Information processing system useful for selecting markers for modeling epistasis action using computer implemented method, comprises memory, processor coupled to memory, and feature selection module coupled to memory and processor

摘要

Information processing system (102) for selecting markers for modeling epistasis action using computer implemented method, comprises: a memory (106); a processor (104) communicatively coupled to the memory; and a feature selection module (109) coupled to the memory and the processor. The feature selection module is designed to perform a method comprising: e.g. receiving a set of genetic markers and a phenotype by a processor; determining a relevance score for each of the set of genetic markers with respect to the phenotype; setting a threshold and adding at least one interaction. Information processing system (102) for selecting markers for modeling epistasis action using computer implemented method, comprises: a memory (106); a processor (104) communicatively coupled to the memory; and a feature selection module (109) coupled to the memory and the processor. The feature selection module is designed to perform a method comprising: receiving a set of genetic markers and a phenotype by a processor; determining a relevance score for each of the set of genetic markers with respect to the phenotype; setting a threshold based on the relevance score of a genetic marker in the set of genetic markers with a highest relevancy score; determining a relevance score for at least one genetic marker in the set of genetic markers, for at least one interaction between at least one genetic marker and at least one other genetic marker in the set of genetic markers; and adding at least one interaction to a top-k feature set based on the relevance score of at least one interaction satisfying the threshold. Each feature in the top-k feature set is one of a genetic maker and an interaction each comprising top-k relevance score. An independent claim is also included for a non-transitory computer program product for selecting markers for modeling epistasis effects by the computer program product, comprising a storage medium readable by a processing circuit and storing instructions for execution by the processing circuit for performing the above mentioned method.