Show simple item record

dc.contributor.author
Wirbel, Jakob
dc.contributor.author
Zych, Konrad
dc.contributor.author
Essex, Morgan
dc.contributor.author
Karcher, Nicolai
dc.contributor.author
Kartal, Ece
dc.contributor.author
Salazar, Guillem
dc.contributor.author
Bork, Peer
dc.contributor.author
Sunagawa, Shinichi
dc.contributor.author
Zeller, Georg
dc.date.accessioned
2021-04-12T13:54:12Z
dc.date.available
2021-04-11T02:58:13Z
dc.date.available
2021-04-12T13:54:12Z
dc.date.issued
2021-03-30
dc.identifier.issn
1474-760X
dc.identifier.other
10.1186/s13059-021-02306-1
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/478136
dc.identifier.doi
10.3929/ethz-b-000478136
dc.description.abstract
The human microbiome is increasingly mined for diagnostic and therapeutic biomarkers using machine learning (ML). However, metagenomics-specific software is scarce, and overoptimistic evaluation and limited cross-study generalization are prevailing issues. To address these, we developed SIAMCAT, a versatile R toolbox for ML-based comparative metagenomics. We demonstrate its capabilities in a meta-analysis of fecal metagenomic studies (10,803 samples). When naively transferred across studies, ML models lost accuracy and disease specificity, which could however be resolved by a novel training set augmentation strategy. This reveals some biomarkers to be disease-specific, with others shared across multiple conditions. SIAMCAT is freely available from siamcat.embl.de.
en_US
dc.format
application/pdf
en_US
dc.language.iso
en
en_US
dc.publisher
BioMed Central
dc.rights.uri
http://creativecommons.org/licenses/by/4.0/
dc.subject
Microbiome data analysis
en_US
dc.subject
Machine learning
en_US
dc.subject
Statistical modeling
en_US
dc.subject
Microbiome-wide association studies (MWAS)
en_US
dc.subject
Meta-analysis
en_US
dc.title
Microbiome meta-analysis and cross-disease comparison enabled by the SIAMCAT machine learning toolbox
en_US
dc.type
Journal Article
dc.rights.license
Creative Commons Attribution 4.0 International
ethz.journal.title
Genome Biology
ethz.journal.volume
22
en_US
ethz.journal.issue
1
en_US
ethz.journal.abbreviated
Genome Biol
ethz.pages.start
93
en_US
ethz.size
27 p.
en_US
ethz.version.deposit
publishedVersion
en_US
ethz.identifier.wos
ethz.identifier.scopus
ethz.publication.place
London
ethz.publication.status
published
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02030 - Dep. Biologie / Dep. of Biology::02520 - Institut für Mikrobiologie / Institute of Microbiology::09583 - Sunagawa, Shinichi / Sunagawa, Shinichi
ethz.leitzahl.certified
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02030 - Dep. Biologie / Dep. of Biology::02520 - Institut für Mikrobiologie / Institute of Microbiology::09583 - Sunagawa, Shinichi / Sunagawa, Shinichi
ethz.date.deposited
2021-04-11T02:58:17Z
ethz.source
SCOPUS
ethz.eth
yes
en_US
ethz.availability
Open access
en_US
ethz.rosetta.installDate
2021-04-12T13:54:24Z
ethz.rosetta.lastUpdated
2024-02-02T13:29:50Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Microbiome%20meta-analysis%20and%20cross-disease%20comparison%20enabled%20by%20the%20SIAMCAT%20machine%20learning%20toolbox&rft.jtitle=Genome%20Biology&rft.date=2021-03-30&rft.volume=22&rft.issue=1&rft.spage=93&rft.issn=1474-760X&rft.au=Wirbel,%20Jakob&Zych,%20Konrad&Essex,%20Morgan&Karcher,%20Nicolai&Kartal,%20Ece&rft.genre=article&rft_id=info:doi/10.1186/s13059-021-02306-1&
 Search print copy at ETH Library

Files in this item

Thumbnail

Publication type

Show simple item record