Autoimmune diseases and risk of non-Hodgkin lymphoma: A Mendelian randomisation study

Abstract

Objective: To examine whether genetically predicted susceptibility to ten autoimmune diseases (Behçet's disease, coeliac disease, dermatitis herpetiformis, lupus, psoriasis, rheumatoid arthritis, sarcoidosis, Sjögren's syndrome, systemic sclerosis, and type 1 diabetes) is associated with risk of non-Hodgkin lymphoma (NHL).

Design: Two sample Mendelian randomization (MR) study.

Setting: Genome wide association studies (GWASs) of ten autoimmune diseases, NHL, and four NHL subtypes (i.e., follicular lymphoma, mature T/natural killer-cell lymphomas, non-follicular lymphoma, and other and unspecified types of NHL).

Analysis: We used data from the largest publicly available GWASs of European ancestry for each autoimmune disease, NHL, and NHL subtypes. For each autoimmune disease, we extracted single nucleotide polymorphisms (SNPs) strongly associated (P < 5×10^-8) with that disease and that were independent of one another (R² < 1×10^-3) as genetic instruments. SNPs within the human leukocyte antigen region were not considered due to potential pleiotropy. Our primary MR analysis was the inverse-variance weighted analysis. Additionally, we conducted MR-Egger, weighted mode, and weighted median regression to address potential bias due to pleiotropy, and robust adjusted profile scores to address weak instrument bias. We carried out sensitivity analysis limited to the non-immune pathway for nominally significant findings. To account for multiple testing, we set the thresholds for statistical significance at P < 5×10^-3.

Participants: The number of cases and controls identified in the relevant GWASs were 437 and 3,325 for Behçet's disease, 4,918 and 5,684 for coeliac disease, 435 and 341,188 for dermatitis herpetiformis, 4,576 and 8,039 for lupus, 11,988 and 275,335 for psoriasis, 22,350 and 74,823 for rheumatoid arthritis, 3,597 and 337,121 for sarcoidosis, 2,735 and 332,115 for Sjögren's syndrome, 9,095 and 17,584 for systemic sclerosis, 18,942 and 501,638 for type 1 diabetes, 2,400 and 410,350 for NHL; and 296 to 2,340 cases and 271,463 controls for NHL subtypes.

Exposures: Genetic variants predicting ten autoimmune diseases: Behçet's disease, coeliac disease, dermatitis herpetiformis, lupus, psoriasis, rheumatoid arthritis, sarcoidosis, Sjögren's syndrome, systemic sclerosis, and type 1 diabetes.

Main outcome measures: Estimated associations between genetically predicted susceptibility to ten autoimmune diseases and the risk of NHL.

Results: The variance of each autoimmune disease explained by the SNPs ranged from 0.3% to 3.1%. Negative associations between type 1 diabetes and sarcoidosis and the risk of NHL were observed (odds ratio [OR] 0.95, 95% confidence interval [CI]: 0.92 to 0.98, P = 5×10^-3, and OR 0.92, 95% CI: 0.85 to 0.99, P = 2.8×10^-2, respectively). These findings were supported by the sensitivity analyses accounting for potential pleiotropy and weak instrument bias. No significant associations were found between the other eight autoimmune diseases and NHL risk. Of the NHL subtypes, type 1 diabetes was most strongly associated with follicular lymphoma (OR 0.91, 95% CI: 0.86 to 0.96, P = 1×10^-3), while sarcoidosis was most strongly associated with other and unspecified NHL (OR 0.86, 95% CI: 0.75 to 0.97, P = 1.8×10^-2).

Conclusions: These findings suggest that genetically predicted susceptibility to type 1 diabetes, and to some extent sarcoidosis, might reduce the risk of NHL. However, future studies with different datasets, approaches, and populations are warranted to further examine the potential associations between these autoimmune diseases and the risk of NHL.

Keywords: Autoimmune diseases; Mendelian randomisation; Non-Hodgkin lymphoma; Sarcoidosis; Type 1 diabetes.

Figure 1.. A schematic overview of the study design

Abbreviations: EXP: exposure; HLA: human leukocyte antigen; MR: mendelian randomisation; OUT: outcome; RAPS: robust adjusted profile scores; SNP: single nucleotide polymorphism. Wald ratio: ${\beta }_{\text{EXP-OUT}}=\frac{{\beta }_{\mathrm{S}\mathrm{N}\mathrm{P}\text{-OUT}}}{{\beta }_{\mathrm{S}\mathrm{N}\mathrm{P}\text{-}\mathrm{E}\mathrm{X}\mathrm{P}}}$; The analyses were carried out in three steps: Step 1, genetic instruments for each autoimmune disease were selected from relevant GWASs (i.e., P < 5 ×10⁻ and an R²<0.001), with ${\beta }_{\text{SNP-EXP}}$ (i.e., association between genetic instrument and the exposure) extracted. Step 2, for these genetic instruments, the genetic instrument-outcome associations ${\beta }_{\text{SNP-OUT}}$ were extracted from the outcome GWAS. Step 3, for each autoimmune disease, the Wald ratio (i.e., the causal estimate) was estimated for $k$ number of SNPs by the formula ${\beta }_{\text{EXP-OUT}}={\beta }_{\text{SNP-OUT}}{/\beta }_{\text{SNP-EXP}}$, and next summarised using the listed MR analyses. In the secondary analyses, only inverse-variance weighted method was applied.

Figure 2a.. Genetically predicted susceptibility to ten autoimmune diseases and risk of non-Hodgkin lymphoma overall

Abbreviations: CI: confidence interval; IVW: inverse-variance weighted; MR: mendelian randomisation; OR: odds ratio; RAPS: robust adjusted profile scores. Legend: all causal estimates were multiplied by 0.693 and next exponentiated in order to represent the odds ratios (ORs) for NHL per doubling in the prevalence of the autoimmune disease under study.

Figure 2b.. Genetically predicted susceptibility to ten autoimmune diseases and risk of non-Hodgkin lymphoma overall

Abbreviations: CI: confidence interval; IVW: inverse-variance weighted; MR: mendelian randomisation; OR: odds ratio; RAPS: robust adjusted profile scores. Legend: all causal estimates were multiplied by 0.693 and next exponentiated in order to represent the odds ratios (ORs) for NHL per doubling in the prevalence of the autoimmune disease under study.

Figure 3.. Inverse-variance weighted analyses of genetically predicted susceptibility to type 1 diabetes, and sarcoidosis, and risk of non-Hodgkin lymphoma subtypes

Abbreviations: CI: confidence interval; NHL: non-Hodgkin lymphoma; OR: odds ratio.

Legend: 1. the analyses were based on inverse-variance weighted approach. 2. all causal estimates were multiplied by 0.693 and next exponentiated in order to represent the odds ratios (ORs) for NHL per doubling in the prevalence of the autoimmune disease under study. 3. As mentioned in Table 2, we used different datasets for NHL and NHL subtypes.