sPLSDA SRBCT Case Study

This case study shows how to use sparse PLS-DA (sPLS-DA) to analyse gene expression data from the SRBCT dataset. sPLS-DA helps classify tumour types while selecting the most relevant genes for discrimination. You’ll learn how to tune the model, assess performance, and visualise the separation of cancer subtypes in a reduced space.

🔍 More on sPLS-DA
📄 Download R script

Data used on this page:
srbct

Key functions used on this page:
pca()
splsda()
perf()
tune()
plotIndiv()
cim()
plotVar()
predict()
auroc()

References:
1. Khan, J., Wei, J.S., Ringner, M., Saal, L.H., Ladanyi, M., Westermann, F., Berthold, F., Schwab, M., Antonescu, C.R., Peterson, C. and Meltzer, P.S., 2001. Classification and diagnostic prediction of cancers using gene expression profiling and artificial neural networks. Nature medicine, 7(6), pp.673-679.