Regression plane concept for analysing continuous cellular processes with machine learning.

Journal: Nature communications
Published Date: May 5, 2021

Abstract

Biological processes are inherently continuous, and the chance of phenotypic discovery is significantly restricted by discretising them. Using multi-parametric active regression we introduce the Regression Plane (RP), a user-friendly discovery tool enabling class-free phenotypic supervised machine learning, to describe and explore biological data in a continuous manner. First, we compare traditional classification with regression in a simulated experimental setup. Second, we use our framework to identify genes involved in regulating triglyceride levels in human cells. Subsequently, we analyse a time-lapse dataset on mitosis to demonstrate that the proposed methodology is capable of modelling complex processes at infinite resolution. Finally, we show that hemocyte differentiation in Drosophila melanogaster has continuous characteristics.

Authors

  • Abel Szkalisity
    Synthetic and Systems Biology Unit, Hungarian Academy of Sciences, Biological Research Center (BRC), Temesvári körút 62, Szeged 6726, Hungary.
  • Filippo Piccinini
    Istituto Scientifico Romagnolo per lo Studio e la Cura dei Tumori (IRST) IRCCS, Meldola, FC, Italy.
  • Attila Beleon
    Synthetic and Systems Biology Unit, Biological Research Centre (BRC), Szeged, Hungary.
  • Tamas Balassa
    Biological Research Centre of the Hungarian Academy of Sciences, Szeged, Hungary.
  • Istvan Gergely Varga
    Institute of Genetics, Biological Research Center (BRC), Szeged, Hungary.
  • Ede Migh
    Synthetic and Systems Biology Unit, Hungarian Academy of Sciences, Biological Research Center (BRC), Temesvári körút 62, Szeged 6726, Hungary.
  • Csaba Molnar
    Biological Research Centre of the Hungarian Academy of Sciences, Szeged, Hungary.
  • Lassi Paavolainen
    Institute for Molecular Medicine Finland (FIMM), University of Helsinki, Tukholmankatu 8, Helsinki 00014, Finland.
  • Sanna Timonen
    Institute for Molecular Medicine Finland-FIMM, Helsinki Institute of Life Science-HiLIFE, University of Helsinki, Helsinki, Finland.
  • Indranil Banerjee
    Cellular Virology Laboratory, Department of Biological Sciences, Indian Institute of Science Education and Research, Mohali (IISER Mohali) Sector 81, S.A.S. Nagar, Mohali-140306, India.
  • Elina Ikonen
    Department of Anatomy, Faculty of Medicine, University of Helsinki, Finland.
  • Yohei Yamauchi
    School of Cellular and Molecular Medicine, University of Bristol, BS8 1TD University Walk, Bristol, UK.
  • Istvan Ando
    Institute of Genetics, Biological Research Center (BRC), Szeged, Hungary.
  • Jaakko Peltonen
    Faculty of Information Technology and Communication Sciences, Tampere University, FI-33014 Tampere University, Tampere, Finland.
  • Vilja Pietiäinen
    Institute for Molecular Medicine Finland-FIMM, Helsinki Institute of Life Science-HiLIFE, University of Helsinki, Helsinki, Finland.
  • Viktor Honti
    Institute of Genetics, Biological Research Center (BRC), Szeged, Hungary.
  • Péter Horváth
    Department of Pulmonology, Semmelweis University, Budapest, Hungary.

Keywords

External Resources

Popular Topics
Recent Journals