This page offers a quick start guide for using PCA and sparse PCA (sPCA) in mixOmics. PCA is a method an exploratory method for single `omics, unsupervised data analysis which transforms high-dimensional data into principle components which maximise the variance in the data. Dimensionality reduction is done using singular value decomposition (SVD) or NIPALS for handling missing values. Sparse PCA allows for the identification of key variables that contribute to defining these principal components.
🎥 Watch: Webinar on PCA
🔭 Tip: Run PCA on each individual omics to see what are the largest sources of variation in the data before running any other mixOmics models
Typical (s)PCA-type questions:
– What are the major trends or patterns in my data?
– Do the samples cluster according to biological conditions of interest?
– Which variables contribute the most to explaining the variance in the data?
Data used on this page:multidrug
Key functions used on this page:pca()spca()plotIndiv()plotVar()selectVar()plotLoadings()
Related case studies:
Case Study: PCA Multidrug
References:
1. Jolliffe I.T. (2002) Principal Component Analysis. Springer Series in Statistics, Springer, New York.
2. Shen, H. and Huang, J. Z. (2008). Sparse principal component analysis via regularized low rank matrix approximation. 99(6), 1015–1034.