丹麦哥本哈根大学Simon Rasmussen课题组的最新研究利用深度变体自动编码器改进了宏基因组的组装。该项研究成果发表在2021年1月4日出版的《自然-生物技术》上。

研究人员开发了用于宏基因组划分（VAMB）的变体自动编码器，该程序使用深度变体自动编码器在聚类之前对序列多丰度和k-mer分布信息进行编码。研究人员证明了变体自动编码器能够集成这两种不同的数据类型，而无需注释的数据集。VAMB的表现优于现有的最新编辑器，其利用模拟和真实数据分别重建了29-98％、45％或近乎完整（NC）的基因组。

此外，VAMB能够分离出平均核苷酸同一性（ANI）达99.5％的密切相关菌株，并将1,000例人类肠道微生物组样本数据集中的255个和91个NC多形拟杆菌和多雷拟杆菌特异性基因组重构为两个不同的簇。研究人员使用了该数据集的2606个NC库，来揭示人类肠道微生物组种群具有不同的分布模式。VAMB可以在标准计算机上运行，并且可以从https://github.com/RasmussenLab/vamb免费获得。

据介绍，尽管最近的研究在宏基因组学分类方面取得了新进展，但是利用宏基因组学数据重构微生物物种仍然具有挑战性。

附：英文原文

Title: Improved metagenome binning and assembly using deep variational autoencoders

Author: Jakob Nybo Nissen, Joachim Johansen, Rosa Lundbye Allese, Casper Kaae Snderby, Jose Juan Almagro Armenteros, Christopher Heje Grnbech, Lars Juhl Jensen, Henrik Bjrn Nielsen, Thomas Nordahl Petersen, Ole Winther, Simon Rasmussen

Issue&Volume: 2021-01-04

Abstract: Despite recent advances in metagenomic binning, reconstruction of microbial species from metagenomics data remains challenging. Here we develop variational autoencoders for metagenomic binning (VAMB), a program that uses deep variational autoencoders to encode sequence coabundance and k-mer distribution information before clustering. We show that a variational autoencoder is able to integrate these two distinct data types without any previous knowledge of the datasets. VAMB outperforms existing state-of-the-art binners, reconstructing 29–98% and 45% more near-complete (NC) genomes on simulated and real data, respectively. Furthermore, VAMB is able to separate closely related strains up to 99.5% average nucleotide identity (ANI), and reconstructed 255 and 91 NC Bacteroides vulgatus and Bacteroides dorei sample-specific genomes as two distinct clusters from a dataset of 1,000human gut microbiome samples. We use 2,606NC bins from this dataset to show that species of the human gut microbiome have different geographical distribution patterns. VAMB can be run on standard hardware and is freely available at https://github.com/RasmussenLab/vamb.

DOI: 10.1038/s41587-020-00777-4

Source: https://www.nature.com/articles/s41587-020-00777-4