Learning representations of microbe-metabolite interactions. Journal Article uri icon

Overview

abstract

  • Integrating multiomics datasets is critical for microbiome research; however, inferring interactions across omics datasets has multiple statistical challenges. We solve this problem by using neural networks (https://github.com/biocore/mmvec) to estimate the conditional probability that each molecule is present given the presence of a specific microorganism. We show with known environmental (desert soil biocrust wetting) and clinical (cystic fibrosis lung) examples, our ability to recover microbe-metabolite relationships, and demonstrate how the method can discover relationships between microbially produced metabolites and inflammatory bowel disease.

publication date

  • December 1, 2019

has subject area

has restriction

  • green

Date in CU Experts

  • November 19, 2019 7:14 AM

Full Author List

  • Morton JT; Aksenov AA; Nothias LF; Foulds JR; Quinn RA; Badri MH; Swenson TL; Van Goethem MW; Northen TR; Vazquez-Baeza Y

author count

  • 17

Other Profiles

Electronic International Standard Serial Number (EISSN)

  • 1548-7105

Additional Document Info

start page

  • 1306

end page

  • 1314

volume

  • 16

issue

  • 12