# US 10,120,975 B2 · Computationally efficient correlation of genetic effects with function-valued traits

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 10,120,975 B2
- Document ID: US10120975B2
- Status: Granted
- Kind: B2
- Application number: 15/084,951
- Filed: 2016-03-30
- Published: 2017-10-05
- Granted: 2018-11-06
- Earliest claimed: 2016-03-30
- Assignees: Microsoft Technology Licensing, LLC
- Applicants: Microsoft Technology Licensing, LLC
- Inventors: Nicolo Fusi; Jennifer Listgarten
- Web page: https://patentgrep.com/patent/US10120975B2

## CPC

- G16B 20/20: Allele or variant detection, e.g. single nucleotide polymorphism [SNP] detection
- G16B 20/00: ICT specially adapted for functional genomics or proteomics, e.g. genotype-phenotype associations
- 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
- G16B 20/40: Population genetics; Linkage disequilibrium
- G16B: BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY

## Abstract

This disclosure presents a model for identifying correlations in genome-wide association studies (GWAS) with function-valued traits that provides increased power and computational efficiency by use of a Gaussian process regression with radial basis function (RBF) kernels to model the function-valued traits and specialized factorizations to achieve speed. A Gaussian Process is assigned to each partition for each allele of a given single nucleotide polymorphism (SNP) which yields flexible alternative models and handles a large number of data points in a way that is statistically and computationally efficient. This model provides techniques for handling missing and unaligned function values such as would occur when not all individuals are measured at the same time points. If the data is complete algebraic re-factorization by decomposition into Kronecker products reduces the time complexity of this model thereby increasing processing speed and reducing memory usage as compared to a naive implementation.

## Claims

### Claim 1

A computationally-efficient method for identifying a correlation between a single-nucleotide polymorphism (SNP) and a function-valued trait in a genome-wide association study (GWAS), the method comprising:
populating a matrix of values of the function-valued trait for a plurality of subjects at a plurality of function domain points;
generating a null model comprising a Gaussian distribution of the matrix with mean zero and a first covariance term, the first covariance term being determined in part by a first non-linear kernel applied to the plurality of function domain points for the function-valued trait and by a first parameter;
representing the first covariance term as a first Kronecker product;
calculating a first maximum likelihood for the null model;
partitioning the matrix into a first partition, a second partition, and a third partition based at least in part on alleles of the SNP;
generating an alternative model that sums together Gaussian distributions of the first partition, the second partition, and the third partition of the matrix with mean zero and a second covariance term determined in part by a second non-linear kernel applied to the first partition, the second partition, and the third partition of the matrix and a second parameter;
representing the second covariance term as a second Kronecker product;
calculating a second maximum likelihood for the alternative model;
calculating a difference between the first maximum likelihood for the null model and the second maximum likelihood for the alternative model;
calculating a test statistic based at least in part on the difference; and
identifying existence of the correlation between the SNP and the function-valued trait based at least in part on the test statistic.

### Claim 2 (depends on 1)

The method of claim 1, further comprising determining that a first Gaussian distribution of the first partition is different from a second Gaussian distribution of the second partition and from a third Gaussian distribution of the third partition.

### Claim 3 (depends on 1)

The method of claim 1, further comprising determining that a first Gaussian distribution of the first partition has a different length scale and a different variance parameter than a second Gaussian distribution of the second partition and different than a third Gaussian distribution of the third partition.

### Claim 4 (depends on 1)

The method of claim 1, wherein the non-linear kernel comprises a radial basis function (RBF) kernel.

### Claim 5 (depends on 1)

The method of claim 1, wherein the first parameter comprises a first length-scale parameter that determines a first scale on which the function-valued trait varies within individual ones of the plurality of subjects and the second parameter comprises a second length-scale parameter that determines a second scale on which the function-valued trait varies within individual ones of the plurality of subjects.

### Claim 6

A computationally-efficient method for identifying a correlation between a single-nucleotide polymorphism (SNP) and a function-valued trait in genome-wide association study (GWAS), the method comprising:
creating a linked matrix having values of the function-valued trait, values of function domain points, and phenotype values for each allele combination of the SNP;
generating an alternative model having a single Gaussian process of a vector derived from the linked matrix and a covariance term, the covariance term based upon at least one scalar and a non-linear kernel;
generating a null model by setting a value of the at least one scalar to zero;
comparing a first maximum likelihood for the alternative model with a second maximum likelihood for the null model; and
determining that the SNP is correlated with the function-valued trait based on the comparison of the first maximum likelihood for the alternative model with the second likelihood for the null model.

### Claim 7 (depends on 6)

The method of claim 6, wherein the non-linear kernel is a radial basis function (RBF) kernel or a Matern kernel.

### Claim 8 (depends on 6)

The method of claim 6, wherein the at least one scalar comprises a correlation parameter for each pair of alleles of the SNP indicating a degree of trait similarity between the data with each allele in the pair.

### Claim 9 (depends on 6)

The method of claim 6, wherein the alternative model comprises a parameter that determines an overall scale on which the function-valued trait varies as a function varies.

### Claim 10 (depends on 6)

The method of claim 6, further comprising:
determining that there are no missing data in the values of the function-valued trait and that the function domain points for each of the plurality of subjects align; and
decomposing at least part of the covariance term to a Kronecker product thereby reducing computational time and memory needed to calculate the first maximum likelihood for the alternative model.

### Claim 11 (depends on 6)

The method of claim 6, further comprising:
marginalizing over the missing values of the function-valued trait; and
adding pseudo-observations as inputs to the non-linear kernel thereby making the values of the function-valued trait conditionally independent and reducing a time complexity for maximizing a lower bound of the first likelihood and a lower bound of the second likelihood, wherein variational inference maximizes a lower bound of the first likelihood and maximizes a lower bound of the second likelihood.

### Claim 12

A computationally-efficient system for identifying a correlation between a single-nucleotide polymorphism (SNP) and a function-valued trait in genome-wide association study (GWAS), the system including:
a data storage device that stores instructions for identifying a correlation between a single-nucleotide polymorphism (SNP) and a function-valued trait in genome-wide association study (GWAS); and
a processor configured to execute the instructions to perform a method including:
creating a linked matrix having values of the function-valued trait, values of function domain points, and phenotype values for each allele combination of the SNP;
generating an alternative model having a single Gaussian process of a vector derived from the linked matrix and a covariance term, the covariance term based upon at least one scalar and a non-linear kernel;
generating a null model by setting a value of the at least one scalar to zero;
comparing a first maximum likelihood for the alternative model with a second maximum likelihood for the null model; and
determining that the SNP is correlated with the function-valued trait based on the comparison of the first maximum likelihood for the alternative model with the second likelihood for the null model.

### Claim 13 (depends on 12)

The system of claim 12, wherein the non-linear kernel is a radial basis function (RBF) kernel or a Matern kernel.

### Claim 14 (depends on 13)

The system of claim 13, wherein the at least one scalar comprises a correlation parameter for each pair of alleles of the SNP indicating a degree of trait similarity between the data with each allele in the pair.

### Claim 15 (depends on 13)

The system of claim 13, wherein the alternative model comprises a parameter that determines an overall scale on which the function-valued trait varies as a function varies.

### Claim 16 (depends on 12)

The system of claim 12, wherein the at least one scalar comprises a correlation parameter for each pair of alleles of the SNP indicating a degree of trait similarity between the data with each allele in the pair.

### Claim 17 (depends on 16)

The system of claim 16, wherein the non-linear kernel is a radial basis function (RBF) kernel or a Matern kernel.

### Claim 18 (depends on 12)

The system of claim 12, wherein the alternative model comprises a parameter that determines an overall scale on which the function-valued trait varies as a function varies.

### Claim 19 (depends on 12)

The system of claim 12, wherein the processor is further configured to execute the instructions to perform the method further including:
determining that there are no missing data in the values of the function-valued trait and that the function domain points for each of the plurality of subjects align; and
decomposing at least part of the covariance term to a Kronecker product thereby reducing computational time and memory needed to calculate the first maximum likelihood for the alternative model.

### Claim 20 (depends on 12)

The system of claim 12, wherein the processor is further configured to execute the instructions to perform the method further including
marginalizing over the missing values of the function-valued trait; and
adding pseudo-observations as inputs to the non-linear kernel thereby making the values of the function-valued trait conditionally independent and reducing a time complexity for maximizing a lower bound of the first likelihood and a lower bound of the second likelihood, wherein variational inference maximizes a lower bound of the first likelihood and maximizes a lower bound of the second likelihood.