Integrative common and rare variant analyses provide insights into the genetic architecture of liver cirrhosis

Abstract

We report a multi-ancestry genome-wide association study on liver cirrhosis and its associated endophenotypes, alanine aminotransferase (ALT) and γ-glutamyl transferase. Using data from 12 cohorts, including 18,265 cases with cirrhosis, 1,782,047 controls, up to 1 million individuals with liver function tests and a validation cohort of 21,689 cases and 617,729 controls, we identify and validate 14 risk associations for cirrhosis. Many variants are located near genes involved in hepatic lipid metabolism. One of these, PNPLA3 p.Ile148Met, interacts with alcohol intake, obesity and diabetes on the risk of cirrhosis and hepatocellular carcinoma (HCC). We develop a polygenic risk score that associates with the progression from cirrhosis to HCC. By focusing on prioritized genes from common variant analyses, we find that rare coding variants in GPAM associate with lower ALT, supporting GPAM as a potential target for therapeutic inhibition. In conclusion, this study provides insights into the genetic underpinnings of cirrhosis.

Fig. 1. Study design and main results.

a, Overall study design, with stage 1 representing the European-specific GWAS meta-analysis and stage 2 representing the cross-ancestry GWAS meta-analysis. b, Miami plot of cirrhosis GWAS. The x axis is the chromosomal location of SNPs and the y axis is the strength of association −log₁₀(P). Note that the y axis includes a break at 50. The lead SNPs and SNPs located within ±1 Mb are highlighted, and the nearest genes are annotated. The top plot shows results from the European-specific GWAS meta-analysis, whereas the bottom plot displays results from the cross-ancestry GWAS meta-analysis. The dashed red line represents the threshold for genome-wide significance (P < 5 × 10⁻⁸). P values were two-sided and based on an IVW fixed-effects meta-analysis, and not adjusted for multiple testing.

Fig. 2. Cross-trait associations between cirrhosis variants and selected metabolic and hepatobiliary traits relevant for cirrhosis.

The heatmap shows associations of variants identified through cirrhosis GWAS meta-analysis or endophenotype-driven analyses with 41 binary and quantitative traits sampled from meta-analysis of data from CHB-CID/DBDS, deCODE, Intermountain Healthcare, FinnGen, UKB and external sources, where available. The number of cases for binary traits and sample size for quantitative traits are shown in parenthesis following each trait. Shown are variants and phenotypes with significant associations after correcting for multiple testing using an FDR of <0.05. P values (two-sided) were derived from linear and logistic regression models. Hierarchical clustering was performed on a variant level using the complete linkage method based on Euclidian distance. Coloring represents z scores for each respective trait or disease, oriented toward the cirrhosis risk-increasing allele. Red indicates an increase in the trait or disease risk, while blue indicates a decrease in the trait or disease risk. SHBG, sex hormone-binding globulin; IGF-1, insulin growth factor 1; ApoA, apolipoprotein A; ApoB, apolipoprotein B; COPD, chronic obstructive pulmonary disease; WHRadjBMI, waist-to-hip-ratio adjusted for BMI; LDL-C, low-density lipoprotein cholesterol; T1D, type 1 diabetes.

Fig. 3. Comparison of genetic associations with NAFLD, ALD and cirrhosis.

a, Shown are the effects of 18 previously reported NAFLD variants and 36 cirrhosis variants identified in this study, totaling 38 distinct signals. The NAFLD effects were derived from meta-analysis of data from deCODE, UKB, CHB, Intermountain Healthcare and FinnGen (n = 22,944). Cirrhosis effects were derived from the cross-ancestry meta-analysis. Variants that had stronger effects (P_Het < 0.05/38, that is corrected for 38 tests) on NAFLD compared with cirrhosis are colored blue, while variants with stronger effects on cirrhosis compared with NAFLD are colored red. b, Shown are the effects of the 36 cirrhosis variants on NAFLD (n = 22,944) and ALD (n = 2,931). Variants with stronger effects (P_Het < 0.05/36, that is corrected for 36 tests) on ALD compared with NAFLD are colored red. For both a and b, points refer to effect estimates (log(OR), measure of center), error bars represent 95% CI and the solid line represents the line of best fit. The dashed identity line (y = x) is shown for reference. P_Het were two-sided and obtained using a likelihood ratio test (Cochran’s Q).

Fig. 4. Interaction between PNPLA3 p.Ile148Met (rs738409), environment and risk of liver-related outcomes in the UKB.

Shown are the association between rs738409 carrier status and risk of five liver outcomes according to BMI categories (<30 versus ≥30 kg m⁻²), weekly alcohol intake (≤14 versus >14 weekly drinks) and T2D (no versus yes). Points refer to OR (measure of center), error bars represent 95% CIs and P represents P value for interaction. We used logistic regression models, adjusted for age, sex and ten principal components (PCs). Interactions between the variant and environmental factors were evaluated using likelihood ratio tests, comparing a main-effect model (variant + environmental factor) with a model including an interaction term (variant × environmental factor). The number of exposed individuals and the number of outcomes within each subcategory are listed in Supplementary Table 15.

Fig. 5. PRSs and hepatobiliary outcomes.

Associations between six different PRS (PRS_ALT, PRS_5-SNP, PRS_15-SNP, PRS_36-SNP, PRS_EUR and PRS_CA) and hepatobiliary outcomes in the UKB. Points refer to ORs (measure of center) per s.d. increase in PRS; error bars represent 95% CIs. Total number of cases is provided following each outcome. Logistic regression models were used, adjusted for age, sex and ten PCs.

Fig. 6. PRSs and disease progression.

a,b, Risk of HCC in individuals with liver cirrhosis according to polygenic risk percentile. c,d, Risk of cirrhosis in individuals with NAFLD diagnosis, according to polygenic risk percentile. We used the PRS_15-SNP to assign individuals to different risk groups. Cumulative incidence (solid line, measure of center) was estimated using Fine-Gray regression, which takes the competing risk of death into account. The lighter shades represent the respective 95% CIs. Number of individuals at risk according to each exposure group and events are given below each plot.