Systematic Mendelian randomization using the human plasma proteome to discover potential therapeutic targets for stroke

Abstract

Stroke is the second leading cause of death with substantial unmet therapeutic needs. To identify potential stroke therapeutic targets, we estimate the causal effects of 308 plasma proteins on stroke outcomes in a two-sample Mendelian randomization framework and assess mediation effects by stroke risk factors. We find associations between genetically predicted plasma levels of six proteins and stroke (P ≤ 1.62 × 10^-4). The genetic associations with stroke colocalize (Posterior Probability >0.7) with the genetic associations of four proteins (TFPI, TMPRSS5, CD6, CD40). Mendelian randomization supports atrial fibrillation, body mass index, smoking, blood pressure, white matter hyperintensities and type 2 diabetes as stroke risk factors (P ≤ 0.0071). Body mass index, white matter hyperintensity and atrial fibrillation appear to mediate the TFPI, IL6RA, TMPRSS5 associations with stroke. Furthermore, thirty-six proteins are associated with one or more of these risk factors using Mendelian randomization. Our results highlight causal pathways and potential therapeutic targets for stroke.

Fig. 1. Overview of this MR study.

Four O-link panels were used to measure plasma proteins in a subset of ~5000 samples from the INTERVAL study. Genetic variants associated with plasma protein levels were identified based on results from their corresponding GWAS. These genetic variants were then used as proxies for the protein level to test their relationship with stroke using data from the MEGASTROKE consortium for stroke outcomes (Primary MR), and with conventional stroke risk factors that were causally associated with stroke (Secondary MR). Colocalization analyses were performed to test the shared genetic associations of protein level, stroke outcomes and risk factors. Mediation analyses by two-step MR were performed for proteins that were potentially causally associated with both risk factors and stroke outcomes. We also tested the relationships of the potentially causal stroke proteins with 784 phenotypes in the UK Biobank to test a broad spectrum of potential effects of hypothetical therapeutic agents for stroke. ^#Stroke outcomes: any stroke; any ischaemic stroke; large artery stroke; cardioembolic stroke; small vessel stroke.

Fig. 2. Venn diagram of identified potential causal proteins for stroke subtypes.

* Indicates the according to protein is instrumented by cis-pQTLs only. These six proteins are taken for further analyses.

Fig. 3. Effects of six potential causal proteins on stroke outcomes.

MR analyses of the effect of proteins on stroke outcomes. The squares are the causal estimates on the OR scale, and the whiskers represent the 95% confidence intervals for these ORs. N_SNPs: number of SNPs used for the estimation of the causal effects in this plot. P values were determined from the inverse-variance-weighted two-sample MR method. Statistical heterogeneity was assessed using the I² statistic. OR odds ratio, CD40 B cell surface antigen CD40, TFPI tissue factor pathway inhibitor, MMP12 matrix metallopeptidase 12, IL6RA interleukin 6 receptor subunit alpha, TMPRSS5 transmembrane serine protease 5, CD6 T-cell differentiation antigen CD6.

Fig. 4. Causal effects of risk factors on stroke outcomes.

MR analyses of the effect of risk factors on stroke outcomes. The squares are the causal estimates on the OR scale, and the whiskers represent the 95% confidence intervals for these ORs. N_SNPs number of SNPs used for the estimation of the causal effects in this plot. P values were determined from the inverse-variance-weighted two-sample MR method. Statistical heterogeneity was assessed using the I² statistic. OR odds ratio, SBP systolic blood pressure, AF atrial fibrillation, WMH white matter hyperintensity, T2D type 2 diabetes, BMI body mass index, Smoking smoking initiation.

Fig. 5. Effect sizes (Z-score) of six potential causal proteins on stroke outcomes and causal risk factors for stroke.

MR analyses of the effect of proteins on stroke and stroke risk factors. Colours in each lattice of the heatmap represent the effect size (Z-score), with genetically predicted increased protein level associated with a higher risk of outcomes coloured in brown and lower risk of outcomes coloured in blue. The darker the colour the larger the effect size. *Indicates that the causal association is significant, which passed Bonferroni correction of P_{causalEstimate_IVW} ≤ 0.05/308 = 1.61 × 10⁻⁴ and passed sensitivity tests with P_Qstat ≥ 0.05 and P_{EggerIntercept} ≥ 0.05.

Fig. 6. Mediation effects of protein on stroke via risk factors.

Mediation analyses to quantify the effects of three proteins on stroke outcomes via risk factors. a TFPI effect on stroke mediated by BMI. b TFPI effect on stroke mediated by WMH; c TMPRSS5 effect on cardioembolic stroke mediated by AF; d IL6RA effect on stroke mediated by AF. $\mathrm{\beta }$_EM effects of exposure on mediator, $\mathrm{\beta }$_MO effects of mediator on outcome, $\mathrm{\beta }$_EO effects of exposure on outcome. BMI body mass index, WMH white matter hyperintensity, AF atrial fibrillation.

Fig. 7. Potential on-target effects of stroke-associated proteins.

Forest plots illustrating the potential on-target effects associated with causal proteins revealed by Phe-MR analysis for TFPI (a) and TMPRSS5 (b). In general, results can be perceived as the effects of per-SD higher circulating protein level on each phenotype. If the effect direction of the target protein on the phenotype is consistent with that on stroke outcomes, it represents 'beneficial' additional indications through the intervention of circulating protein level. Conversely, opposing effect directions of the target protein on the phenotype and stroke represents 'deleterious' side-effects. For example, a higher level of TFPI is associated with a lower risk of ischaemic stroke and so phenotypes with OR <1 represents 'beneficial effects', OR >1 represents 'deleterious effects' when the hypothetical intervention increases TFPI levels. Only significant associations that passed Bonferroni correction (P ≤ 0.05/6/784 = 1.06 × 10⁻⁵) were plotted. See Supplementary Data 14 for more clinical information on the ICD code phenotypes. The dots are the causal estimates on the OR scale, and the whiskers represent the 95% confidence intervals for these ORs.