This case study shows how to use MINT sPLS-DA to classify microbiome samples across multiple studies based on the type of inhibition treatment (e.g. ammonia vs. placebo). MINT corrects for batch effects and identifies OTUs that consistently discriminate treatment groups across studies. You’ll learn how to tune the model, explore treatment-associated features, and interpret class separation in microbial data.
🔍 More on MINT sPLS-DA
📄 Download R script
Data used on this page:
External microbial data
Key functions used on this page:pca()
mint.splsda()
tune()plotIndiv()
plotLoadings()
plotVar()
cim()
network()
perf()
auroc()
References:
1. Poirier S. and Chapleur O. Influence of support media supplementation to reduce the inhibition of anaerobic digestion by phenol and ammonia: Effect on degradation performances and microbial dynamics. Data in Brief. 2018; 19: 1733-1754.
2. Poirier S. and Chapleur O. Inhibition of anaerobic digestion by phenol and ammonia: Effect on degradation performances and microbial dynamics. Data in Brief. 2018: 2235-2239.
3. Poirier S, Déjean, S, Midoux, C, Lê Cao K-A, Chapleur O (2020). Integrating independent microbial studies to build predictive models of anaerobic digestion inhibition by ammonia and phenol. Bioresource Technology 316:12395