Improved metagenome binning and assembly using deep variational autoencoders

Research output: Contribution to journalJournal articlepeer-review

Standard

Improved metagenome binning and assembly using deep variational autoencoders. / Nissen, Jakob Nybo; Johansen, Joachim; Allesoe, Rosa Lundbye; Sonderby, Casper Kaae; Armenteros, Jose Juan Almagro; Gronbech, Christopher Heje; Jensen, Lars Juhl; Nielsen, Henrik Bjørn; Petersen, Thomas Nordahl; Winther, Ole; Rasmussen, Simon.

In: Nature Biotechnology, Vol. 39, 2021, p. 555-560.

Research output: Contribution to journalJournal articlepeer-review

Harvard

Nissen, JN, Johansen, J, Allesoe, RL, Sonderby, CK, Armenteros, JJA, Gronbech, CH, Jensen, LJ, Nielsen, HB, Petersen, TN, Winther, O & Rasmussen, S 2021, 'Improved metagenome binning and assembly using deep variational autoencoders', Nature Biotechnology, vol. 39, pp. 555-560. https://doi.org/10.1038/s41587-020-00777-4

APA

Nissen, J. N., Johansen, J., Allesoe, R. L., Sonderby, C. K., Armenteros, J. J. A., Gronbech, C. H., Jensen, L. J., Nielsen, H. B., Petersen, T. N., Winther, O., & Rasmussen, S. (2021). Improved metagenome binning and assembly using deep variational autoencoders. Nature Biotechnology, 39, 555-560. https://doi.org/10.1038/s41587-020-00777-4

Vancouver

Nissen JN, Johansen J, Allesoe RL, Sonderby CK, Armenteros JJA, Gronbech CH et al. Improved metagenome binning and assembly using deep variational autoencoders. Nature Biotechnology. 2021;39:555-560. https://doi.org/10.1038/s41587-020-00777-4

Author

Nissen, Jakob Nybo ; Johansen, Joachim ; Allesoe, Rosa Lundbye ; Sonderby, Casper Kaae ; Armenteros, Jose Juan Almagro ; Gronbech, Christopher Heje ; Jensen, Lars Juhl ; Nielsen, Henrik Bjørn ; Petersen, Thomas Nordahl ; Winther, Ole ; Rasmussen, Simon. / Improved metagenome binning and assembly using deep variational autoencoders. In: Nature Biotechnology. 2021 ; Vol. 39. pp. 555-560.

Bibtex

@article{942fe6339c004b539db86f8f8debd21c,
title = "Improved metagenome binning and assembly using deep variational autoencoders",
abstract = "Despite recent advances in metagenomic binning, reconstruction of microbial species from metagenomics data remains challenging. Here we develop variational autoencoders for metagenomic binning (VAMB), a program that uses deep variational autoencoders to encode sequence coabundance and k-mer distribution information before clustering. We show that a variational autoencoder is able to integrate these two distinct data types without any previous knowledge of the datasets. VAMB outperforms existing state-of-the-art binners, reconstructing 29-98% and 45% more near-complete (NC) genomes on simulated and real data, respectively. Furthermore, VAMB is able to separate closely related strains up to 99.5% average nucleotide identity (ANI), and reconstructed 255 and 91 NC Bacteroides vulgatus and Bacteroides dorei sample-specific genomes as two distinct clusters from a dataset of 1,000 human gut microbiome samples. We use 2,606 NC bins from this dataset to show that species of the human gut microbiome have different geographical distribution patterns. VAMB can be run on standard hardware and is freely available at https://github.com/RasmussenLab/vamb.",
keywords = "GENOMES, ALGORITHM, INFORMATION, COVERAGE, BACTERIA",
author = "Nissen, {Jakob Nybo} and Joachim Johansen and Allesoe, {Rosa Lundbye} and Sonderby, {Casper Kaae} and Armenteros, {Jose Juan Almagro} and Gronbech, {Christopher Heje} and Jensen, {Lars Juhl} and Nielsen, {Henrik Bj{\o}rn} and Petersen, {Thomas Nordahl} and Ole Winther and Simon Rasmussen",
year = "2021",
doi = "10.1038/s41587-020-00777-4",
language = "English",
volume = "39",
pages = "555--560",
journal = "Nature Biotechnology",
issn = "1087-0156",
publisher = "nature publishing group",

}

RIS

TY - JOUR

T1 - Improved metagenome binning and assembly using deep variational autoencoders

AU - Nissen, Jakob Nybo

AU - Johansen, Joachim

AU - Allesoe, Rosa Lundbye

AU - Sonderby, Casper Kaae

AU - Armenteros, Jose Juan Almagro

AU - Gronbech, Christopher Heje

AU - Jensen, Lars Juhl

AU - Nielsen, Henrik Bjørn

AU - Petersen, Thomas Nordahl

AU - Winther, Ole

AU - Rasmussen, Simon

PY - 2021

Y1 - 2021

N2 - Despite recent advances in metagenomic binning, reconstruction of microbial species from metagenomics data remains challenging. Here we develop variational autoencoders for metagenomic binning (VAMB), a program that uses deep variational autoencoders to encode sequence coabundance and k-mer distribution information before clustering. We show that a variational autoencoder is able to integrate these two distinct data types without any previous knowledge of the datasets. VAMB outperforms existing state-of-the-art binners, reconstructing 29-98% and 45% more near-complete (NC) genomes on simulated and real data, respectively. Furthermore, VAMB is able to separate closely related strains up to 99.5% average nucleotide identity (ANI), and reconstructed 255 and 91 NC Bacteroides vulgatus and Bacteroides dorei sample-specific genomes as two distinct clusters from a dataset of 1,000 human gut microbiome samples. We use 2,606 NC bins from this dataset to show that species of the human gut microbiome have different geographical distribution patterns. VAMB can be run on standard hardware and is freely available at https://github.com/RasmussenLab/vamb.

AB - Despite recent advances in metagenomic binning, reconstruction of microbial species from metagenomics data remains challenging. Here we develop variational autoencoders for metagenomic binning (VAMB), a program that uses deep variational autoencoders to encode sequence coabundance and k-mer distribution information before clustering. We show that a variational autoencoder is able to integrate these two distinct data types without any previous knowledge of the datasets. VAMB outperforms existing state-of-the-art binners, reconstructing 29-98% and 45% more near-complete (NC) genomes on simulated and real data, respectively. Furthermore, VAMB is able to separate closely related strains up to 99.5% average nucleotide identity (ANI), and reconstructed 255 and 91 NC Bacteroides vulgatus and Bacteroides dorei sample-specific genomes as two distinct clusters from a dataset of 1,000 human gut microbiome samples. We use 2,606 NC bins from this dataset to show that species of the human gut microbiome have different geographical distribution patterns. VAMB can be run on standard hardware and is freely available at https://github.com/RasmussenLab/vamb.

KW - GENOMES

KW - ALGORITHM

KW - INFORMATION

KW - COVERAGE

KW - BACTERIA

U2 - 10.1038/s41587-020-00777-4

DO - 10.1038/s41587-020-00777-4

M3 - Journal article

C2 - 33398153

VL - 39

SP - 555

EP - 560

JO - Nature Biotechnology

JF - Nature Biotechnology

SN - 1087-0156

ER -

ID: 255684029