2022
DOI: 10.1109/access.2022.3176954
|View full text |Cite
|
Sign up to set email alerts
|

A Deep Embedded Clustering Algorithm for the Binning of Metagenomic Sequences

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
6
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
4
2

Relationship

0
6

Authors

Journals

citations
Cited by 8 publications
(6 citation statements)
references
References 24 publications
0
6
0
Order By: Relevance
“…To extract features, methods like CNN can be used for taxonomic classification[ 106 109 110 ]. Autoencoders are used by MetaDEC [ 111 ], which groups reads together by creating a graph where the nodes are reads, linked if they exhibit significant overlap in their substrings. Subsequently, clusters are extracted from this graph.…”
Section: Resultsmentioning
confidence: 99%
“…To extract features, methods like CNN can be used for taxonomic classification[ 106 109 110 ]. Autoencoders are used by MetaDEC [ 111 ], which groups reads together by creating a graph where the nodes are reads, linked if they exhibit significant overlap in their substrings. Subsequently, clusters are extracted from this graph.…”
Section: Resultsmentioning
confidence: 99%
“…VAMB showed improvements in the reconstruction of near-complete strains over multiple datasets, with a performance increase of 29% to 98% on simulated datasets and 45% on real data compared to other state-of-the-art metagenomic binning methods, such as MetaBAT2, MaxBin2, and Canopy. Other recent approaches further explore deep learning algorithms to learn contig embeddings [15], [16].…”
Section: Prior Workmentioning
confidence: 99%
“…MeShClust v3.0 [18] uses the mean shift algorithm and alignment-free identity scores for the sake of not paying precious time due to the costly global alignment algorithm. MetaDEC [19] applies a deep unsupervised learning approach to cluster metagenomic DNA strands. MM-seqs2 [20] uses a graph-based approach, in which every noisy copy is a vertex, and two noisy copies are connected if they satisfy a particular similarity criteria.…”
Section: Related Workmentioning
confidence: 99%