ATXN2 trinucleotide repeat length correlates with risk of ALS

Abstract

We investigated a CAG trinucleotide repeat expansion in the ATXN2 gene in amyotrophic lateral sclerosis (ALS). Two new case-control studies, a British dataset of 1474 ALS cases and 567 controls, and a Dutch dataset of 1328 ALS cases and 691 controls were analyzed. In addition, to increase power, we systematically searched PubMed for case-control studies published after 1 August 2010 that investigated the association between ATXN2 intermediate repeats and ALS. We conducted a meta-analysis of the new and existing studies for the relative risks of ATXN2 intermediate repeat alleles of between 24 and 34 CAG trinucleotide repeats and ALS. There was an overall increased risk of ALS for those carrying intermediate sized trinucleotide repeat alleles (odds ratio 3.06 [95% confidence interval 2.37-3.94]; p = 6 × 10^-18), with an exponential relationship between repeat length and ALS risk for alleles of 29-32 repeats (R² = 0.91, p = 0.0002). No relationship was seen for repeat length and age of onset or survival. In contrast to trinucleotide repeat diseases, intermediate ATXN2 trinucleotide repeat expansion in ALS does not predict age of onset but does predict disease risk.

Keywords: ALS; ATXN2; Age of onset; Amyotrophic lateral sclerosis; CAG; Expansion; Exponential risk; Intermediate expansion; Risk; SCA2; Trinucleotide repeat; Triplet.

Fig. 1

Distribution of ATXN2 alleles with trinucleotide repeat size 24 or more in the (A) British and (B) Dutch datasets. (A) The British dataset included 1474 ALS individuals and 574 controls. There were 2867 alleles of size 23 or less in cases and 1105 in controls. (B) The Dutch dataset included 1328 ALS individuals and 691 controls. There were 2596 alleles of size 23 or less in cases and 1344 in controls.

Fig. 2

Flow chart of study selection according to the PRISMA protocol. Thirteen previously published studies were selected for analysis, 7 from Europe (Conforti et al., 2012, Corrado et al., 2011, Daoud et al., 2011, Gispert et al., 2012, Lattante et al., 2014, Van Damme et al., 2011, Van Langenhove et al., 2012), 3 studies of Han Chinese (2 from China [Liu et al., 2013, Lu et al., 2015] and 1 from Taiwan [Soong et al., 2014]), 1 from Turkey (Lahut et al., 2012), and 2 studies from the USA (Elden et al., 2010, Ross et al., 2011).

Fig. 3

Forest plots of individual alleles between 29 and 33 repeats. Primary analysis of the relative risk of ALS was conducted using low risk-bias case-control studies. UK = new UK data, NL = new Dutch data. Relative risk (RR) was estimated using a fixed effects approach and by comparing individual counts of ATXN2 alleles with the pooled count of alleles with ≤23 repeats as baseline. (A) ATXN2 allele of 29 repeats, RR = 1.68 (1.11, 2.54). No heterogeneity was observed (p-value of heterogeneity >0.05). (B) ATXN2 allele of 30 repeats, RR = 2.02 (1.30, 3.15). One of 15 studies was excluded for absence of carriers of allele 30, both in cases and controls. Significant heterogeneity was observed (p-value of heterogeneity <0.05). (C) ATXN2 allele of 31 repeats, RR = 2.96 (1.73, 5.05). One of 15 studies was excluded for absence of carriers of allele 31, both in cases and controls. No heterogeneity was observed (p-value of heterogeneity >0.05). (D) ATXN2 allele of 32 repeats, RR = 8.37 (4.02, 17.43). Two of 15 studies were excluded for absence of carriers of allele 32, both in cases and controls. No heterogeneity was observed (p-value of heterogeneity >0.05). (E) ATXN2 allele of 33 repeats, RR = 4.73 (1.92, 11.63). No heterogeneity was observed (p-value of heterogeneity >0.05). Abbreviation: ALS, amyotrophic lateral sclerosis.

Fig. 3

Forest plots of individual alleles between 29 and 33 repeats. Primary analysis of the relative risk of ALS was conducted using low risk-bias case-control studies. UK = new UK data, NL = new Dutch data. Relative risk (RR) was estimated using a fixed effects approach and by comparing individual counts of ATXN2 alleles with the pooled count of alleles with ≤23 repeats as baseline. (A) ATXN2 allele of 29 repeats, RR = 1.68 (1.11, 2.54). No heterogeneity was observed (p-value of heterogeneity >0.05). (B) ATXN2 allele of 30 repeats, RR = 2.02 (1.30, 3.15). One of 15 studies was excluded for absence of carriers of allele 30, both in cases and controls. Significant heterogeneity was observed (p-value of heterogeneity <0.05). (C) ATXN2 allele of 31 repeats, RR = 2.96 (1.73, 5.05). One of 15 studies was excluded for absence of carriers of allele 31, both in cases and controls. No heterogeneity was observed (p-value of heterogeneity >0.05). (D) ATXN2 allele of 32 repeats, RR = 8.37 (4.02, 17.43). Two of 15 studies were excluded for absence of carriers of allele 32, both in cases and controls. No heterogeneity was observed (p-value of heterogeneity >0.05). (E) ATXN2 allele of 33 repeats, RR = 4.73 (1.92, 11.63). No heterogeneity was observed (p-value of heterogeneity >0.05). Abbreviation: ALS, amyotrophic lateral sclerosis.

Fig. 4

Forest plot of the relative risk of ALS for ATXN2 alleles with 29–33 trinucleotide repeats. UK = new UK data, NL = new Dutch data. Fifteen studies at low risk of bias were included. Fixed effects methods were used to estimate the relative risk. No heterogeneity was observed (p-value of heterogeneity >0.05). Abbreviation: ALS, amyotrophic lateral sclerosis.

Fig. 5

Plot of the relative risk for each ATXN2 allele (25–32 repeats). The distribution of the relative risk estimates of alleles of between 25 and 32 CAG trinucleotide repeats obtained from the 15 low bias studies fitted an exponential curve well, showing an exponential growth in relative risk, surpassing the threshold for significant association for alleles of size 29–32 (R² = 0.91 [95% CI 0.82, 0.99], p = 0.0002). The relative risk estimate of the 24 repeat allele was excluded because of a large unidentified heterogeneity across studies. Including this allele, however, did not significantly change the curve fit. Black bars indicate the 95% CI of the relative risk estimates. The red line indicates no effect. Abbreviation: CI, confidence interval.