Modeling of Microbiome Data

In the first chapter, the concepts of tidymodeling were introduced. In the second chapter, the statistical concepts that are often used in Bioinformatics and Biostatistics were introduced. The third chapter touched upon different preprocessing techniques to apply. This chapter combines the first three chapters to build and evaluate models for a real-world dataset. As mentioned in the preface, the dataset used is 16S rRNA amplicon reads used to investigate the microbiome of MS patients (Cox et al. 2021). Here, the data is used to predict the disease status an individual given the microbiome.

Cox, Laura M., Amir Hadi Maghzi, Shirong Liu, Stephanie K. Tankou, Fyonn H. Dhang, Valerie Willocq, Anya Song, et al. 2021. “Gut Microbiome in Progressive Multiple Sclerosis.” Annals of Neurology 89 (June): 1195–1211. https://doi.org/10.1002/ANA.26084.