Open AccessContext-aware dimensionality reduction deconvolutes gut microbial community dynamics
Author(s) -
Cameron Martino,
Liat Shenhav,
Clarisse Marotz,
George Armstrong,
Daniel McDonald,
Yoshiki Vázquez-Baeza,
James T. Morton,
Lingjing Jiang,
Maria Gloria Dominguez-Bello,
Austin D. Swafford,
Eran Halperin,
Rob Knight
Publication year - 2020
Publication title -
nature biotechnology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 15.358
H-Index - 445
eISSN - 1546-1696
pISSN - 1087-0156
DOI - 10.1038/s41587-020-0660-7
Subject(s) - dimensionality reduction , context (archaeology) , microbiome , computational biology , variation (astronomy) , curse of dimensionality , computer science , biology , artificial intelligence , bioinformatics , paleontology , physics , astrophysics
The translational power of human microbiome studies is limited by high interindividual variation. We describe a dimensionality reduction tool, compositional tensor factorization (CTF), that incorporates information from the same host across multiple samples to reveal patterns driving differences in microbial composition across phenotypes. CTF identifies robust patterns in sparse compositional datasets, allowing for the detection of microbial changes associated with specific phenotypes that are reproducible across datasets.