Adversarial and variational autoencoders improve metagenomic binning

Líndez, Pau Piera; Johansen, Joachim; Kutuzova, Svetlana; Sigurdsson, Arnor Ingi; Nissen, Jakob Nybo; Rasmussen, Simon

doi:10.1038/s42003-023-05452-3

Cited by 5 publications

(3 citation statements)

References 32 publications

(45 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Contigs longer than 1 kb were selected for metagenomic binning. We utilized multiple toolkits to recover high-quality MAGs, each sample assembly or co-assembly was binned using a combination of several tools including BASALT (via MetaBAT2 v2.12.1, MaxBin2 v.2.2.4, and CONCOCT v1.1.0 with more-sensitivity parameter) 37 – 40 , metaWRAP (via MetaBAT2 v2.12.1 and CONCOCT v1.1.0) 41 , MetaBinner v1.4.4 42 , MetaCoAG v1.1 43 , SemiBin v1.5.1 (single_easy_bin,–self-supervised) 44 , Vamb v4.1.0 45 and MetaDecoder v1.0.18 46 with default parameters. The resulting bins were then pre-assessed and quality-filtered using MDMcleaner v0.8.7 47 , retaining only bins with completeness ≥50% and contamination ≤10%.…”

Section: Methodsmentioning

confidence: 99%

Recovery of 1887 metagenome-assembled genomes from the South China Sea

Xu,

Huang,

Chen

et al. 2024

Sci Data

View full text Add to dashboard Cite

The South China Sea (SCS) is a marginal sea characterized by strong land-sea biogeochemical interactions. SCS has a distinctive landscape with a multitude of seamounts in its basin. Seamounts create “seamount effects” that influence the diversity and distribution of planktonic microorganisms in the surrounding oligotrophic waters. Although the vertical distribution and community structure of marine microorganisms have been explored in certain regions of the global ocean, there is a lack of comprehensive microbial genomic surveys for uncultured microorganisms in SCS, particularly in the seamount regions. Here, we employed a metagenomic approach to study the uncultured microbial communities sampled from the Xianbei seamount region to the North Coast waters of SCS. A total of 1887 non-redundant prokaryotic metagenome-assembled genomes (MAGs) were reconstructed, of which, 153 MAGs were classified as high-quality MAGs based on the MIMAG standards. The community structure and genomic information provided by this dataset could be used to analyze microbial distribution and metabolism in the SCS.

show abstract

Section: Methodsmentioning

confidence: 99%

Recovery of 1887 metagenome-assembled genomes from the South China Sea

Xu,

Huang,

Chen

et al. 2024

Sci Data

View full text Add to dashboard Cite

show abstract

“…All the metagenomic assemblies obtained for each metagenome were de novo binned separately using MetaBAT2 v2.2.15 (Kang et al, 2019), AVAMB v4.0.0.DEV (Líndez et al, 2023), MetaCoAg v1.1.1 (Mallawaarachchi and Lin, 2022), SemiBin2 v1.5.1 in self-supervised mode (Pan et al, 2023), MetaDecoder v1.0.17 (Liu et al, 2022), and CONCOCT v1.1.0 (Alneberg et al, 2014). All binning processes were executed with default parameters and 139,808 as the initial seed.…”

Section: Methodsmentioning

confidence: 99%

Life on the edge: microbial diversity, resistome, and virulome in soils from the Union Glacier cold desert

Arros,

Palma,

Gálvez-Silva

et al. 2024

Preprint

View full text Add to dashboard Cite

The high-latitude regions of Antarctica remain among the most remote, extreme, and least explored areas on Earth. Despite the highly restrictive conditions, microbial life has been found in these environments, although with limited information on their genetic properties and functional capabilities. Moreover, the accelerated melting of the Antarctic permafrost, the increasing exposure of soils, and the growing human transit pose the question of whether these environments could be a source of microbes or genes that could emerge and cause global health problems. In this line, although a high bacterial diversity and autochthonous multidrug-resistant bacteria have been found in soils of the Antarctic Peninsula, we still lack information regarding the resistome of areas closer to the South Pole. Moreover, no previous studies have evaluated the pathogenic potential of microbes inhabiting Antarctic soils. In this work, we combined metagenomic and culture-dependent approaches to investigate the microbial diversity, resistome, virulome, and mobile genetic elements (MGEs) in soils from Union Glacier, a high-latitude cold desert in West Antarctica. Despite the low organic matter content, diverse bacterial lineages were found, predominating Actinomycetota and Pseudomonadota, with limited archaeal and fungal taxa. We recovered more than 80 species-level representative genomes (SRGs) of predominant bacterial taxa and the archaeon Nitrosocosmicus sp. Diverse putative resistance and virulence genes were predicted among the SRGs, metagenomic reads, and contigs. Furthermore, we characterized bacterial isolates resistant to up to 24 clinical antibiotics, mainly Pseudomonas, Arthrobacter, Plantibacter, and Flavobacterium. Moreover, some isolates produced putative virulence factors, including siderophores, pyocyanins, and exoenzymes with hemolytic, lecithinase, protease, and DNAse activity. This evidence uncovers a largely unexplored resistome and virulome hosted by deep Antarctica's soil microbial communities and the presence of bacteria with pathogenic potential, highlighting the relevance of One Health approaches for environmental surveillance in the white continent.

show abstract

“…k -means, k -medoids and DBSCAN) [ 57–65 ], traditional machine learning techniques (label propagation and Gaussian mixture models) [ 19 , 66–68 ] and deep learning techniques (variational autoencoders [ 69 , 70 ], Siamese neural networks [ 71 , 72 ]. adversarial autoencoders [ 73 ] and feed-forward neural networks [ 74 ]) to bin sequences.…”

Section: Features Used In Metagenomic Binningmentioning

confidence: 99%

Solving genomic puzzles: computational methods for metagenomic binning

Mallawaarachchi,

Wickramarachchi,

Xue

et al. 2024

Briefings in Bioinformatics

View full text Add to dashboard Cite

Metagenomics involves the study of genetic material obtained directly from communities of microorganisms living in natural environments. The field of metagenomics has provided valuable insights into the structure, diversity and ecology of microbial communities. Once an environmental sample is sequenced and processed, metagenomic binning clusters the sequences into bins representing different taxonomic groups such as species, genera, or higher levels. Several computational tools have been developed to automate the process of metagenomic binning. These tools have enabled the recovery of novel draft genomes of microorganisms allowing us to study their behaviors and functions within microbial communities. This review classifies and analyzes different approaches of metagenomic binning and different refinement, visualization, and evaluation techniques used by these methods. Furthermore, the review highlights the current challenges and areas of improvement present within the field of research.

show abstract

Adversarial and variational autoencoders improve metagenomic binning

Cited by 5 publications

References 32 publications

Recovery of 1887 metagenome-assembled genomes from the South China Sea

Recovery of 1887 metagenome-assembled genomes from the South China Sea

Life on the edge: microbial diversity, resistome, and virulome in soils from the Union Glacier cold desert

Solving genomic puzzles: computational methods for metagenomic binning

Contact Info

Product

Resources

About