Trans-ancestral rare variant association study with machine learning-based phenotyping for metabolic dysfunction-associated steatotic liver disease

Abstract

Background: Genome-wide association studies (GWAS) have identified common variants associated with metabolic dysfunction-associated steatotic liver disease (MASLD). However, rare coding variant studies have been limited by phenotyping challenges and small sample sizes. We test associations of rare and ultra-rare coding variants with proton density fat fraction (PDFF) and MASLD case-control status in 736,010 participants of diverse ancestries from the UK Biobank, All of Us, and BioMe and performed a trans-ancestral meta-analysis. We then developed models to accurately predict PDFF and MASLD status in the UK Biobank and tested associations with these predicted phenotypes to increase statistical power.

Results: The trans-ancestral meta-analysis with PDFF and MASLD case-control status identifies two single variants and two gene-level associations in APOB, CDH5, MYCBP2, and XAB2. Association testing with predicted phenotypes, which replicates more known genetic variants from GWAS than true phenotypes, identifies 16 single variants and 11 gene-level associations implicating 23 additional genes. Two variants were polymorphic only among African ancestry participants and several associations showed significant heterogeneity in ancestry and sex-stratified analyses. In total, we identified 27 genes, of which 3 are monogenic causes of steatosis (APOB, G6PC1, PPARG), 4 were previously associated with MASLD (APOB, APOC3, INSR, PPARG), and 23 had supporting clinical, experimental, and/or genetic evidence.

Conclusions: Our results suggest that trans-ancestral association analyses can identify ancestry-specific rare and ultra-rare coding variants in MASLD pathogenesis. Furthermore, we demonstrate the utility of machine learning in genetic investigations of difficult-to-phenotype diseases in trans-ancestral biobanks.

Keywords: Genetic association studies; Machine learning; Metabolic dysfunction-associated steatotic liver disease.

Fig. 1

Study workflow. Abbreviations: PDFF, proton density fat fraction; MRI, magnetic resonance imaging; PTV, protein-truncating variant

Fig. 2

Variants and genes identified by true phenotypes across the UK Biobank, All of Us, and BioMe. A–B Manhattan plots showing associations from single variant testing (A) and gene-level testing (B). The red dashed lines represent thresholds for exome-wide significance (A; 4.3 × 10⁻⁷) and Bonferroni significance (B; 2.7 × 10⁻⁶). C–D Single variant associations, labeled as chromosome:position:reference allele:effect allele (gene) (effect direction), and gene-level associations, labeled as gene (effect direction), with MASLD-related measurements (C) as well as outcomes and risk factors (D). Only associations with p < 0.05 are shown. For most measurements and all outcomes and risk factors, associations represent a meta-analysis of results from UK Biobank, All of Us, and BioMe. The color of each box indicates the effect size and direction (Z score); for display purposes, Z scores are capped at 10 and − 10. Complete data are available in Additional file 1: Tables S9–S10. Abbreviations: CRP, C-reactive protein; ALP alkaline phosphatase; ALT, alanine aminotransferase; AST, aspartate aminotransferase; GGT, gamma-glutamyltransferase; SHBG, sex hormone binding globulin

Fig. 3

Construction of machine learning-predicted phenotypes in the UK Biobank. A 2D histogram comparing predicted log(PDFF) at the imaging visit with true log(PDFF) at the imaging visit. B 2D histogram comparing predicted log(PDFF) at the baseline visit with true log(PDFF) at the imaging visit. C Top 20 features for the PDFF prediction model as determined by SHapley Additive exPlanations (SHAP) analysis. The color of each bar reflects Spearman’s ρ between feature values and SHAP values. D Genetic correlations between true and predicted phenotypes in the UK Biobank. “Predicted PDFF (subset)” represents testing of predicted PDFF only among participants with true PDFF measureemnts. Abbreviations: SHBG (sex hormone binding globulin)

Fig. 4

Variants and genes identified by predicted phenotypes in the UK Biobank. A–B Manhattan plots showing associations from single variant testing (A) and gene-level testing (B). The red dashed lines represent thresholds for exome-wide significance (A; 4.3 × 10⁻⁷) and Bonferroni significance (B; 2.7 × 10⁻⁶). Genes and variants marked with an asterisk did not pass post hoc filtering (i.e., nominal association with a true phenotype or with both liver enzymes and metabolic dysfunction markers) and were not further analyzed

Fig. 5

MASLD-related trait associations for predicted phenotype variants and genes. A–D Single variant associations, labeled as chromosome:position:reference allele:effect allele (gene) (effect direction), and gene-level associations, labeled as gene (effect direction), with MASLD-related measurements (A–B) as well as outcomes and risk factors (C–D). Only associations with p < 0.05 are shown. For most phenotypes, associations represent a meta-analysis of results from UK Biobank, All of Us, and BioMe. The color of each box indicates the effect size and direction (Z score). Complete data are available in Additional file 1: Tables S9–S10. A, C Single variants and genes positively associated with predicted MASLD/PDFF. B, D Single variants and genes negatively associated with predicted MASLD/PDFF. Abbreviations: CRP, C-reactive protein; ALP, alkaline phosphatase; ALT, alanine aminotransferase; AST, aspartate aminotransferase; GGT, gamma-glutamyltransferase; SHBG, sex hormone binding globulin

Fig. 6

Supporting evidence for MASLD-associated genes. Clinical, experimental, and genetic evidence for genes identified in this study. Genes in tiers 1, 2, 3, and 4 have ≥ 4, 3, 2, or ≤ 1 sources of evidence, respectively. For clinical phenotypes, “MASLD” includes monogenic causes of steatosis (e.g., abetalipoproteinemia, familial partial lipodystrophy, glycogen storage disease 1a). For clinical phenotypes, animal models, and genetic associations, “MASLD-related phenotype” includes metabolic dysfunction phenotypes (e.g., metabolic syndrome, type 2 diabetes). Complete data are available in Additional file 1: Table S24