DecBin: Bayesian-optimized deep clustering for long-read metagenomic binning
Briefings in Bioinformatics · 2026
DOI: 10.1093/bib/bbag571 ↗Kurz gefasst
Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2026. Verfasst von Yi-Heng Zhu und 6 weiteren Autor:innen. Beteiligte Einrichtung: College of Artificial Intelligence, Nanjing Agricultural University, 666 Binjiang Avenue, Jiangbei New District, Nanjing, Jiangsu 211800, China. Hauptthemen laut MEDLINE: Metagenomics, Metagenome. Die Arbeit nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fundamental Research Funds for the Central Universities, Natural Science Foundation of Jiangsu Province, National Natural Science Foundation of China.
Abstract (Originalsprache)
Accurate metagenomic binning is essential for reconstructing microbial genomes, thereby facilitating the discovery of novel taxa, the identification of pathogens, and the characterization of antimicrobial resistance genes. Most existing methods are designed for assembled contigs and cannot be directly applied to raw long reads. Although a few dedicated long-read binning methods have emerged, challenges remain in bin-number estimation and representation learning. Here, we propose Deep Embedded Clustering for Long-read Binning (DecBin), an adaptive method for directly binning raw long reads through integrating a variational autoencoder (VAE), Bayesian optimization, and deep embedded clustering within a unified framework. Computational experiments on large-scale simulated and mock-community datasets demonstrate that DecBin outperforms state-of-the-art methods in both long-read binning and metagenome-assembled genome recovery, while also achieving strain-level resolution in a low-complexity natural microbiome. Further analysis shows that the advantage of DecBin is partly attributable to its Davies–Bouldin index-guided Bayesian optimization, which explicitly evaluates candidate cluster numbers using a global cluster-validity criterion, thereby improving bin-number estimation across communities of varying complexity. Meanwhile, joint fine-tuning of the VAE encoder and clustering layer enables clustering feedback to refine the latent space, yielding representations better aligned with genome partitions. These findings highlight the potential of adaptive deep clustering for metagenomic binning directly from raw long reads without prior assembly. The source code of DecBin is freely available at https://github.com/LorMeBioAI/DecBin.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Artificial Intelligence, Nanjing Agricultural University, 666 Binjiang Avenue, Jiangbei New District, Nanjing, Jiangsu 211800, China.
- Jiangsu Provincial Key Lab for Organic-based Fertilizer Creation and Soil Health Manipulation, Jiangsu Collaborative Innovation Center of Solid Organic Wastes, Educational Ministry Engineering Center of Resource-Saving…
ORCID-Profile: Yi-Heng Zhu, Xinchi Li, Gaofei Jiang
Förderung
- Fundamental Research Funds for the Central Universities
- Natural Science Foundation of Jiangsu Province
- National Natural Science Foundation of China
Zitieren
APA
Zhu, Y. H., Li, X., Liu, Z., Liu, J., Ye, R., Xue, W., & Jiang, G. (2026). DecBin: Bayesian-optimized deep clustering for long-read metagenomic binning. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbag571
Vancouver
Zhu YH, Li X, Liu Z, Liu J, Ye R, Xue W, et al. DecBin: Bayesian-optimized deep clustering for long-read metagenomic binning. Briefings in Bioinformatics. 2026. doi:10.1093/bib/bbag571
BibTeX
@article{Zhu2026,
author = {Zhu, Yi-Heng and Li, Xinchi and Liu, Zuo and Liu, Jing and Ye, Rui and Xue, Wei and Jiang, Gaofei},
title = {DecBin: Bayesian-optimized deep clustering for long-read metagenomic binning},
journal = {Briefings in Bioinformatics},
year = {2026},
doi = {10.1093/bib/bbag571}
}
EUVIMED