DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Learning representations of microbe–metabolite interactions

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 illustrate 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.

Authors:
ORCiD logo [1]; ORCiD logo [1];  [1];  [2];  [3];  [4];  [5];  [5]; ORCiD logo [6];  [1];  [1];  [1];  [7]; ORCiD logo [1];  [8]; ORCiD logo [1]; ORCiD logo [1]
  1. Univ. of California, San Diego, CA (United States)
  2. Univ. of Maryland Baltimore County (UMBC), Baltimore, MD (United States)
  3. Michigan State Univ., East Lansing, MI (United States)
  4. New York Univ. (NYU), NY (United States)
  5. Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States). Environmental Genomics Division
  6. Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States). Environmental Genomics Division ; USDOE Joint Genome Institute (JGI), Walnut Creek, CA (United States)
  7. Simons Foundation, New York, NY (United States). Flatiron Inst.
  8. New York Univ. (NYU), NY (United States); Simons Foundation, New York, NY (United States). Flatiron Inst. ; Courant Inst., New York, NY (United States). Computer Science Dept.
Publication Date:
Research Org.:
Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
Sponsoring Org.:
USDOE Office of Science (SC)
OSTI Identifier:
1582030
Grant/Contract Number:  
AC02-05CH11231; P41GM103484; S10RR029121; CA211211; DGE-1144086
Resource Type:
Accepted Manuscript
Journal Name:
Nature Methods
Additional Journal Information:
Journal Volume: 16; Journal Issue: 12; Journal ID: ISSN 1548-7091
Publisher:
Nature Publishing Group
Country of Publication:
United States
Language:
English
Subject:
59 BASIC BIOLOGICAL SCIENCES; Microbial communities; Data integration; Machine learning; Metabolomics

Citation Formats

Morton, James T., Aksenov, Alexander A., Nothias, Louis Felix, Foulds, James R., Quinn, Robert A., Badri, Michelle H., Swenson, Tami L., Van Goethem, Marc W., Northen, Trent R., Vazquez-Baeza, Yoshiki, Wang, Mingxun, Bokulich, Nicholas A., Watters, Aaron, Song, Se Jin, Bonneau, Richard, Dorrestein, Pieter C., and Knight, Rob. Learning representations of microbe–metabolite interactions. United States: N. p., 2019. Web. doi:10.1038/s41592-019-0616-3.
Morton, James T., Aksenov, Alexander A., Nothias, Louis Felix, Foulds, James R., Quinn, Robert A., Badri, Michelle H., Swenson, Tami L., Van Goethem, Marc W., Northen, Trent R., Vazquez-Baeza, Yoshiki, Wang, Mingxun, Bokulich, Nicholas A., Watters, Aaron, Song, Se Jin, Bonneau, Richard, Dorrestein, Pieter C., & Knight, Rob. Learning representations of microbe–metabolite interactions. United States. https://doi.org/10.1038/s41592-019-0616-3
Morton, James T., Aksenov, Alexander A., Nothias, Louis Felix, Foulds, James R., Quinn, Robert A., Badri, Michelle H., Swenson, Tami L., Van Goethem, Marc W., Northen, Trent R., Vazquez-Baeza, Yoshiki, Wang, Mingxun, Bokulich, Nicholas A., Watters, Aaron, Song, Se Jin, Bonneau, Richard, Dorrestein, Pieter C., and Knight, Rob. Mon . "Learning representations of microbe–metabolite interactions". United States. https://doi.org/10.1038/s41592-019-0616-3. https://www.osti.gov/servlets/purl/1582030.
@article{osti_1582030,
title = {Learning representations of microbe–metabolite interactions},
author = {Morton, James T. and Aksenov, Alexander A. and Nothias, Louis Felix and Foulds, James R. and Quinn, Robert A. and Badri, Michelle H. and Swenson, Tami L. and Van Goethem, Marc W. and Northen, Trent R. and Vazquez-Baeza, Yoshiki and Wang, Mingxun and Bokulich, Nicholas A. and Watters, Aaron and Song, Se Jin and Bonneau, Richard and Dorrestein, Pieter C. and Knight, Rob},
abstractNote = {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 illustrate 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.},
doi = {10.1038/s41592-019-0616-3},
journal = {Nature Methods},
number = 12,
volume = 16,
place = {United States},
year = {2019},
month = {11}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Citation Metrics:
Cited by: 9 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

Quantitative microbiome profiling links gut community variation to microbial load
journal, November 2017

  • Vandeputte, Doris; Kathagen, Gunter; D’hoe, Kevin
  • Nature, Vol. 551, Issue 7681
  • DOI: 10.1038/nature24460

Multi-omics of the gut microbial ecosystem in inflammatory bowel diseases
journal, May 2019


Charge competition and the linear dynamic range of detection in electrospray ionization mass spectrometry
journal, October 2004

  • Tang, Keqi; Page, Jason S.; Smith, Richard D.
  • Journal of the American Society for Mass Spectrometry, Vol. 15, Issue 10
  • DOI: 10.1016/j.jasms.2004.04.034

Dimension reduction techniques for the integrative analysis of multi-omics data
journal, March 2016

  • Meng, Chen; Zeleznik, Oana A.; Thallinger, Gerhard G.
  • Briefings in Bioinformatics, Vol. 17, Issue 4
  • DOI: 10.1093/bib/bbv108

Combining selected immunomodulatory Propionibacterium freudenreichii and Lactobacillus delbrueckii strains: Reverse engineering development of an anti-inflammatory cheese
journal, December 2015

  • Plé, Coline; Breton, Jérôme; Richoux, Romain
  • Molecular Nutrition & Food Research, Vol. 60, Issue 4
  • DOI: 10.1002/mnfr.201500580

Proportionality: A Valid Alternative to Correlation for Relative Data
journal, March 2015


Latent variable modeling for the microbiome
journal, June 2018


A penalized matrix decomposition, with applications to sparse principal components and canonical correlation analysis
journal, April 2009


Correlation detection strategies in microbial data sets vary widely in sensitivity and precision
journal, February 2016

  • Weiss, Sophie; Van Treuren, Will; Lozupone, Catherine
  • The ISME Journal, Vol. 10, Issue 7
  • DOI: 10.1038/ismej.2015.235

mixOmics: An R package for ‘omics feature selection and multiple data integration
journal, November 2017


Rhamnolipids from Pseudomonas aeruginosa disperse the biofilms of sulfate-reducing bacteria
journal, October 2018


PLS-DA for compositional data with application to metabolomics: PLS-DA for Compositional Data
journal, July 2014

  • Kalivodová, Alžběta; Hron, Karel; Filzmoser, Peter
  • Journal of Chemometrics, Vol. 29, Issue 1
  • DOI: 10.1002/cem.2657

Fungi stabilize connectivity in the lung and skin microbial ecosystems
journal, January 2018


Best practices for analysing microbiomes
journal, May 2018


Inferring Correlation Networks from Genomic Survey Data
journal, September 2012


Sparse and Compositionally Robust Inference of Microbial Ecological Networks
journal, May 2015

  • Kurtz, Zachary D.; Müller, Christian L.; Miraldi, Emily R.
  • PLOS Computational Biology, Vol. 11, Issue 5
  • DOI: 10.1371/journal.pcbi.1004226

A Winogradsky-based culture system shows an association between microbial fermentation and cystic fibrosis exacerbation
journal, December 2014

  • Quinn, Robert A.; Whiteson, Katrine; Lim, Yan-Wei
  • The ISME Journal, Vol. 9, Issue 4
  • DOI: 10.1038/ismej.2014.234

Establishing microbial composition measurement standards with reference frames
journal, June 2019


Mechanistic investigation of ionization suppression in electrospray ionization
journal, November 2000

  • King, Richard; Bonfiglio, Ryan; Fernandez-Metzler, Carmen
  • Journal of the American Society for Mass Spectrometry, Vol. 11, Issue 11
  • DOI: 10.1016/S1044-0305(00)00163-X

Metabolomics of Fecal Extracts Detects Altered Metabolic Activity of Gut Microbiota in Ulcerative Colitis and Irritable Bowel Syndrome
journal, September 2011

  • Le Gall, Gwénaëlle; Noor, Samah O.; Ridgway, Karyn
  • Journal of Proteome Research, Vol. 10, Issue 9
  • DOI: 10.1021/pr2003598

Inflammation-induced IgA+ cells dismantle anti-liver cancer immunity
journal, November 2017

  • Shalapour, Shabnam; Lin, Xue-Jia; Bastian, Ingmar N.
  • Nature, Vol. 551, Issue 7680
  • DOI: 10.1038/nature24302

Advances in Principal Balances for Compositional Data
journal, November 2017

  • Martín-Fernández, J. A.; Pawlowsky-Glahn, V.; Egozcue, J. J.
  • Mathematical Geosciences, Vol. 50, Issue 3
  • DOI: 10.1007/s11004-017-9712-z

Strategies for the Assessment of Matrix Effect in Quantitative Bioanalytical Methods Based on HPLC−MS/MS
journal, July 2003

  • Matuszewski, B. K.; Constanzer, M. L.; Chavez-Eng, C. M.
  • Analytical Chemistry, Vol. 75, Issue 13
  • DOI: 10.1021/ac020361s

Pseudomonas aeruginosa rhamnolipids: biosynthesis and potential applications
journal, November 2000

  • Maier, R. M.; Soberón-Chávez, G.
  • Applied Microbiology and Biotechnology, Vol. 54, Issue 5
  • DOI: 10.1007/s002530000443

Exometabolite niche partitioning among sympatric soil bacteria
journal, September 2015

  • Baran, Richard; Brodie, Eoin L.; Mayberry-Lewis, Jazmine
  • Nature Communications, Vol. 6, Issue 1
  • DOI: 10.1038/ncomms9289

Matrix Factorization Techniques for Recommender Systems
journal, August 2009

  • Koren, Yehuda; Bell, Robert; Volinsky, Chris
  • Computer, Vol. 42, Issue 8
  • DOI: 10.1109/MC.2009.263

Sharing and community curation of mass spectrometry data with Global Natural Products Social Molecular Networking
journal, August 2016

  • Wang, Mingxun; Carver, Jeremy J.; Phelan, Vanessa V.
  • Nature Biotechnology, Vol. 34, Issue 8
  • DOI: 10.1038/nbt.3597

The interaction between bacteria and bile
journal, September 2005


Reproducible, interactive, scalable and extensible microbiome data science using QIIME 2
journal, July 2019


Commensal Propionibacterium strain UF1 mitigates intestinal inflammation via Th17 cell regulation
journal, September 2017

  • Colliou, Natacha; Ge, Yong; Sahay, Bikash
  • Journal of Clinical Investigation, Vol. 127, Issue 11
  • DOI: 10.1172/JCI95376

How bile acids confer gut mucosal protection against bacteria
journal, March 2006

  • Hofmann, A. F.; Eckmann, L.
  • Proceedings of the National Academy of Sciences, Vol. 103, Issue 12
  • DOI: 10.1073/pnas.0600780103

Immunomodulation properties of multi-species fermented milks
journal, February 2016


Pyocyanin Production by Pseudomonas aeruginosa Induces Neutrophil Apoptosis and Impairs Neutrophil-Mediated Host Defenses In Vivo
journal, March 2005


Biplots of compositional data
journal, October 2002

  • Aitchison, John; Greenacre, Michael
  • Journal of the Royal Statistical Society: Series C (Applied Statistics), Vol. 51, Issue 4
  • DOI: 10.1111/1467-9876.00275

Interkingdom metabolic transformations captured by microbial imaging mass spectrometry
journal, August 2012

  • Moree, W. J.; Phelan, V. V.; Wu, C. -H.
  • Proceedings of the National Academy of Sciences, Vol. 109, Issue 34
  • DOI: 10.1073/pnas.1206855109

A multi-omic future for microbiome studies
journal, April 2016


Similarity network fusion for aggregating data types on a genomic scale
journal, January 2014

  • Wang, Bo; Mezlini, Aziz M.; Demir, Feyyaz
  • Nature Methods, Vol. 11, Issue 3
  • DOI: 10.1038/nmeth.2810

Microbiome Datasets Are Compositional: And This Is Not Optional
journal, November 2017

  • Gloor, Gregory B.; Macklaim, Jean M.; Pawlowsky-Glahn, Vera
  • Frontiers in Microbiology, Vol. 8
  • DOI: 10.3389/fmicb.2017.02224

Canonical correspondence analysis and related multivariate methods in aquatic ecology
journal, September 1995

  • ter Braak, Cajo J. F.; Verdonschot, Piet F. M.
  • Aquatic Sciences, Vol. 57, Issue 3
  • DOI: 10.1007/BF00877430

Niche partitioning of a pathogenic microbiome driven by chemical gradients
journal, September 2018

  • Quinn, Robert A.; Comstock, William; Zhang, Tianyu
  • Science Advances, Vol. 4, Issue 9
  • DOI: 10.1126/sciadv.aau1908

EMPeror: a tool for visualizing high-throughput microbial community data
journal, November 2013

  • Vázquez-Baeza, Yoshiki; Pirrung, Meg; Gonzalez, Antonio
  • GigaScience, Vol. 2, Issue 1
  • DOI: 10.1186/2047-217X-2-16

Predictive metabolomic profiling of microbial communities using amplicon or metagenomic sequences
journal, July 2019


Klebsiella pneumoniae: Going on the Offense with a Strong Defense
journal, June 2016

  • Paczosa, Michelle K.; Mecsas, Joan
  • Microbiology and Molecular Biology Reviews, Vol. 80, Issue 3
  • DOI: 10.1128/MMBR.00078-15

Linking soil biology and chemistry in biological soil crust using isolate exometabolomics
journal, January 2018


Alterations in skin microbiome mediated by radiotherapy and their potential roles in the prognosis of radiotherapy-induced dermatitis: a pilot study
journal, March 2021


Causal effects in microbiomes using interventional calculus
journal, March 2021


The Gut Microbiome in Autism: Study-Site Effects and Longitudinal Analysis of Behavior Change
journal, April 2021


Systems Analysis of Gut Microbiome Influence on Metabolic Disease in HIV-Positive and High-Risk Populations
journal, June 2021


A Generic Multivariate Framework for the Integration of Microbiome Longitudinal Studies With Other Data Types
journal, November 2019


Sharing and community curation of mass spectrometry data with Global Natural Products Social Molecular Networking
text, January 2016

  • M., Waters, Katrina; Yao, Peng,; L., McPhail, Kerry
  • The University of North Carolina at Chapel Hill University Libraries
  • DOI: 10.17615/dd92-mf79

Erratum: A Winogradsky-based culture system shows an association between microbial fermentation and cystic fibrosis exacerbation
journal, March 2015

  • Quinn, Robert A.; Whiteson, Katrine; Lim, Yan-Wei
  • The ISME Journal, Vol. 9, Issue 4
  • DOI: 10.1038/ismej.2014.266

Pattern recognition and machine learning
journal, August 1974


Pattern Recognition and Machine Learning
journal, January 2007

  • Maindonald, John
  • Journal of Statistical Software, Vol. 17, Issue Book Review 5
  • DOI: 10.18637/jss.v017.b05

Sparse and compositionally robust inference of microbial ecological networks
text, January 2014


Works referencing / citing this record:

The Connection and Disconnection Between Microbiome and Metabolome: A Critical Appraisal in Clinical Research
journal, February 2020


Machine Learning Applications for Mass Spectrometry-Based Metabolomics
journal, June 2020


Machine Learning Applications for Mass Spectrometry-Based Metabolomics
text, January 2020