Due to the complexity of metagenomic community, de novo assembly on next generation sequencing data is commonly unable to produce microbial complete genomes. Metagenomic binning is a crucial task that could group the fragmented contigs into clusters based on their nucleotide compositions and read depths. These features work well on the long contigs, but are not stable for the short ones. Assembly and paired-end graphs can provide the connectedness between contigs, where the linked contigs have high chance to be derived from the same clusters. Results: We developed METAMVGL, a multi-view graph-based metagenomic contig binning algorithm by integrating both assembly and paired-end graphs. It could strikingly rescue the short contigs and correct the binning errors from dead ends subgraphs. METAMVGL could learn the graphs' weights automatically and predict the contig labels in a uniform multi-view label propagation framework. In the experiments, we observed METAMVGL significantly increased the high-confident edges in the combined graph and linked dead ends to the main graph. It also outperformed with many state-of-the-art binning methods, MaxBin2, MetaBAT2, MyCC, CONCOCT, SolidBin and Graphbin on the metagenomic sequencing from simulation, two mock communities and real Sharon data. Availability and implementation: The software is available at https://github.com/ZhangZhenmiao/METAMVGL.

中文翻译：

---

METAMVGL：一种基于多视图图的宏基因组重叠群算法，通过组合装配图和端对图

由于宏基因组学社区的复杂性，下一代测序数据的从头组装通常无法产生微生物完整的基因组。元基因组装仓是一项至关重要的任务，可以根据其核苷酸组成和读取深度将片段重叠群分组为簇。这些功能在长重叠群上效果很好，但对于短重叠群却不稳定。装配图和成对末端图可以提供重叠群之间的连接性，其中链接的重叠群极有可能从相同的群集中派生。结果：我们通过集成组装图和配对端图，开发了METAMVGL，一种基于多视图图的宏基因组重叠群算法。它可以显着地拯救短重叠群，并纠正死角子图的分箱错误。METAMVGL可以学习图表的 自动加权，并在统一的多视图标签传播框架中预测重叠群标签。在实验中，我们观察到METAMVGL显着增加了组合图中的高可信边缘，并将死角链接到了主图中。在模拟，两个模拟社区和实际Sharon数据的宏基因组测序方面，它在许多最新的装箱方法（MaxBin2，MetaBAT2，MyCC，CONCOCT，SolidBin和Graphbin）上也表现出色。可用性和实施​​：该软件可从https://github.com/ZhangZhenmiao/METAMVGL获得。在模拟，两个模拟社区和实际Sharon数据的宏基因组测序方面，它在许多最新的装箱方法（MaxBin2，MetaBAT2，MyCC，CONCOCT，SolidBin和Graphbin）上也表现出色。可用性和实施​​：该软件可从https://github.com/ZhangZhenmiao/METAMVGL获得。在模拟，两个模拟社区和实际Sharon数据的宏基因组测序方面，它在许多最新的装箱方法（MaxBin2，MetaBAT2，MyCC，CONCOCT，SolidBin和Graphbin）上也表现出色。可用性和实施​​：该软件可从https://github.com/ZhangZhenmiao/METAMVGL获得。