This workshop will provide a beginner’s guide to matrix factorization, principal component analysis (PCA), the difference between singular value decomposition, different forms of PCA and fast PCA for single-cell data as well as correspondence analysis and decomposition of the Pearson Residuals. We will describe how to detect artifacts and select the optimal number of components. It will focus on SVD, PCA, COA applied toy datasets and single-cell data.
Principal component analysis (PCA) is a key step in many bioinformatics pipelines. In this interactive session we will take a deep dive into the various implementations of singular value decomposition (SVD) and principal component analysis (PCA) to clarify the relationship between these methods, and to demonstrate the equivalencies and contrasts between these methods. We will describe correspondence analysis (COA) and demonstrate how it differs from PCA. We will also discuss interpretation of outputs, as well as some common pitfalls and sources of confusion in utilizing these methods.
A basic understanding of R syntax would be helpful, but not required. No prior knowledge of PCA necessary.
We invite audience members to engage with questions and examples from their own workflows. R notebooks will also be available in advance to run code interactively with the workshop.
Upon completion of this workshop, we expect participants to have gained an understanding of how to apply PCA and other SVD-based methods in research.