MISS is a a nonlinear methodology based on mutual information for genetic association.
The an information theoretic approach to genetic association, which has been integrated jointly with a feature selection algorithm. The algorithm was been tested on a synthetic data with a controlled phenotype and in the particular case of the F7 gene. This algorithm proposes a multi-target approach and unveils combinations of SNPs that explain more significant information of the phenotype than their individual polymorphisms.
The software package with documentation can be found here.
The paper describing MISS can be found here.
- Brunel, H.; Gallardo, J.; Buil, A.; Vallverdu, M.; Soria, J.; Caminal, P.; Perera, A. (2010). MISS: a non-linear methodology based on mutual information for genetic association studies in both population and sib-pairs analysis. Bioinformatics, 26, 1811-1818.