Skip to content

Principal Component Analysis of Pedigree Relationship Matrix via Randomized SVD

Notifications You must be signed in to change notification settings

HighlanderLab/RandPedigreePCA

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

48 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Randomized Pedigree Principal Component Analysis

Randomized Pedigree Principal Component Analysis (rpPCA) performs principal component analysis (PCA) of pedigree-based genetic relatedness matrix (GRM) using randomized linear algebra. Henderson (1975) developed an efficient way to compute the lower Cholesky factor of the inverse GRM. rpPCA uses this sparse Cholesky factor to compute the principal components that reveals the underlying population structure of the sample without setting up the GRM. This approach enables PCA for populations with large pedigrees.

R package

Setup

To install the package from GitHub (it's not yet on CRAN), run:

devtools::install_github("HighlanderLab/RandPedigreePCA", subdir = "randPedPCA",
                         ref="v0.9.1", build_vignettes = T)

First steps

For a demnstration, check out

vignette("pedigree-pca")

Python

An example can be found in notebook/Example.ipynb.

About

Principal Component Analysis of Pedigree Relationship Matrix via Randomized SVD

Resources

Stars

Watchers

Forks

Packages

No packages published

Contributors 4

  •  
  •  
  •  
  •