Multi-polygenic score approach to trait prediction

Abstract

A primary goal of polygenic scores, which aggregate the effects of thousands of trait-associated DNA variants discovered in genome-wide association studies (GWASs), is to estimate individual-specific genetic propensities and predict outcomes. This is typically achieved using a single polygenic score, but here we use a multi-polygenic score (MPS) approach to increase predictive power by exploiting the joint power of multiple discovery GWASs, without assumptions about the relationships among predictors. We used summary statistics of 81 well-powered GWASs of cognitive, medical and anthropometric traits to predict three core developmental outcomes in our independent target sample: educational achievement, body mass index (BMI) and general cognitive ability. We used regularized regression with repeated cross-validation to select from and estimate contributions of 81 polygenic scores in a UK representative sample of 6710 unrelated adolescents. The MPS approach predicted 10.9% variance in educational achievement, 4.8% in general cognitive ability and 5.4% in BMI in an independent test set, predicting 1.1%, 1.1%, and 1.6% more variance than the best single-score predictions. As other relevant GWA analyses are reported, they can be incorporated in MPS models to maximize phenotype prediction. The MPS approach should be useful in research with modest sample sizes to investigate developmental, multivariate and gene-environment interplay issues and, eventually, in clinical settings to predict and prevent problems using personalized interventions.

Figure 1

(a) Multi-polygenic score (MPS) model predicting educational achievement. Standardized coefficients of polygenic predictors selected by elastic net via repeated cross-validation in training set. Analogous to conventional multiple regression, a standardized coefficient represents the contribution of the predictor to the outcome when adjusting for all other variables in the model. The mean variance explained of the resampling distribution from the cross-validation was mean-cv-R²_train=0.12. The out-of-sample prediction of the model was R²_test=0.109. (b) MPS model predicting general cognitive ability. Standardized coefficients of polygenic predictors selected by elastic net via repeated cross-validation in training set. Analogous to conventional multiple regression, a standardized coefficient represents the contribution of the predictor to the outcome when adjusting for all other variables in the model. The mean variance explained of the resampling distribution from the cross-validation was mean-cv-R²_train=0.051. The out-of-sample prediction of the model was R²_test=0.048. (c) MPS model predicting body mass index (BMI). Standardized coefficients of polygenic predictors selected by elastic net via repeated cross-validation in training set. Analogous to conventional multiple regression, a standardized coefficient represents the contribution of the predictor to the outcome when adjusting for all other variables in the model. The mean variance explained of the resampling distribution from the cross-validation was mean-cv-R²_train=0.074. The out-of-sample prediction of the model was R²_test=0.054.

Figure 2

(a) Educational achievement by multi-polygenic score (MPS) deciles. Observed mean grade (across the three subjects Mathematics, English and Science) by deciles of the MPS predictions in the test set. Bars represent 95% confidence estimates. (b) General cognitive ability by MPS deciles. Observed mean standardized general cognitive ability by deciles of the MPS predictions in the test set. Bars represent 95% confidence estimates. (c) Body mass index (BMI) by MPS deciles. Observed mean standardized BMI (age and sex adjusted by external reference) by deciles of the MPS predictions in the test set. Bars represent 95% confidence estimates.