Using polygenic scores for identifying individuals at increased risk of substance use disorders in clinical and population samples

Abstract

Genome-wide, polygenic risk scores (PRS) have emerged as a useful way to characterize genetic liability. There is growing evidence that PRS may prove useful for early identification of those at increased risk for certain diseases. The current potential of PRS for alcohol use disorders (AUD) remains an open question. Using data from both a population-based sample [the FinnTwin12 (FT12) study] and a high-risk sample [the Collaborative Study on the Genetics of Alcoholism (COGA)], we examined the association between PRSs derived from genome-wide association studies (GWASs) of (1) alcohol dependence/alcohol problems, (2) alcohol consumption, and (3) risky behaviors with AUD and other substance use disorder (SUD) criteria. These PRSs explain ~2.5-3.5% of the variance in AUD (across FT12 and COGA) when all PRSs are included in the same model. Calculations of area under the curve (AUC) show PRS provide only a slight improvement over a model with age, sex, and ancestral principal components as covariates. While individuals in the top 20, 10, and 5% of the PRS distribution had greater odds of having an AUD compared to the lower end of the continuum in both COGA and FT12, the point estimates at each threshold were statistically indistinguishable. Those in the top 5% reported greater levels of licit (alcohol and nicotine) and illicit (cannabis and opioid) SUD criteria. PRSs are associated with risk for SUD in independent samples. However, usefulness for identifying those at increased risk in their current form is modest, at best. Improvement in predictive ability will likely be dependent on increasing the size of well-phenotyped discovery samples.

Fig. 1. Parameter estimates for PRS in independent and conditional models.

Parameter estimates (with 95% confidence intervals), from linear mixed models for alcohol use disorder (AUD) criteria regressed on polygenic risk scores (PRS) for drinks per week (GSCAN DPW), problem alcohol use (PROB ALC), and risky behaviors (RISK PC) in COGA and FT12. Independent = model with only corresponding PRS. Conditional = model with all PRS included. Adjusted for age, sex, first 10 ancestral principal components, genotyping array, and data collection site (only COGA for the latter two). All tests were two-sided.

Fig. 2. ROC curves for baseline and PRS models.

Receiver operating characteristic (ROC) curves for baseline models (covariates only) and polygenic risk score (PRS) models (PRS + covariate) for each level of severity in alcohol use disorder (AUD). Area under the curve (AUC) for the PRS model (Full AUC) and change in in AUC from Base to PRS model (Δ AUC) is presented each cell. AUC provides an estimate of the probability a randomly selected subject with the condition has a test result indicating greater suspicion than that of a randomly chosen subject without the condition. An AUC of 0.5 indicates that a classifier does not provide any useful information in determining cases from controls.

Fig. 3. Top 5% of PRS Continuum.

Mean levels of substance use disorder (SUD) criteria for alcohol, cannabis, cocaine, nicotine, and opioid use disorders for top 5% of each polygenic risk score (PRS) compared to the bottom 95%. Black bar represents mean of bottom 95% of each sample. 95% confidence intervals estimated using 1000 bootstrap resampling.