Python version of Factored Spectrally Transformed Linear Mixed Models
Python Jupyter Notebook C++ Other
Switch branches/tags
Nothing to show
Clone or download


FaST-LMM, which stands for Factored Spectrally Transformed Linear Mixed Models, is a program for performing both single-SNP and SNP-set genome-wide association studies (GWAS) on extremely large data sets. This release contains the improvements described in Widmer et al., Scientific Reports 2014, and tests for epistasis.

Our documentation (including live examples) is also available as ipython notebooks:

Additionally, API documentation is available:

A C++ version, which is generally less functional, is available at

Quick install:

If you have pip installed, installation is as easy as:

pip install fastlmm

Detailed Package Install Instructions:

fastlmm has the following dependencies:

python 2.7


  • numpy
  • scipy
  • matplotlib
  • pandas
  • scikit.learn (sklearn)
  • cython
  • pysnptools
  • optional: [statsmodels -- install only required for logistic-based tests, not the standard linear LRT]

(1) Installation of dependent packages

We highly recommend using a python distribution such as Anaconda ( or Enthought ( Both these distributions can be used on linux and Windows, are free for non-commercial use, and optionally include an MKL-compiled distribution for optimal speed. This is the easiest way to get all the required package dependencies.

(2) Installing from source

Go to the directory where you copied the source code for fastlmm.

On linux:

At the shell, type:

sudo python install

On Windows:

At the OS command prompt, type

python install

For developers (and also to run regression tests)

When working on the developer version, first add the src directory of the package to your PYTHONPATH environment variable.

For building C-extensions, first make sure all of the above dependencies are installed (including cython)

To build extension (from .\src dir), type the following at the OS prompt:

python build_ext --inplace

Note, if this fails with a gcc permission denied error, then specifying the correct compiler will likely fix the problem, e.g.

python build_ext --inplace --compiler=msvc

Don't forget to set your PYTHONPATH to point to the directory above the one named fastlmm in the fastlmm source code. For e.g. if fastlmm is in the [somedir] directory, then in the unix shell use:


Or in the Windows DOS terminal, one can use:


(or use the Windows GUI for env variables).

Note for Windows: You must have Visual Studio installed. If you have VisualStudio2008 installed (which was used to build python2.7) you need to nothing more. Otherwise, follow these instructions:

If you have Visual Studio 2010 installed, execute:


or with Visual Studio 2012 installed:


or with Visual Studio 2013 installed:


Running regression tests

From the directory tests at the top level, run:


This will run a series of regression tests, reporting "." for each one that passes, "F" for each one that does not match up, and "E" for any which produce a run-time error. After they have all run, you should see the string "............" indicating that they all passed, or if they did not, something such as "....F...E......", after which you can see the specific errors.

Note that you must use "python build_ext --inplace" to run the regression tests, and not "python install".