Nonlinear machine learning pattern recognition and bacteria-metabolite multilayer network analysis of perturbed gastric microbiome

Publikation: Beitrag in FachzeitschriftForschungsartikelBeigetragenBegutachtung

Beitragende

  • Claudio Durán - , Biotechnologisches Zentrum (BIOTEC) (Autor:in)
  • Sara Ciucci - , Biomedizin Kybernetik (FoG), Biotechnologisches Zentrum (BIOTEC), Dresden International Graduate School for Biomedicine and Bioengineering (DIGS-BB) (Autor:in)
  • Alessandra Palladini - , Biotechnologisches Zentrum (BIOTEC) (Autor:in)
  • Umer Z Ijaz - , University of Glasgow (Autor:in)
  • Antonio G Zippo - , Netherlands Institute for Neuroscience (Autor:in)
  • Francesco Paroni Sterbini - , Max Planck Institute for Terrestrial Microbiology (Autor:in)
  • Luca Masucci - , Max Planck Institute for Terrestrial Microbiology (Autor:in)
  • Giovanni Cammarota - , Internal Medicine and Gastroenterology Unit (Autor:in)
  • Gianluca Ianiro - , Internal Medicine and Gastroenterology Unit (Autor:in)
  • Pirjo Spuul - , Tallinn University of Technology (Autor:in)
  • Michael Schroeder - , Biotechnologisches Zentrum (BIOTEC), Professur für Bioinformatik (Autor:in)
  • Stephan W Grill - , Biotechnologisches Zentrum (BIOTEC), Max Planck Institute of Molecular Cell Biology and Genetics (Autor:in)
  • Bryony N Parsons - , University of Liverpool (UOL) (Autor:in)
  • D Mark Pritchard - , University of Liverpool (UOL) (Autor:in)
  • Brunella Posteraro - , Max Planck Institute for Terrestrial Microbiology (Autor:in)
  • Maurizio Sanguinetti - , Max Planck Institute for Terrestrial Microbiology (Autor:in)
  • Giovanni Gasbarrini - , Internal Medicine and Gastroenterology Unit (Autor:in)
  • Antonio Gasbarrini - , Internal Medicine and Gastroenterology Unit (Autor:in)
  • Carlo Vittorio Cannistraci - , Biomedizin Kybernetik (FoG), Biotechnologisches Zentrum (BIOTEC), Medizinische Physik, Center for Complex Network Intelligence (CCNI) at Tsinghua Laboratory of Brain and Intelligence (THBI), Tsinghua University (Autor:in)

Abstract

The stomach is inhabited by diverse microbial communities, co-existing in a dynamic balance. Long-term use of drugs such as proton pump inhibitors (PPIs), or bacterial infection such as Helicobacter pylori, cause significant microbial alterations. Yet, studies revealing how the commensal bacteria re-organize, due to these perturbations of the gastric environment, are in early phase and rely principally on linear techniques for multivariate analysis. Here we disclose the importance of complementing linear dimensionality reduction techniques with nonlinear ones to unveil hidden patterns that remain unseen by linear embedding. Then, we prove the advantages to complete multivariate pattern analysis with differential network analysis, to reveal mechanisms of bacterial network re-organizations which emerge from perturbations induced by a medical treatment (PPIs) or an infectious state (H. pylori). Finally, we show how to build bacteria-metabolite multilayer networks that can deepen our understanding of the metabolite pathways significantly associated to the perturbed microbial communities.

Details

OriginalspracheEnglisch
Aufsatznummer1926
FachzeitschriftNature communications
Jahrgang12
Ausgabenummer1
PublikationsstatusVeröffentlicht - 26 März 2021
Peer-Review-StatusJa

Externe IDs

PubMedCentral PMC7997970
Scopus 85103532911
ORCID /0000-0003-2848-6949/work/141543357

Schlagworte

Schlagwörter

  • Bacteria/classification, Gastrointestinal Microbiome/drug effects, Helicobacter Infections/drug therapy, Helicobacter pylori/drug effects, Humans, Machine Learning, Microbiota/drug effects, Population Dynamics, Proton Pump Inhibitors/therapeutic use, RNA, Ribosomal, 16S/genetics, Stomach/microbiology

Bibliotheksschlagworte