Local binary patterns as a feature descriptor in alignment-free visualisation of metagenomic data
Local binary patterns as a feature descriptor in alignment-free visualisation of metagenomic data
复制标题
DOI：
10.1109/ssci.2016.7849955
复制
发表时间：
2016-12
期刊：
影响因子：
--
通讯作者：
S. Kouchaki;Santosh Tirunagari;Avraam Tapinos;D. Robertson
中科院分区：
文献类型：
--
作者：
S. Kouchaki;Santosh Tirunagari;Avraam Tapinos;D. Robertson
鸟枪测序促进了复杂微生物群落的分析。然而，在没有先前分类信息的情况下对这些群落进行聚类和可视化是一个重大挑战。可以利用特征描述符方法从数据中提取这些分类关系。在这里，我们提出了一种新的方法，包括本地二进制模式（LBP）加上随机奇异值分解（RSVD）和Barnes-Hut t-随机邻居嵌入（BH-tSNE）突出的宏基因组数据的基础分类结构。我们的方法的有效性证明了使用几个模拟和一个真实的宏基因组数据集。
Shotgun sequencing has facilitated the analysis of complex microbial communities. However, clustering and visualising these communities without prior taxonomic information is a major challenge. Feature descriptor methods can be utilised to extract these taxonomic relations from the data. Here, we present a novel approach consisting of local binary patterns (LBP) coupled with randomised singular value decomposition (RSVD) and Barnes-Hut t-stochastic neighbor embedding (BH-tSNE) to highlight the underlying taxonomic structure of the metagenomic data. The effectiveness of our approach is demonstrated using several simulated and a real metagenomic datasets.