MACHINE LEARNING PLATFORM FOR GENERATING RISK MODELS
The disclosed embodiments concern methods, apparatus, systems, and computer program products for developing polygenic risk score (PRS) models. In some implementations, a fully automated process is provided that allows for a PRS model to be defined by an initial set of parameters. In some implementations the PRS models are trained to provide a PRS for particular populations.
1 . A method for generating a polygenic risk score (PRS) model to predict phenotypes of a user, the method comprising:
receiving user-selected parameters related to a PRS model including a phenotype of interest;
obtaining genetic data for a plurality of individuals based on the user-selected parameters including data pertaining to a presence or absence of the phenotype of interest in the plurality of individuals;
determining a plurality of population-specific genetic datasets based on the plurality of individuals;
analyzing one or more of the population-specific genetic datasets to determine one or more sets of SNPs that are statistically associated with a phenotype of interest for that population-specific genetic dataset, wherein each set of SNPs corresponds with one population-specific genetic dataset;
applying SNP filtering criteria to the one or more sets of SNPs to generate a plurality of training SNP sets, wherein the SNP filtering criteria is based at least in part on the user-selected parameters;
loading into a cache of a computer system genetic and phenotypic information for the plurality of individuals in each genetic dataset;
training a plurality of models using machine-learning techniques based at least in part on the genetic and phenotypic information for the plurality of individuals in the cache, the plurality of training SNP sets, and the phenotype of interest;
generating one or more performance metrics for each of the plurality of models for each of the population-specific genetic datasets;
determining a plurality of population-specific models based on the one or more performance metrics.
2 . The method of claim 1 , further comprising determining a combined set of SNPs that are statistically associated with the phenotype of interest based at least in part on a meta-analysis of the one or more sets of SNPs.
3 . The method of claim 2 , further comprising determining the combined set of SNPS based on an inverse weighting of the one or more sets of SNPs.
4 . The method of claim 2 , further comprising determining the combined set of SNPS based on scores from other polygenic models for at least some of the plurality of individuals.
5 . The method of claim 1 , further comprising determining the plurality of individuals by filtering a dataset of individuals based on the user-selected parameters.
6 . The method of claim 5 , wherein the user-selected parameters includes one or more of: research consent status, missing SNP values, relatedness to other individuals in the dataset of individuals, minimum age, maximum age, sequencing platform, sex, and population classifier label.
7 . The method of claim 1 , further comprising:
receiving phenotype data for the plurality of individuals, and
additionally analyzing the phenotype data of the plurality of individuals to determine the plurality of SNPs that are statistically associated with a phenotype of interest.
8 . The method of claim 7 , wherein the phenotype data includes one or more of: answers to survey questions, family history, medical records, biomarkers, and data from one or more wearable sensors.
9 . The method of claim 1 , wherein the genetic data includes one or more of: directly genotyped data, imputed genetic data, next generation sequencing data, whole genome sequencing data, and functionally aggregated data.
10 . The method of claim 1 , wherein the genetic data includes imputed data with greater than about 50,000,000 variants per individual, greater than about 75,000,000 variants per individual, or greater than about 100,000,000 variants per individual.
11 . The method of claim 1 , wherein a database storing the genetic data includes genetic data for greater than 10,000,000 individuals.
12 . The method of claim 1 , further comprising dividing one or more of the population-specific datasets into a training set, validation set, and test set, wherein analyzing one or more of the population-specific datasets is the genetic data of the plurality of individuals in the training sets.
13 . The method of claim 12 , wherein dividing each of the population-specific datasets is based on the user-selected parameters.
14 . The method of claim 12 , further comprising:
determining that a number of individuals in a first population-specific dataset does not exceed a first threshold; and
identifying the first population-specific dataset as a test set.
15 . The method of claim 12 , further comprising:
determining that a number of individuals in a second population-specific dataset does not exceed a second threshold; and
dividing the second population-specific dataset into a training set and validation set.
16 . The method of claim 12 , wherein the generating one or more performance metrics is based on the genetic data and phenotype data of the plurality of individuals in the validation set.
17 . The method of claim 12 , further comprising analyzing the population-specific models based on the genetic data and phenotype data of the plurality of individuals in the population-specific test set.
18 . The method of claim 1 , wherein analyzing at least the genetic data includes running a genome wide association study (GWAS) on the genetic data and the phenotype of interest.
19 . The method of claim 18 , wherein running the GWAS includes separating the plurality of individuals into case and control groups based on the user-selected parameters.
20 . The method of claim 1 , wherein the filtering criteria includes one or more of: allow listing, distance pruning, p-value threshold, and linkage disequilibrium pruning.
21 . The method of claim 1 , wherein the cache of the computer system comprises genetic and phenotypic information for at least about 1,000,000 individuals, at least about 500,000 individuals, or at least about 100,000 individuals.
22 . The method of claim 1 , wherein the population-specific models include more than about 3,000 SNPs, more than about 5,000 SNPs, more than about 10,000 SNPs, more than about 50,000 SNPs, more than about 100,000 SNPs, or more than about 200,000 SNPs.
23 . The method of claim 1 , wherein the plurality of models include models trained on two or more of the population-specific genetic datasets.
24 . The method of claim 1 , wherein training the plurality of models is further based on principal components derived from the plurality of individuals.
25 . The method of claim 1 , wherein the plurality of population-specific models comprise a model for one or more ethnicities selected from the group consisting of: European, African American, Sub-Saharan African, North Africa, LatinX, Central America, East Asian, South Asian, Southeast Asian, West Asian, and Central Asian.
26 . The method of claim 1 , further comprising deleting the genetic and phenotypic information for the plurality of individuals in each genetic dataset within 30 days of loading the genetic and phenotypic information for the plurality of individuals in each genetic dataset into the cache.
27 . The method of claim 1 , wherein the user-selected parameters comprise one or more parameters from the group consisting of: the phenotype of interest, SNPs previously determined to be associated with the phenotype of interest, prior GWAS results for the phenotype of interest, thresholds for dividing the population-specific genetic datasets into training, validation, and test sets, imputation panels, GWAS covariates including sex, age, sequencing platform, and/or principal components, lower limit for SNPs to be included in SNP sets, upper limit for SNPs to be included in SNP sets, a plurality of thresholds for p-values used to determine SNP sets, distance between SNPs in SNP sets, allow list for SNPs, disallow list for SNPs, phenotypic feature to include in model training, type of model to train, hyperparameters for training models, one or more performance metrics for evaluating models, and population-specific ethnicities for which to train a PRS model.
28 . The method of claim 1 , wherein the one or more performance metrics include area under the curve (AUC).
29 . The method of claim 1 , further comprising:
selecting a population-specific SNP set from the plurality of models based on the performance metrics, each population-specific SNP set corresponding to a population-specific genetic dataset; and
training the plurality of population-specific based on the corresponding population-specific SNP set.
30 . The method of claim 1 , further comprising storing metadata associated with one or more of population-specific models.
31 . The method of claim 30 , wherein the metadata comprises one or more of:
number of SNPs,
SNP selection parameters,
area under the curve (AUC) values of the population-specific model,
AUC values of the promoted model based on the genetic data and one or more metrics from the group consisting of: age, sex, sequencing platform, and population classifier label,
R-squared,
relative risk (top vs. bottom and top vs. middle),
observed absolute risk (phenotype) difference (top vs. bottom, top vs. middle), and
model specification.
32 . The method of claim 1 , further comprising recalibrating the population-specific models using Platt scaling.
33 . The method of claim 1 , further comprising:
providing a user's data to one of the population-specific models, based on the user's ancestry, to generate a (PRS) score; and
generating a user report on the phenotype of interest based on the PRS score.
34 . The method of claim 33 , wherein the user report comprises the following outcomes for the phenotype of interest: “Increased Likelihood”, “Typical Likelihood”, “Not Determined”, “Not Applicable.”
35 . A method for generating a polygenic risk score (PRS) model to predict a phenotype of a user, the method comprising:
receiving user-selected parameters related to a PRS model;
obtaining genetic data for a plurality of individuals based on the user-selected parameters;
determining a plurality of population-specific genetic datasets based on the plurality of individuals;
receiving a set of SNPs that are correlated with a phenotype of interest;
applying SNP filtering criteria to the one or more sets of SNPs to generate a plurality of training SNP sets, wherein the SNP filtering criteria is based at least in part on the user-selected parameters;
loading into a cache of a computer system genetic and phenotypic information for the plurality of individuals in each genetic dataset;
training a plurality of models using machine-learning techniques based at least in part on the genetic and phenotypic information for the plurality of individuals in the cache, the plurality of training SNP sets, and the phenotype of interest;
generating one or more performance metrics for each of the plurality of models for each of the population-specific genetic datasets;
selecting a best population-specific SNP set from the plurality of models for each of the population-specific models based on the performance metrics, each population-specific SNP set corresponding to a population-specific genetic dataset;
training a plurality of population-specific models based on the corresponding population-specific SNP set and the corresponding population-specific genetic dataset.
36 . A system for generating a polygenic risk score (PRS) model to predict phenotypes of a user, the system comprising:
one or more processors and associated memory; and
computer readable instructions for:
receiving user-selected parameters related to a PRS model including a phenotype of interest;
obtaining genetic data for a plurality of individuals based on the user-selected parameters including data pertaining to a presence or absence of the phenotype of interest in the plurality of individuals;
determining a plurality of population-specific genetic datasets based on the plurality of individuals;
analyzing one or more of the population-specific genetic datasets to determine one or more sets of SNPs that are statistically associated with a phenotype of interest for that population-specific genetic dataset, wherein each set of SNPs corresponds with one population-specific genetic dataset;
applying SNP filtering criteria to the one or more sets of SNPs to generate a plurality of training SNP sets, wherein the SNP filtering criteria is based at least in part on the user-selected parameters;
loading into a cache of a computer system genetic and phenotypic information for the plurality of individuals in each genetic dataset;
training a plurality of models using machine-learning techniques based at least in part on the genetic and phenotypic information for the plurality of individuals in the cache, the plurality of training SNP sets, and the phenotype of interest;
generating one or more performance metrics for each of the plurality of models for each of the population-specific genetic datasets;
determining a plurality of population-specific models based on the one or more performance metrics.
37 . A non-transient computer-readable medium comprising program instructions for causing a computer to generate a polygenic risk score (PRS) model to predict phenotypes of a user, the program instructions comprising:
receive user-selected parameters related to a PRS model including a phenotype of interest;
obtain genetic data for a plurality of individuals based on the user-selected parameters including data pertaining to a presence or absence of the phenotype of interest in the plurality of individuals;
determine a plurality of population-specific genetic datasets based on the plurality of individuals;
analyze one or more of the population-specific genetic datasets to determine one or more sets of SNPs that are statistically associated with a phenotype of interest for that population-specific genetic dataset, wherein each set of SNPs corresponds with one population-specific genetic dataset;
apply SNP filtering criteria to the one or more sets of SNPs to generate a plurality of training SNP sets, wherein the SNP filtering criteria is based at least in part on the user-selected parameters;
load into a cache of a computer system genetic and phenotypic information for the plurality of individuals in each genetic dataset;
train a plurality of models using machine-learning techniques based at least in part on the genetic and phenotypic information for the plurality of individuals in the cache, the plurality of training SNP sets, and the phenotype of interest;
generate one or more performance metrics for each of the plurality of models for each of the population-specific genetic datasets;
determine a plurality of population-specific models based on the one or more performance metrics.