Development of genome-wide polygenic risk scores for lipid traits and clinical applications for dyslipidemia, subclinical atherosclerosis, and diabetes cardiovascular complications among East Asians

Abstract

Background: The clinical utility of personal genomic information in identifying individuals at increased risks for dyslipidemia and cardiovascular diseases remains unclear.

Methods: We used data from Biobank Japan (n = 70,657-128,305) and developed novel East Asian-specific genome-wide polygenic risk scores (PRSs) for four lipid traits. We validated (n = 4271) and subsequently tested associations of these scores with 3-year lipid changes in adolescents (n = 620), carotid intima-media thickness (cIMT) in adult women (n = 781), dyslipidemia (n = 7723), and coronary heart disease (CHD) (n = 2374 cases and 6246 controls) in type 2 diabetes (T2D) patients.

Results: Our PRSs aggregating 84-549 genetic variants (0.251 < correlation coefficients (r) < 0.272) had comparably stronger association with lipid variations than the typical PRSs derived based on the genome-wide significant variants (0.089 < r < 0.240). Our PRSs were robustly associated with their corresponding lipid levels (7.5 × 10^{- 103} < P < 1.3 × 10^{- 75}) and 3-year lipid changes (1.4 × 10^{- 6} < P < 0.0130) which started to emerge in childhood and adolescence. With the adjustments for principal components (PCs), sex, age, and body mass index, there was an elevation of 5.3% in TC (β ± SE = 0.052 ± 0.002), 11.7% in TG (β ± SE = 0.111 ± 0.006), 5.8% in HDL-C (β ± SE = 0.057 ± 0.003), and 8.4% in LDL-C (β ± SE = 0.081 ± 0.004) per one standard deviation increase in the corresponding PRS. However, their predictive power was attenuated in T2D patients (0.183 < r < 0.231). When we included each PRS (for TC, TG, and LDL-C) in addition to the clinical factors and PCs, the AUC for dyslipidemia was significantly increased by 0.032-0.057 in the general population (7.5 × 10^{- 3} < P < 0.0400) and 0.029-0.069 in T2D patients (2.1 × 10^{- 10} < P < 0.0428). Moreover, the quintile of TC-related PRS was moderately associated with cIMT in adult women (β ± SE = 0.011 ± 0.005, P_trend = 0.0182). Independent of conventional risk factors, the quintile of PRSs for TC [OR (95% CI) = 1.07 (1.03-1.11)], TG [OR (95% CI) = 1.05 (1.01-1.09)], and LDL-C [OR (95% CI) = 1.05 (1.01-1.09)] were significantly associated with increased risk of CHD in T2D patients (4.8 × 10^{- 4} < P < 0.0197). Further adjustment for baseline lipid drug use notably attenuated the CHD association.

Conclusions: The PRSs derived and validated here highlight the potential for early genomic screening and personalized risk assessment for cardiovascular disease.

Keywords: Diabetes cardiovascular complications; East Asians; Lipid traits; Polygenic risk scores; Subclinical atherosclerosis.

Fig. 1

Study design and workflow. A polygenic risk score (PRS) for each lipid trait was derived by (1) association statistics from the Biobank Japanese Project and (2) linkage disequilibrium (LD) between genetic variants from a reference panel of 504 East Asians in 1000 Genomes Project. A total of 34 candidate PRSs were developed using two strategies: (1) the “pruning and thresholding” approach, which involves pruning the genetic variants based on the pairwise threshold of LD r² (0.2, 0.4, and 0.6), and subsequently applying a p value threshold (1, 0.5, 0.1, 0.05, 0.01, 1 × 10⁻³, 1 × 10⁻⁴, 1 × 10⁻⁵, and 5 × 10⁻⁸) to the association statistics. And (2) the LDPred computational algorithm, a Bayesian method that estimates the posterior mean causal effect for each variant by assuming a prior effect size from summary statistics and LD information from an external reference panel. Multiple LDpred scores were calculated by varying the tuning parameter ρ (1, 0.3, 0.1, 0.03, 0.01, 3 × 10^− 3, and 1 × 10^− 3) which are the fractions of markers with non-zero effects. The optimal PRS for each lipid trait was chosen based on maximal correlation with the corresponding lipid trait in a total of 4271 individuals in the validation datasets, and then tested for the associations with lipid metabolism, changes in lipid levels, and cardiovascular risk in multiple independent cohorts

Fig. 2

Odds ratio (OR) of coronary heart disease stratified by quintile of polygenic risk scores [a PRS_TC, b PRS_TG, c PRS_HDL, and d PRS_LDL] in T2D patients (n = 2374 cases vs 6246 controls). P_linear refers to the p value testing for a linear trend across five quintiles of polygenic risk score. P_top refers to the p value testing for the association of a high polygenic risk score with coronary heart disease by comparing the top 20% of the distribution with the remaining 80% of the distribution. P_bottom refers to the p value testing for the association of a low polygenic risk score with coronary heart disease by comparing the bottom 20% of the distribution with the remaining 80% of the distribution. Within each individual cohort, all p values were obtained from logistic regression with the adjustment of principal components, sex, age, duration of diabetes, body mass index, smoking status, HbA1c, systolic blood pressure, estimated glomerular filtration rate, and log-transformed albumin-creatinine ratio. Results from individual cohorts were meta-analyzed using fixed effects model