. Electronic address: lars.feuk@igp.uu.se.
  • Jan Komorowski
    Department of Cell and Molecular Biology, Computational and Systems Biology, Uppsala University, Uppsala, Sweden; Institute of Computer Science, Polish Academy of Sciences, Warsaw, 01248, Poland.

Keywords

External Resources

Popular Topics
Recent Journals