MB-GAN: Microbiome Simulation via Generative Adversarial Network
Open Access
- 29 January 2021
- journal article
- research article
- Published by Oxford University Press (OUP) in GigaScience
- Vol. 10 (2)
- https://doi.org/10.1093/gigascience/giab005
Abstract
Trillions of microbes inhabit the human body and have a profound effect on human health. The recent development of metagenome-wide association studies and other quantitative analysis methods accelerate the discovery of the associations between human microbiome and diseases. To assess the strengths and limitations of these analytical tools, simulating realistic microbiome datasets is critically important. However, simulating the real microbiome data is challenging because it is difficult to model their correlation structure using explicit statistical models. To address the challenge of simulating realistic microbiome data, we designed a novel simulation framework termed MB-GAN, by using a generative adversarial network (GAN) and utilizing methodology advancements from the deep learning community. MB-GAN can automatically learn from given microbial abundances and compute simulated abundances that are indistinguishable from them. In practice, MB-GAN showed the following advantages. First, MB-GAN avoids explicit statistical modeling assumptions, and it only requires real datasets as inputs. Second, unlike the traditional GANs, MB-GAN is easily applicable and can converge efficiently. By applying MB-GAN to a case-control gut microbiome study of 396 samples, we demonstrated that the simulated data and the original data had similar first-order and second-order properties, including sparsity, diversities, and taxa-taxa correlations. These advantages are suitable for further microbiome methodology development where high-fidelity microbiome data are needed.Keywords
Funding Information
- National Institutes of Health (5P30CA142543, 5R01GM126479, 5R01HG008983, 1R56HG011035)
This publication has 24 references indexed in Scilit:
- Testing in Microbiome-Profiling Studies with MiRKAT, the Microbiome Regression-Based Kernel Association TestAmerican Journal of Human Genetics, 2015
- Microbiome, Metagenomics, and High-Dimensional Compositional Data AnalysisAnnual Review of Statistics and Its Application, 2015
- Proportionality: A Valid Alternative to Correlation for Relative DataPLoS Computational Biology, 2015
- Identification and assembly of genomes and genetic elements in complex metagenomic samples without using reference genomesNature Biotechnology, 2014
- A metagenome-wide association study of gut microbiota in type 2 diabetesNature, 2012
- Microbial Co-occurrence Relationships in the Human MicrobiomePLoS Computational Biology, 2012
- The Phylogenetic Kantorovich–Rubinstein Metric for Environmental Sequence SamplesJournal of the Royal Statistical Society Series B: Statistical Methodology, 2012
- Genotype and SNP calling from next-generation sequencing dataNature Reviews Genetics, 2011
- edgeR: a Bioconductor package for differential expression analysis of digital gene expression dataBioinformatics, 2009
- UniFrac: a New Phylogenetic Method for Comparing Microbial CommunitiesApplied and Environmental Microbiology, 2005