MetaMarker: A pipeline for de novo discovery of novel metagenomic biomarkers

Research output: Contribution to journalArticle

Abstract

Summary: We present MetaMarker, a pipeline for discovering metagenomic biomarkers from whole-metagenome sequencing samples. Different from existing methods, MetaMarker is based on a de novo approach that does not require mapping raw reads to a reference database. We applied MetaMarker on whole-metagenome sequencing of colorectal cancer (CRC) stool samples from France to discover CRC specific metagenomic biomarkers. We showed robustness of the discovered biomarkers by validating in independent samples from Hong Kong, Austria, Germany and Denmark. We further demonstrated these biomarkers could be used to build a machine learning classifier for CRC prediction. Availability and implementation: MetaMarker is freely available at https://bitbucket.org/mkoohim/metamarker under GPLv3 license. Supplementary information: Supplementary data are available at Bioinformatics online.

Original languageEnglish (US)
Pages (from-to)3812-3814
Number of pages3
JournalBioinformatics
Volume35
Issue number19
DOIs
StatePublished - Oct 1 2019

Fingerprint

Metagenomics
Biomarkers
Colorectal Cancer
Pipelines
Metagenome
Colorectal Neoplasms
Sequencing
Austria
Hong Kong
Denmark
Licensure
Bioinformatics
Computational Biology
France
Germany
Learning systems
Machine Learning
Classifiers
Availability
Classifier

ASJC Scopus subject areas

  • Statistics and Probability
  • Biochemistry
  • Molecular Biology
  • Computer Science Applications
  • Computational Theory and Mathematics
  • Computational Mathematics

Cite this

MetaMarker : A pipeline for de novo discovery of novel metagenomic biomarkers. / Koohi-Moghadam, Mohamad; Borad, Mitesh J.; Tran, Nhan L.; Swanson, Kristin R.; Boardman, Lisa A.; Sun, Hongzhe; Wang, Junwen.

In: Bioinformatics, Vol. 35, No. 19, 01.10.2019, p. 3812-3814.

Research output: Contribution to journalArticle

@article{acabde20f91040169e1827f1f3ea18c0,
title = "MetaMarker: A pipeline for de novo discovery of novel metagenomic biomarkers",
abstract = "Summary: We present MetaMarker, a pipeline for discovering metagenomic biomarkers from whole-metagenome sequencing samples. Different from existing methods, MetaMarker is based on a de novo approach that does not require mapping raw reads to a reference database. We applied MetaMarker on whole-metagenome sequencing of colorectal cancer (CRC) stool samples from France to discover CRC specific metagenomic biomarkers. We showed robustness of the discovered biomarkers by validating in independent samples from Hong Kong, Austria, Germany and Denmark. We further demonstrated these biomarkers could be used to build a machine learning classifier for CRC prediction. Availability and implementation: MetaMarker is freely available at https://bitbucket.org/mkoohim/metamarker under GPLv3 license. Supplementary information: Supplementary data are available at Bioinformatics online.",
author = "Mohamad Koohi-Moghadam and Borad, {Mitesh J.} and Tran, {Nhan L.} and Swanson, {Kristin R.} and Boardman, {Lisa A.} and Hongzhe Sun and Junwen Wang",
year = "2019",
month = "10",
day = "1",
doi = "10.1093/bioinformatics/btz123",
language = "English (US)",
volume = "35",
pages = "3812--3814",
journal = "Bioinformatics",
issn = "1367-4803",
publisher = "Oxford University Press",
number = "19",

}

TY - JOUR

T1 - MetaMarker

T2 - A pipeline for de novo discovery of novel metagenomic biomarkers

AU - Koohi-Moghadam, Mohamad

AU - Borad, Mitesh J.

AU - Tran, Nhan L.

AU - Swanson, Kristin R.

AU - Boardman, Lisa A.

AU - Sun, Hongzhe

AU - Wang, Junwen

PY - 2019/10/1

Y1 - 2019/10/1

N2 - Summary: We present MetaMarker, a pipeline for discovering metagenomic biomarkers from whole-metagenome sequencing samples. Different from existing methods, MetaMarker is based on a de novo approach that does not require mapping raw reads to a reference database. We applied MetaMarker on whole-metagenome sequencing of colorectal cancer (CRC) stool samples from France to discover CRC specific metagenomic biomarkers. We showed robustness of the discovered biomarkers by validating in independent samples from Hong Kong, Austria, Germany and Denmark. We further demonstrated these biomarkers could be used to build a machine learning classifier for CRC prediction. Availability and implementation: MetaMarker is freely available at https://bitbucket.org/mkoohim/metamarker under GPLv3 license. Supplementary information: Supplementary data are available at Bioinformatics online.

AB - Summary: We present MetaMarker, a pipeline for discovering metagenomic biomarkers from whole-metagenome sequencing samples. Different from existing methods, MetaMarker is based on a de novo approach that does not require mapping raw reads to a reference database. We applied MetaMarker on whole-metagenome sequencing of colorectal cancer (CRC) stool samples from France to discover CRC specific metagenomic biomarkers. We showed robustness of the discovered biomarkers by validating in independent samples from Hong Kong, Austria, Germany and Denmark. We further demonstrated these biomarkers could be used to build a machine learning classifier for CRC prediction. Availability and implementation: MetaMarker is freely available at https://bitbucket.org/mkoohim/metamarker under GPLv3 license. Supplementary information: Supplementary data are available at Bioinformatics online.

UR - http://www.scopus.com/inward/record.url?scp=85072717584&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85072717584&partnerID=8YFLogxK

U2 - 10.1093/bioinformatics/btz123

DO - 10.1093/bioinformatics/btz123

M3 - Article

C2 - 30825371

AN - SCOPUS:85072717584

VL - 35

SP - 3812

EP - 3814

JO - Bioinformatics

JF - Bioinformatics

SN - 1367-4803

IS - 19

ER -