Machine learning pattern recognition and differential network analysis of gastric microbiome in the presence of proton pump inhibitor treatment or Helicobacter pylori infection

Sara Ciucci, et al.

Go to the profile of Nature Communications
Mar 26, 2020

Received Date: 18th February 20

Sara CiucciClaudio DuranAlessandra PalladiniUmer Z. IjazFrancesco Paroni SterbiniLuca MasucciGiovanni CammarotaGianluca IaniroPirjo SpuulMichael SchroederStephan W. GrillBryony N. ParsonsMark PritchardBrunella PosteraroMaurizio SanguinettiGiovanni GasbarriniAntonio GasbarriniCarlo Vittorio Cannistraci

Although long thought to be a sterile and inhospitable environment, the stomach is inhabited by diverse microbial communities, co-existing in a dynamic balance. Long-term use of orally administered 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 the early phase. They mainly focus on the most prevalent taxa and rely on linear techniques for multivariate analysis.

Here we disclose the importance of complementing linear dimensionality reduction techniques such as Principal Component Analysis and Multidimensional Scaling with nonlinear approaches derived from the physics of complex systems. Then, we show the importance to complete multivariate pattern analysis with differential network analysis, to reveal mechanisms of re-organizations which emerge from combinatorial microbial variations induced by a medical treatment (PPIs) or an infectious state (H. pylori).

Read in full at bioRxiv

This is an abstract of a preprint hosted on an independent third party site. It has not been peer reviewed but is currently under consideration at Nature Communications.

Go to the profile of Nature Communications

Nature Communications

Nature Research, Springer Nature