A metagenomics approach to investigate microbiome sociobiology

Andersen, Sandra Breum; Schluter, Jonas

doi:10.1073/pnas.2100934118

Cited by 3 publications

(2 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This so-called “cultivation bottleneck” limits culturing approaches to studying microbes 1 . In contrast, metagenomics enables culture-free microbial diversity characterization by analysing the entire set of genomes present in a given environmental sample 3 . Unfortunately, despite advances in sequencing throughput and bioinformatic tooling, reconstructing high-quality genomes from short-read sequenced metagenomics samples remains challenging 4 .…”

Section: Introductionmentioning

confidence: 99%

Adversarial and variational autoencoders improve metagenomic binning

Líndez,

Johansen,

Kutuzova

et al. 2023

Commun Biol

View full text Add to dashboard Cite

Assembly of reads from metagenomic samples is a hard problem, often resulting in highly fragmented genome assemblies. Metagenomic binning allows us to reconstruct genomes by re-grouping the sequences by their organism of origin, thus representing a crucial processing step when exploring the biological diversity of metagenomic samples. Here we present Adversarial Autoencoders for Metagenomics Binning (AAMB), an ensemble deep learning approach that integrates sequence co-abundances and tetranucleotide frequencies into a common denoised space that enables precise clustering of sequences into microbial genomes. When benchmarked, AAMB presented similar or better results compared with the state-of-the-art reference-free binner VAMB, reconstructing ~7% more near-complete (NC) genomes across simulated and real data. In addition, genomes reconstructed using AAMB had higher completeness and greater taxonomic diversity compared with VAMB. Finally, we implemented a pipeline Integrating VAMB and AAMB that enabled improved binning, recovering 20% and 29% more simulated and real NC genomes, respectively, compared to VAMB, with moderate additional runtime.

show abstract

Section: Introductionmentioning

confidence: 99%

Adversarial and variational autoencoders improve metagenomic binning

Líndez,

Johansen,

Kutuzova

et al. 2023

Commun Biol

View full text Add to dashboard Cite

show abstract

“…Microbes can be characterized using traditional culture-dependent approaches ( Fig. 1 A ) that involve the isolation and sequencing of individual microbes from lab-based cultures [3] , [4] . However, some microbes cannot be easily isolated and cultured in vitro due to their complex natural habitats, such as unreproducible environmental, temporal, physical, biochemical and genetic complexities [5] .…”

Section: Introductionmentioning

confidence: 99%

A review of computational tools for generating metagenome-assembled genomes from metagenomic sequencing data

Yang

Chowdhury

Zhang

et al. 2021

Computational and Structural Biotechnology Journal

123

View full text Add to dashboard Cite

show abstract

Adversarial and variational autoencoders improve metagenomic binning

Johansen

Sigurdsson

Nissen

et al. 2023

Preprint

View full text Add to dashboard Cite

Assembly of reads from metagenomic samples is a hard problem, often resulting in highly fragmented genome assemblies. Metagenomic binning allows us to reconstruct genomes by re-grouping the sequences by their organism of origin, thus representing a crucial processing step when exploring the biological diversity of metagenomic samples. Here we present Adversarial Autoencoders for Metagenomics Binning (AAMB), an ensemble deep learning approach that integrates sequence co-abundances and tetranucleotide frequencies into a common denoised space that enables precise clustering of sequences into microbial genomes. When benchmarked, AAMB presented similar or better results compared with the state-of-the-art reference-free binner VAMB, reconstructing ~7% more near-complete (NC) genomes across simulated and real data. In addition, genomes reconstructed using AAMB had higher completeness and greater taxonomic diversity compared with VAMB. Finally, we implemented a pipeline integrating VAMB and AAMB that enabled improved binning, recovering 20% and 29% more simulated and real NC genomes, respectively, compared to VAMB with moderate additional runtime. AAMB is freely available at https://github.com/RasmussenLab/VAMB.

show abstract

A metagenomics approach to investigate microbiome sociobiology

Cited by 3 publications

References 38 publications

Adversarial and variational autoencoders improve metagenomic binning

Adversarial and variational autoencoders improve metagenomic binning

A review of computational tools for generating metagenome-assembled genomes from metagenomic sequencing data

Adversarial and variational autoencoders improve metagenomic binning

Contact Info

Product

Resources

About