丹麦哥本哈根大学Simon Rasmussen小组的最新研究提出了整合内在特征和分类学改进宏基因组分类。2026年4月27日出版的《自然—生物技术》杂志发表了这项成果。

本文提出了一种基于半监督双峰变分自编码器的元基因组分类工具TaxVAMB，它将四核苷酸频率和连续丰度与分类信息结合起来。TaxVAMB在CAMI2人类微生物组数据集上的表现优于所有其他分类器，比第二好的分类器平均多返回29%的高质量组合，在短读数据集上的表现与最佳分类器相当。在人类肠道长读数据集上，TaxVAMB多回收了29%的高质量样本。在典型的单样本设置中，与VAMB相比，TaxVAMB平均返回83%的高质量箱子。最后，TaxVAMB对不完整基因组的分类比其他任何工具都好，平均比第二好的分类器多返回300%的高质量不完整基因组。

据了解，研究微生物组的常用程序是将已测序的基因组组合成元基因组组装的基因组。目前，最先进的分类方法主要以丰度和基于序列的基序（如四核苷酸频率）为主题，而基于比对分类的分类标签尚未得到广泛的应用。

附：英文原文

Title: Improving metagenome binning by integrating intrinsic features and taxonomy

Author: Kutuzova, Svetlana, Piera Lndez, Pau, Danielsen, Lasse Schnell, Nielsen, Knud Nor, Olsen, Nikoline S., Riber, Leise, Gobbi, Alex, Forero-Junco, Laura Milena, Erdmann Dougherty, Peter, Westergaard, Jesper Cairo, Browne, Patrick Denis, Christensen, Svend, Hestbjerg Hansen, Lars, Nielsen, Mads, Nybo Andersen, Jakob, Rasmussen, Simon

Issue&Volume: 2026-04-27

Abstract: A common procedure for studying the microbiome is binning the sequenced contigs into metagenome-assembled genomes. State-of-the-art binning methods use coabundance and sequence-based motifs such as tetranucleotide frequencies, whereas taxonomic labels derived from alignment based classification have not been widely used. Here we propose TaxVAMB, a metagenome binning tool based on semisupervised bimodal variational autoencoders, combining tetranucleotide frequencies and contig coabundances with taxonomic information. TaxVAMB outperformed all other binners on CAMI2 human microbiome datasets, returning on average 29% more high-quality assemblies than the next best binner, and performed on par with the best binners on short-read datasets. On a human gut long-read dataset, TaxVAMB recovered 29% more high-quality bins. In a typical single-sample setup, TaxVAMB on average returns 83% more high-quality bins compared to VAMB. Lastly, TaxVAMB binned incomplete genomes better than any other tool, returning on average 300% more high-quality bins of incomplete genomes than the next best binner.

DOI: 10.1038/s41587-026-03098-0

Source: https://www.nature.com/articles/s41587-026-03098-0