This case study shows how to use MINT sPLS-DA to classify stem cell types (Fibroblast, hESC, hiPSC) from transcriptomic data collected across multiple studies. MINT sPLS-DA identifies reproducible gene signatures that discriminate cell types while accounting for study-specific effects. You’ll learn how to tune the model, assess cross-study performance, and visualise class separation and gene contributions.
More on MINT
Download R script
Data used on this page:stemcells
Key functions used on this page:plsda()
mint.splsda()
perf()
tune()plotIndiv()
plotVar()
cim()
network()
auroc()
predict()
References:
1. Rohart F, Gautier B, Singh A, Lê Cao K-A (2017). mixOmics: an R package for ‘omics feature selection and multiple data integration.