Department of Environmental Medicine, Tianjin Institute of Environmental and Operational Medicine, Tianjin 300050, China.
BioMap (Beijing) Intelligence Technology Limited, Beijing 100005, China.
Bioinformatics. 2022 Aug 10;38(16):4027-4029. doi: 10.1093/bioinformatics/btac438.
Characterizing biomarkers based on microbiome profiles has great potential for translational medicine and precision medicine. Here, we present microbiomeMarker, an R/Bioconductor package implementing commonly used normalization and differential analysis (DA) methods, and three supervised learning models to identify microbiome markers. microbiomeMarker also allows comparison of different methods of DA and confounder analysis. It uses standardized input and output formats, which renders it highly scalable and extensible, and allows it to seamlessly interface with other microbiome packages and tools. In addition, the package provides a set of functions to visualize and interpret the identified microbiome markers.
microbiomeMarker is freely available from Bioconductor (https://www.bioconductor.org/packages/microbiomeMarker). Source code is available and maintained at GitHub (https://github.com/yiluheihei/microbiomeMarker).
Supplementary data are available at Bioinformatics online.
基于微生物组谱特征来描述生物标志物对于转化医学和精准医学具有巨大的潜力。在这里，我们提出了 microbiomeMarker，这是一个 R/Bioconductor 包，实现了常用的标准化和差异分析（DA）方法，以及三个用于识别微生物组标记物的监督学习模型。microbiomeMarker 还允许比较不同的 DA 方法和混杂因素分析。它使用标准化的输入和输出格式，这使其具有高度的可扩展性和可扩展性，并允许它与其他微生物组包和工具无缝接口。此外，该包还提供了一组用于可视化和解释所识别的微生物组标记物的功能。
microbiomeMarker 可从 Bioconductor（https://www.bioconductor.org/packages/microbiomeMarker）免费获得。源代码可在 GitHub（https://github.com/yiluheihei/microbiomeMarker）上获得并维护。
补充数据可在 Bioinformatics 在线获得。
