Microbiome Preprocessing Machine Learning Pipeline.

Journal: Frontiers in immunology
PMID:

Abstract

BACKGROUND: 16S sequencing results are often used for Machine Learning (ML) tasks. 16S gene sequences are represented as feature counts, which are associated with taxonomic representation. Raw feature counts may not be the optimal representation for ML.

Authors

  • Yoel Jasner
    Department of Mathematics, Bar-Ilan University, Ramat Gan, Israel.
  • Anna Belogolovski
    Department of Mathematics, Bar-Ilan University, Ramat Gan, Israel.
  • Meirav Ben-Itzhak
    Department of Mathematics, Bar-Ilan University, Ramat Gan, Israel.
  • Omry Koren
    Azrieli Faculty of Medicine, Bar-Ilan University, Ramat Gan, Israel.
  • Yoram Louzoun
    Department of Mathematics, Bar-Ilan University, Ramat-Gan, Israel.