DCVBin: a novel binning method for single-sample metagenomes based on DNA language model and variational autoencoder
Briefings in Bioinformatics · 04.05.2026 · 27 (3)
DOI: 10.1093/bib/bbag241 ↗Kurz gefasst
Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 19.05.2026. Verfasst von Jingyuan Wang und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Artificial Intelligence, Jilin University, Qianjin Street No. 3003, 130000, Changchun, Jilin, China. Hauptthemen laut MEDLINE: Metagenomics, Metagenome. Die Arbeit nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National Natural Science Foundation of China, Science and Technology Development Plan Project of Jilin Province, China, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
DNA contigs binning is necessary to reconstruct metagenome-assembled genomes. Current metagenomic DNA contigs binning methods often leverage coverage profiles across multiple related metagenomes and have demonstrated strong performance on co-assembled contigs. However, in single-sample scenarios where coverage information is rare, their performance drops significantly, limiting the in-depth development of metagenomics at the individual sample level. To address this issue, we propose DCVBin, a novel single-sample metagenomic contigs binning method that incorporates semantic features extracted from a DNA language model. Specifically, our approach continues pretraining on a DNA language model to capture more domain-specific semantic representations, which are then integrated with 4-mer frequencies using a variational autoencoder. Clustering is subsequently performed using the k-means algorithm, in which the number of clusters is determined by single copy genes. Experimental results on six publicly available datasets demonstrate that DCVBin achieves high-accuracy single-sample metagenomic binning and outperforms other state-of-the-art methods. Furthermore, DCVBin is included into a disease diagnostic framework that is evaluated on a cohort of gut metagenomes from people with colorectal cancer and healthy people. The framework is shown to be accurate in predicting colorectal cancer using gut metagenomes and has identified a list of potential microbial biomarkers.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Artificial Intelligence, Jilin University, Qianjin Street No. 3003, 130000, Changchun, Jilin, China.
- School of Electrical and Information Engineering, Jilin Engineering Normal University, Kaixuan Road No. 3050, 130000, Changchun, Jilin, China.
- College of Communication Engineering, Jilin University, Remin Street No. 5988, 130000, Changchun, Jilin, China.
ORCID-Profile: Yun Liu
Förderung
- National Natural Science Foundation of China
- Science and Technology Development Plan Project of Jilin Province, China
- Fundamental Research Funds for the Central Universities
Zitieren
APA
Wang, J., Liu, Y., Liu, F., Hou, T., Chen, S., Liu, S., & Liu, Y. (2026). DCVBin: a novel binning method for single-sample metagenomes based on DNA language model and variational autoencoder. Briefings in Bioinformatics, 27(3). https://doi.org/10.1093/bib/bbag241
Vancouver
Wang J, Liu Y, Liu F, Hou T, Chen S, Liu S, et al. DCVBin: a novel binning method for single-sample metagenomes based on DNA language model and variational autoencoder. Briefings in Bioinformatics. 2026;27(3). doi:10.1093/bib/bbag241
BibTeX
@article{Wang2026,
author = {Wang, Jingyuan and Liu, Yifan and Liu, Fu and Hou, Tao and Chen, Siming and Liu, Shengxi and Liu, Yun},
title = {DCVBin: a novel binning method for single-sample metagenomes based on DNA language model and variational autoencoder},
journal = {Briefings in Bioinformatics},
year = {2026},
volume = {27},
number = {3},
doi = {10.1093/bib/bbag241}
}
EUVIMED