期刊
MICROBIOME
卷 6, 期 -, 页码 -出版社
BMC
DOI: 10.1186/s40168-018-0469-5
关键词
Termite microbiota; 16S rRNA gene sequencing; Artificial neural network; Deep learning; Low-abundant drivers
类别
资金
- National Science Foundation (NSF) division of Emerging Frontiers in Research and Innovation in Multicellular and Inter-kingdom signaling [1137249]
Background: As the importance of beneficial bacteria is better recognized, understanding the dynamics of symbioses becomes increasingly crucial. In many gut symbioses, it is essential to understand whether changes in host diet play a role in the persistence of the bacterial gut community. In this study, termites were fed six dietary sources and the microbial community was monitored over a 49-day period using 16S rRNA gene sequencing. A deep backpropagation artificial neural network (ANN) was used to learn how the six different lignocellulose food sources affected the temporal composition of the hindgut microbiota of the termite as well as taxon-taxon and taxon-substrate interactions. Results: Shifts in the termite gut microbiota after diet change in each colony were observed using 16S rRNA gene sequencing and beta diversity analyses. The artificial neural network accurately predicted the relative abundances of taxa at random points in the temporal study and showed that low-abundant taxa maintain community driving correlations in the hindgut. Conclusions: This combinatorial approach utilizing 16S rRNA gene sequencing and deep learning revealed that low-abundant bacteria that often do not belong to the core community are drivers of the termite hindgut bacterial community composition.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据