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


Loading...

Date

2021-03-30

Publication Type

Journal Article

ETH Bibliography

yes

Citations

Altmetric

Data

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.

Publication status

published

Editor

Book title

Volume

22 (1)

Pages / Article No.

93

Publisher

BioMed Central

Event

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Microbiome data analysis; Machine learning; Statistical modeling; Microbiome-wide association studies (MWAS); Meta-analysis

Organisational unit

09583 - Sunagawa, Shinichi / Sunagawa, Shinichi check_circle

Notes

Funding

Related publications and datasets