PCAtools: everything Principal Component Analysis5 months ago
Introduction | Installation | 1. Download the package from Bioconductor | 2. Load the package into R session | Quick start: DESeq2 | Conduct principal component analysis (PCA): | A scree plot | A bi-plot | Quick start: Gene Expression Omnibus (GEO) | A pairs plot | A loadings plot | An eigencor plot | Access the internal data | Advanced features | Determine optimum number of PCs to retain | Modify bi-plots | Colour by a metadata factor, use a custom label, add lines through origin, and add legend | Supply custom colours and encircle variables by group | Stat ellipses | Change shape based on tumour grade, remove connectors, and add titles | Modify line types, remove gridlines, and increase point size | Colour by a continuous variable and plot other PCs | Quickly explore potentially informative PCs via a pairs plot | Determine the variables that drive variation among each PC | Correlate the principal components back to the clinical data | Plot the entire project on a single panel | Make predictions on new data | Acknowledgments | Session info | References
PCAtools 2.25.0Kevin Blighe, Aaron LunPCAtools.Rmd