Predictive and comparative network analysis of the gut microbiota in type 2 diabetes

Mostafa Abbas, Yasser El-Manzalawy

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Metagenome-wide analysis studies provide a unique set of microbial features for biomarker discovery of associated disease as well as for studying diversity and dynamics of microbial communities under different conditions. Taxonomic classification of microbes in metagenomic samples quantifies what microbes are present and in what proportion. Despite the availably of several computational taxonomy profiling methods, this crucial step in metagenome-wide analysis remains very challenging and how using different taxonomy profiling methods might influence the outcome of the analysis is not wellstudied. In this work, we consider three taxonomy profiling methods (MetaPhlAn2, Kraken, and EBI metagenomics pipeline) and examine their effect on the outcome of metagenome-wide analysis based on machine learning and comparative network approaches. Our results suggest that Kraken OTU-based data representation yields the best performing classifiers even using less number of features (e.g., OTUs). In addition, our preliminary results underscore the viability of leveraging multiple taxonomic classification methods in microbial network analysis. Finally, our analysis results are consistent with the current knowledge and reveal novel insights into interaction relationships between potential biomarkers in the gut microbiome associated with T2D.

Original languageEnglish
Title of host publicationACM-BCB 2017 - Proceedings of the 8th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics
PublisherAssociation for Computing Machinery, Inc
Pages313-320
Number of pages8
ISBN (Electronic)9781450347228
DOIs
Publication statusPublished - 20 Aug 2017
Event8th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics, ACM-BCB 2017 - Boston, United States
Duration: 20 Aug 201723 Aug 2017

Other

Other8th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics, ACM-BCB 2017
CountryUnited States
CityBoston
Period20/8/1723/8/17

Fingerprint

Taxonomies
Medical problems
Electric network analysis
Type 2 Diabetes Mellitus
Metagenome
Biomarkers
Metagenomics
Learning systems
Classifiers
Pipelines
Gastrointestinal Microbiome

Keywords

  • Comparative network analysis
  • Metagenomics
  • Predictive analytics
  • Type 2 diabetes

ASJC Scopus subject areas

  • Software
  • Biomedical Engineering
  • Health Informatics
  • Computer Science Applications

Cite this

Abbas, M., & El-Manzalawy, Y. (2017). Predictive and comparative network analysis of the gut microbiota in type 2 diabetes. In ACM-BCB 2017 - Proceedings of the 8th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics (pp. 313-320). Association for Computing Machinery, Inc. https://doi.org/10.1145/3107411.3107472

Predictive and comparative network analysis of the gut microbiota in type 2 diabetes. / Abbas, Mostafa; El-Manzalawy, Yasser.

ACM-BCB 2017 - Proceedings of the 8th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics. Association for Computing Machinery, Inc, 2017. p. 313-320.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abbas, M & El-Manzalawy, Y 2017, Predictive and comparative network analysis of the gut microbiota in type 2 diabetes. in ACM-BCB 2017 - Proceedings of the 8th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics. Association for Computing Machinery, Inc, pp. 313-320, 8th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics, ACM-BCB 2017, Boston, United States, 20/8/17. https://doi.org/10.1145/3107411.3107472
Abbas M, El-Manzalawy Y. Predictive and comparative network analysis of the gut microbiota in type 2 diabetes. In ACM-BCB 2017 - Proceedings of the 8th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics. Association for Computing Machinery, Inc. 2017. p. 313-320 https://doi.org/10.1145/3107411.3107472
Abbas, Mostafa ; El-Manzalawy, Yasser. / Predictive and comparative network analysis of the gut microbiota in type 2 diabetes. ACM-BCB 2017 - Proceedings of the 8th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics. Association for Computing Machinery, Inc, 2017. pp. 313-320
@inproceedings{32d2bffee39b4286ac97955c49522d17,
title = "Predictive and comparative network analysis of the gut microbiota in type 2 diabetes",
abstract = "Metagenome-wide analysis studies provide a unique set of microbial features for biomarker discovery of associated disease as well as for studying diversity and dynamics of microbial communities under different conditions. Taxonomic classification of microbes in metagenomic samples quantifies what microbes are present and in what proportion. Despite the availably of several computational taxonomy profiling methods, this crucial step in metagenome-wide analysis remains very challenging and how using different taxonomy profiling methods might influence the outcome of the analysis is not wellstudied. In this work, we consider three taxonomy profiling methods (MetaPhlAn2, Kraken, and EBI metagenomics pipeline) and examine their effect on the outcome of metagenome-wide analysis based on machine learning and comparative network approaches. Our results suggest that Kraken OTU-based data representation yields the best performing classifiers even using less number of features (e.g., OTUs). In addition, our preliminary results underscore the viability of leveraging multiple taxonomic classification methods in microbial network analysis. Finally, our analysis results are consistent with the current knowledge and reveal novel insights into interaction relationships between potential biomarkers in the gut microbiome associated with T2D.",
keywords = "Comparative network analysis, Metagenomics, Predictive analytics, Type 2 diabetes",
author = "Mostafa Abbas and Yasser El-Manzalawy",
year = "2017",
month = "8",
day = "20",
doi = "10.1145/3107411.3107472",
language = "English",
pages = "313--320",
booktitle = "ACM-BCB 2017 - Proceedings of the 8th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics",
publisher = "Association for Computing Machinery, Inc",

}

TY - GEN

T1 - Predictive and comparative network analysis of the gut microbiota in type 2 diabetes

AU - Abbas, Mostafa

AU - El-Manzalawy, Yasser

PY - 2017/8/20

Y1 - 2017/8/20

N2 - Metagenome-wide analysis studies provide a unique set of microbial features for biomarker discovery of associated disease as well as for studying diversity and dynamics of microbial communities under different conditions. Taxonomic classification of microbes in metagenomic samples quantifies what microbes are present and in what proportion. Despite the availably of several computational taxonomy profiling methods, this crucial step in metagenome-wide analysis remains very challenging and how using different taxonomy profiling methods might influence the outcome of the analysis is not wellstudied. In this work, we consider three taxonomy profiling methods (MetaPhlAn2, Kraken, and EBI metagenomics pipeline) and examine their effect on the outcome of metagenome-wide analysis based on machine learning and comparative network approaches. Our results suggest that Kraken OTU-based data representation yields the best performing classifiers even using less number of features (e.g., OTUs). In addition, our preliminary results underscore the viability of leveraging multiple taxonomic classification methods in microbial network analysis. Finally, our analysis results are consistent with the current knowledge and reveal novel insights into interaction relationships between potential biomarkers in the gut microbiome associated with T2D.

AB - Metagenome-wide analysis studies provide a unique set of microbial features for biomarker discovery of associated disease as well as for studying diversity and dynamics of microbial communities under different conditions. Taxonomic classification of microbes in metagenomic samples quantifies what microbes are present and in what proportion. Despite the availably of several computational taxonomy profiling methods, this crucial step in metagenome-wide analysis remains very challenging and how using different taxonomy profiling methods might influence the outcome of the analysis is not wellstudied. In this work, we consider three taxonomy profiling methods (MetaPhlAn2, Kraken, and EBI metagenomics pipeline) and examine their effect on the outcome of metagenome-wide analysis based on machine learning and comparative network approaches. Our results suggest that Kraken OTU-based data representation yields the best performing classifiers even using less number of features (e.g., OTUs). In addition, our preliminary results underscore the viability of leveraging multiple taxonomic classification methods in microbial network analysis. Finally, our analysis results are consistent with the current knowledge and reveal novel insights into interaction relationships between potential biomarkers in the gut microbiome associated with T2D.

KW - Comparative network analysis

KW - Metagenomics

KW - Predictive analytics

KW - Type 2 diabetes

UR - http://www.scopus.com/inward/record.url?scp=85031319773&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85031319773&partnerID=8YFLogxK

U2 - 10.1145/3107411.3107472

DO - 10.1145/3107411.3107472

M3 - Conference contribution

SP - 313

EP - 320

BT - ACM-BCB 2017 - Proceedings of the 8th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics

PB - Association for Computing Machinery, Inc

ER -