Feature selection for efficient epistasis modeling for phenotype prediction

• US 10,108,775 B2
• Filed: 09/18/2013
• Issued: 10/23/2018
• Est. Priority Date: 01/21/2013
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Haws, David, He, Dan, Parida, Laxmi P.
• Primary Examiner(s): Zeman, Mary K
• Application Number:
  US14/030,743
• Publication Number:
  US 20140207436A1
• Time in Patent Office: 1,861 Days
• CPC Class Codes: G16B 20/00 ICT specially adapted for functional genomics or proteomics, e.g. genotype-phenotype associations
• CPC Class Codes: G16B 20/20 Allele or variant detection, e.g. single nucleotide polymorphism [SNP] detection
• CPC Class Codes: G16B 40/00 ICT specially adapted for biostatistics; ICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding
• CPC Class Codes: G16B 5/00 ICT specially adapted for modelling or simulations in systems biology, e.g. gene-regulatory networks, protein interaction networks or metabolic networks
• CPC Class Codes: G16B 5/20 Probabilistic models

Abstract

Various embodiments select markers for modeling epistasis effects. In one embodiment, a processor receives a set of genetic markers and a phenotype. A relevance score is determined with respect to the phenotype for each of the set of genetic markers. A threshold is set based on the relevance score of a genetic marker with a highest relevancy score. A relevance score is determined for at least one genetic marker in the set of genetic markers for at least one interaction between the at least one genetic marker and at least one other genetic marker in the set of genetic markers. The at least one interaction is added to a top-k feature set based on the relevance score of the at least one interaction satisfying the threshold.

Claims

1. An information processing system for reducing search time of features in sample data and reducing computation time when training a model for generating specialized data based on the features, the information processing system comprising:

a memory;

a processor communicatively coupled to the memory; and

a feature selection circuit coupled to the memory and the processor, wherein the feature selection circuit is configured to perform a plurality of operations comprising;

receiving a set of genetic markers and a phenotype from at least one external information processing system;

training an epistasis effect model based on the set of genetic markers and the phenotype;

reducing computation time of the information processing system during the training of the epistasis effect model and further reducing feature selection time of the epistasis effect model, wherein reducing the computation time and the feature selection time comprises;

determining, for each of the set of genetic markers, a relevance score with respect to the phenotype according to I(x_j^training;

c^training), where I is mutual information between a given genetic marker x_j and a phenotype c, where mutual information I between two variables x and y is defined, based on their joint marginal probabilities p(x) and p(y) and probabilistic distribution p(x, y), as;

2. The information processing system of claim 1, wherein the method further comprises:

randomly sampling a subset of genetic markers from the set of genetic markers; and

selecting the at least one additional genetic marker from the subset of genetic markers.

3. The information processing system of claim 2, wherein determining the relevance score of the at least one interaction comprises:

determining a first set of relevance scores comprising a relevance score with respect to the phenotype for each of a first plurality of interactions between the at least one genetic marker and each of the subset of genetic markers;

determining, based on a normal distribution associated with the first set of relevance scores, a probability of the at least one genetic marker being associated with an interaction comprising a relevance score greater than the threshold;

comparing the probability to a probability threshold; and

determining, based on the probability satisfying the probability threshold, a second set of relevance scores comprising a relevance score for each of a second plurality of interactions between the at least one genetic marker and a remaining set of genetic markers in the set of genetic markers, wherein the second plurality of interactions comprises the at least one interaction, and wherein the remaining set of genetic markers comprises the at least one additional genetic marker.

4. The information processing system of claim 1, wherein the method further comprises:

generating, based on adding the at least one interaction to the top-k feature set, an updated top-k feature set by removing one of a genetic marker and an interaction associated with a lowest relevance score from the top-k feature set.

5. The information processing system of claim 1, wherein the method further comprises:

updating the threshold according to a highest relevance score associated with one of a genetic marker and an interaction within the updated top-k feature;

determining a relevance score for at least one additional interaction between the at least one genetic marker and at least one other genetic marker in the set of genetic markers;

comparing the relevance score of at least one additional interaction to the threshold that has been updated; and

adding the at least one additional interaction to the top-k feature set based on the relevance score of the at least one additional interaction satisfying the threshold that has been updated.

6. A non-transitory computer program product for reducing search time of features in sample data and reducing computation time when training a model for generating specialized data based on the features, the computer program product comprising:

a storage medium readable by a processing circuit of an information processing system and storing instructions for execution by a feature selection circuit of the information processing system for performing a method comprising;

receiving a set of genetic markers and a phenotype from at least one external information processing system;

training an epistasis effect model based on the set of genetic markers and the phenotype;

reducing computation time of the information processing system during the training of the epistasis effect model, and further reducing feature selection time of the epistasis effect model, wherein reducing the computation time and the feature selection time comprises;

determining, for each of the set of genetic markers, a relevance score with respect to the phenotype according to I(x_j^training;

c^training), where I is mutual information between a given genetic marker x_j and a phenotype c, where mutual information I between two variables x and y is defined, based on their joint marginal probabilities p(x) and p(y) and probabilistic distribution p(x, y), as;

7. The non-transitory computer program product of claim 6, wherein the method further comprises:

randomly sampling a subset of genetic markers from the set of genetic markers; and

selecting the at least one additional genetic marker from the subset of genetic markers.

8. The non-transitory computer program product of claim 7, wherein determining the relevance score of the at least one interaction comprises:

determining a first set of relevance scores comprising a relevance score with respect to the phenotype for each of a first plurality of interactions between the at least one genetic marker and each of the subset of genetic markers;

determining, based on a normal distribution associated with the first set of relevance scores, a probability of the at least one genetic marker being associated with an interaction comprising a relevance score greater than the threshold;

comparing the probability to a probability threshold; and

determining, based on the probability satisfying the probability threshold, a second set of relevance scores comprising a relevance score for each of a second plurality of interactions between the at least one genetic marker and a remaining set of genetic markers in the set of genetic markers, wherein the second plurality of interactions comprises the at least one interaction, and wherein the remaining set of genetic markers comprises the at least one additional genetic marker.

9. The non-transitory computer program product of claim 6, wherein the method further comprises:

generating, based on adding the at least one interaction to the top-k feature set, an updated top-k feature set by removing one of a genetic marker and an interaction associated with a lowest relevance score from the top-k feature set.

10. The non-transitory computer program product of claim 6, wherein the method further comprises:

updating the threshold according to a highest relevance score associated with one of a genetic marker and an interaction within the updated top-k feature.

11. The non-transitory computer program product of claim 10, wherein the method further comprises:

determining a relevance score for at least one additional interaction between the at least one genetic marker and at least one other genetic marker in the set of genetic markers;

comparing the relevance score of at least one additional interaction to the threshold that has been updated; and

adding the at least one additional interaction to the top-k feature set based on the relevance score of the at least one additional interaction satisfying the threshold that has been updated.