Machine Learning Algorithms Reveals Country-Specific Metagenomic Taxa from American Gut Project Data

Jose Liñares-Blanco, Carlos Fernandez-Lozano, Jose A Seoane, Guillermo Lopez-Campos

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

In recent years, microbiota has become an increasingly relevant factor for the understanding and potential treatment of diseases. In this work, based on the data reported by the largest study of microbioma in the world, a classification model has been developed based on Machine Learning (ML) capable of predicting the country of origin (United Kingdom vs United States) according to metagenomic data. The data were used for the training of a glmnet algorithm and a Random Forest algorithm. Both algorithms obtained similar results (0.698 and 0.672 in AUC, respectively). Furthermore, thanks to the application of a multivariate feature selection algorithm, eleven metagenomic genres highly correlated with the country of origin were obtained. An in-depth study of the variables used in each model is shown in the present work.
Original languageEnglish
Title of host publicationPublic Health and Informatics
Pages382-386
Volume281
ISBN (Electronic)978-1-64368-185-6
DOIs
Publication statusPublished - 27 May 2021

Publication series

NameStudies in health technology and informatics

Keywords

  • Feature Selection
  • Machine-Learning
  • Metagenomics

Fingerprint Dive into the research topics of 'Machine Learning Algorithms Reveals Country-Specific Metagenomic Taxa from American Gut Project Data'. Together they form a unique fingerprint.

Cite this