https://github.com/sens/fastlmm.jl

Julia implementation of Factored Spectrally Transformed Linear Mixed Models
https://github.com/sens/fastlmm.jl

julia linear-mixed-models statistical-genetics

Last synced: about 2 months ago
JSON representation

Julia implementation of Factored Spectrally Transformed Linear Mixed Models

• Host: GitHub
• URL: https://github.com/sens/fastlmm.jl
• Owner: sens
• License: agpl-3.0
• Created: 2016-03-22T14:59:29.000Z (almost 9 years ago)
• Default Branch: master
• Last Pushed: 2021-03-13T16:10:50.000Z (almost 4 years ago)
• Last Synced: 2024-10-10T17:47:41.470Z (2 months ago)
• Topics: julia, linear-mixed-models, statistical-genetics
• Language: Julia
• Size: 18.1 MB
• Stars: 6
• Watchers: 3
• Forks: 5
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# FaST-LMM: *Fa*ctored *S*pectrally *T*ransformed *L*inear *M*ixed *M*odels

[![Build Status](https://travis-ci.org/sens/FaSTLMM.jl.svg?branch=master)](https://travis-ci.org/sens/FaSTLMM.jl)

Genetic analysis in structured populations used mixed linear models

where the variance matrix of the error term is a linear combination of

an identity matrix and a positive definite matrix.

The linear model is of the familiar form: 𝑦 = 𝑋 β + ϵ.

- 𝑦: phenotype

- 𝑋: covariates

- β: fixed effects

- ϵ: error term

Further, V(ϵ) = τ²𝐾+ σ²𝐼, where τ² is

the genetic variance, σ² is the environmental variance, 𝐾

is the kinship matrix, and 𝐼 is the identity matrix.

The key idea in speeding up computations here is that by rotating the

phenotypes by the eigenvectors of 𝐾 we can transform estimation to a

weighted least squares problem.

This code is under development.

Guide to the directories:

- `src`: Julia source code

- `data`: Example data for development and testing

- `test`: Code for testing

- `docs`: Notes on comparisons with other implementations