MINT: Mutual Information based Transductive Feature Selection for Genetic Trait Prediction
This addresses feature selection challenges in genetic trait prediction for plant/animal breeding and epidemiology, but appears incremental as it adapts an existing criterion to a transductive setting.
The authors tackled the curse-of-dimensionality in whole genome prediction of complex traits by proposing MINT, a transductive feature selection method based on MRMR, and showed it generally outperforms the state-of-the-art inductive method mRMR.
Whole genome prediction of complex phenotypic traits using high-density genotyping arrays has attracted a great deal of attention, as it is relevant to the fields of plant and animal breeding and genetic epidemiology. As the number of genotypes is generally much bigger than the number of samples, predictive models suffer from the curse-of-dimensionality. The curse-of-dimensionality problem not only affects the computational efficiency of a particular genomic selection method, but can also lead to poor performance, mainly due to correlation among markers. In this work we proposed the first transductive feature selection method based on the MRMR (Max-Relevance and Min-Redundancy) criterion which we call MINT. We applied MINT on genetic trait prediction problems and showed that in general MINT is a better feature selection method than the state-of-the-art inductive method mRMR.