Microbiome meta-analysis and cross-disease comparison enabled by the SIAMCAT machine learning toolbox

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 v...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Genome Biology Jg. 22; H. 1; S. 93
Hauptverfasser: Wirbel, Jakob, Zych, Konrad, Essex, Morgan, Karcher, Nicolai, Kartal, Ece, Salazar, Guillem, Bork, Peer, Sunagawa, Shinichi, Zeller, Georg
Format: Journal Article
Sprache:Englisch
Veröffentlicht: London BioMed Central 30.03.2021
Springer Nature B.V
BMC
Schlagworte:
Algorithms
Animal Genetics and Genomics
Bioinformatics
Biomarkers
Biomedical and Life Sciences
Computational Biology - methods
computer software
Confounding Factors, Epidemiologic
Crohn Disease - etiology
Databases, Genetic
Datasets
Evolutionary Biology
Gastrointestinal Microbiome
genome
Human Genetics
Humans
Inflammatory bowel disease
Learning algorithms
Life Sciences
Machine Learning
Meta-analysis
Meta-Analysis as Topic
Metagenome
Metagenomics
Metagenomics - methods
Microbial Genetics and Genomics
microbiome
Microbiome data analysis
Microbiome-wide association studies (MWAS)
Microbiomes
Microbiota
Models, Statistical
Plant Genetics and Genomics
ROC Curve
Software
Statistical analysis
Statistical modeling
Taxonomy
therapeutics
Variables
Workflow
Statistical modeling
Microbiome data analysis
Microbiome-wide association studies (MWAS)
Machine learning
Meta-analysis
ISSN:1474-760X, 1474-7596, 1474-760X
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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 .
Bibliographie:ObjectType-Article-2
SourceType-Scholarly Journals-1
content type line 14
ObjectType-Feature-3
ObjectType-Evidence Based Healthcare-1
ObjectType-Article-1
ObjectType-Feature-2
content type line 23
ISSN:1474-760X
1474-7596
1474-760X
DOI:10.1186/s13059-021-02306-1