Effects of data transformation and model selection on feature importance in microbiome classification data.

Journal: Microbiome
PMID:

Abstract

BACKGROUND: Accurate classification of host phenotypes from microbiome data is crucial for advancing microbiome-based therapies, with machine learning offering effective solutions. However, the complexity of the gut microbiome, data sparsity, compositionality, and population-specificity present significant challenges. Microbiome data transformations can alleviate some of the aforementioned challenges, but their usage in machine learning tasks has largely been unexplored.

Authors

  • Zuzanna Karwowska
    MaƂopolska Centre of Biotechnology, Jagiellonian University, Krakow, Poland.
  • Oliver Aasmets
    Estonian Genome Centre, Institute of Genomics, University of Tartu, Tartu, Estonia.
  • Tomasz Kosciolek
    Department of Computer Science, Bioinformatics Group, University College London, Gower Street, London, WC1E 6BT, United Kingdom.
  • Elin Org
    Estonian Genome Centre, Institute of Genomics, University of Tartu, Tartu, Estonia. elin.org@ut.ee.