Lymphocyte activation gene-3-associated protein networks are associated with HDL-cholesterol and mortality in the Trans-omics for Precision Medicine program

Abstract

Deficiency of the immune checkpoint lymphocyte activation gene-3 (LAG3) protein is significantly associated with both elevated HDL-cholesterol (HDL-C) and myocardial infarction risk. We determined the association of genetic variants within ±500 kb of LAG3 with plasma LAG3 and defined LAG3-associated plasma proteins with HDL-C and clinical outcomes. Whole genome sequencing and plasma proteomics were obtained from the Multi-Ethnic Study of Atherosclerosis (MESA) and the Framingham Heart Study (FHS) cohorts as part of the Trans-Omics for Precision Medicine program. In situ Hi-C chromatin capture was performed in EBV-transformed cell lines isolated from four MESA participants. Genetic association analyses were performed in MESA using multivariate regression models, with validation in FHS. A LAG3-associated protein network was tested for association with HDL-C, coronary heart disease, and all-cause mortality. We identify an association between the LAG3 rs3782735 variant and plasma LAG3 protein. Proteomics analysis reveals 183 proteins significantly associated with LAG3 with four proteins associated with HDL-C. Four proteins discovered for association with all-cause mortality in FHS shows nominal associations in MESA. Chromatin capture analysis reveals significant cis interactions between LAG3 and C1S, LRIG3, TNFRSF1A, and trans interactions between LAG3 and B2M. A LAG3-associated protein network has significant associations with HDL-C and mortality.

Fig. 1. Regional association plots for statistically significant genetic association study region based on meta-analysis results of MESA on LAG3 protein levels in Exam 1.

The plot presents results for the index variant rs3782735 at chr12:6775910 +/- 250 kb, with linkage disequilibrium determined using the multi-ethnic TOPMed WGS data from MESA.

Fig. 2. Study design for discovery/validation of genetic association analysis of LAG3 protein levels in MESA and FHS.

Abbreviations: Afr. Amer. = African American; HC = heterozygosity count; FDR = False discovery rate.

Fig. 3. LAG3 related proteins with (a) HDL-C associations discovered and validated in both MESA and FHS, and (b) all-cause mortality associations discovered in FHS and with nominal support from MESA.

Plots show estimated effects and 95% confidence limits. Analyses were performed with inverse normal transformed protein levels in MESA and log-transformed protein levels in FHS. a Association of HDL-C with protein levels was examined by linear regression with covariate adjustment for age, sex, study site (in MESA), race/ethnicity (in MESA), PCs of ancestry, BMI, triglycerides, pack-years of smoking (in MESA), current smoking (in FHS), current alcohol use, LAG3 protein level, plate ID and batch (in FHS). Among the 183 proteins examined for association with HDL-C in both MESA and FHS, four of them were discovered and validated in both cohorts (leucine rich repeats and immunoglobulin like domains 3 [LRIG3], DNV family receptor alpha 1 [GFRA1], insulin like growth factor 1 receptor [IGF1R] and DCTP pyrophosphatase 1 [DCTPP1]). b Of the 183 proteins examined for association with CHD and all-cause mortality in MESA, we did not observe any results at FDR < 0.05. In FHS, while there were no associations at FDR < 0.05 for CHD, we observed that 18 of the 183 LAG3-associated proteins demonstrating FDR < 0.05 were significantly associated with all-cause mortality based on two-sided Z-tests for the coefficients from Cox regression with a total sample of n = 1913, including 650 events (Supplementary Data 12). In MESA, none of these 18 proteins reached Bonferroni-corrected statistical significance, but four of the 18 proteins showed nominal associations with all-cause mortality (tumor necrosis factor receptor super family 1 A [TNFRSF1A], beta-2-microglobulin [B2M], tumor necrosis factor receptor super family 1B [TNFRSF1B] and cystatin C [CST3]; all P < 0.05 based on two-sided Z-tests for the coefficients from Cox regression with n = 935 including 95 events. Association of baseline protein levels with all-cause mortality was examined under a Cox proportional hazards model with covariate adjustment for age, sex, race/ethnicity (in MESA), PCs of ancestry, BMI, total cholesterol, HDL-C, SBP, DBP, pack-years of smoking (in MESA), current smoking status (in FHS) and batch (in FHS).

Fig. 4. Hi-C near cis and cis interactions from the LAG3 locus on chromosome 12: MESA.

We performed in situ Hi-C analysis in EBV-transformed B lymphoblasts from two female (one African-American and one Hispanic) MESA carriers homozygous for the SCARB1 rs10846744 reference G and two female (one African-American and one Hispanic) MESA carriers homozygous for the effect C alleles. The in situ Hi-C analysis was performed as recommended by the 4D Nucleome Consortium using the four base pair cutter DpnII restriction enzyme and high read depth next gen sequencing (NGS) to maximize resolution of the high frequency interactions between chromatin contacts (https://www.4dnucleome.org/protocols.html). Each cell library underwent deep NGS at read depths between 1.4–3.3 billion and this was done independently twice as technical replicates for each cell library. Bioinformatic analysis was conducted using Hi-C Pro software with binning of the matrix at different resolutions and iterative correction and eigenvector decompensation normalization of the matrix for each of the four libraries^,. Readouts were all valid paired-end reads and corresponding high frequency contact interaction scores. We then used data generated from the million binning resolution and filtered it based on the LAG3 chromosomal coordinates (chr12:677250-6778455) using human assembly GRCh38/hg38 (https://genome.ucsc.edu/cgi-bin/hgGateway), which yielded both cis (chr12) and trans interactions. We set interaction scores at the LAG3 locus arbitrarily at 1 and then compared interaction scores from direct and indirect cis and trans interactions. Student t-test was performed with P ≤ 0.05 considered statistically significant. The results shown are representative from one of the MESA cell lines, with the schematic representing the near cis (panel a) and cis interactions (panel b) from the LAG3 locus on chromosome 12.