Structured Linear Mixed Model (StructLMM) is a computationally efficient method to test for and characterize loci that interact with multiple environments [1].
This a standalone module that implements the basic functionalities of StructLMM. However, we recommend using StructLMM via LIMIX2 as this additionally implements:
- Multiple methods for GWAS;
- Methods to characterize GxE at specific variants;
- Command line interface.
From terminal, it can be installed using pip:
pip install struct-lmm>>> from numpy import ones, concatenate
>>> from numpy.random import RandomState
>>>
>>> from struct_lmm import StructLMM
>>>
>>> random = RandomState(1)
>>> n = 20
>>> k = 4
>>> y = random.randn(n, 1)
>>> E = random.randn(n, k)
>>> M = ones((n, 1))
>>> x = 1.0 * (random.rand(n, 1) < 0.2)
>>>
>>> lmm = StructLMM(y, M, E)
>>> lmm.fit(verbose=False)
>>> # Association test
>>> pv = lmm.score_2dof_assoc(x)
>>> print(pv)
0.8470017313426488
>>> # Association test
>>> pv, rho = lmm.score_2dof_assoc(x, return_rho=True)
>>> print(pv)
0.8470017313426488
>>> print(rho)
0
>>> M = concatenate([M, x], axis=1)
>>> lmm = StructLMM(y, M, E)
>>> lmm.fit(verbose=False)
>>> # Interaction test
>>> pv = lmm.score_2dof_inter(x)
>>> print(pv)
0.6781100453132024If you encounter any problem, please, consider submitting a new issue.
This project is licensed under the MIT License.
[1] Moore, R., Casale, F. P., Bonder, M. J., Horta, D., Franke, L., Barroso, I., & Stegle, O. (2018). A linear mixed-model approach to study multivariate gene–environment interactions (p. 1). Nature Publishing Group.