A genome-wide association study identifies novel genetic variants associated with neck or shoulder pain in the UK biobank (N = 430,193)

Abstract

Introduction: Neck and shoulder pain are prevalent musculoskeletal disorders that significantly affect the quality of life for a substantial portion of the global population. Studies have shown that women are more susceptible than men.

Objective: This study aims to discover genetic variants associated with neck or shoulder pain through a genome-wide association study (GWAS), using data from 430,193 participants in the UK Biobank.

Methods: A genome-wide association study was performed adjusting for age, sex, BMI, and 8 population principal components. Significant and independent genetic variants were replicated by FinnGen.

Results: The primary GWAS revealed 5 significant genetic loci (including 2 novel) associated with neck or shoulder pain, with the most significant single nucleotide polymorphism (SNP) being rs9889282 (P = 2.63 × 10^-12) near CA10 on chromosome 17. Two novel significant associations were detected on chromosomes 18 and 14, with the top SNPs being rs4608411 (P = 8.20 × 10^-9) near TCF4 and rs370565192 (P = 3.80 × 10^-8) in DCAF5, respectively. Our secondary GWAS identified a single novel genetic locus in SLC24A3 among males and 2 genetic loci (including one novel near LINC02770) among females. In the replication stage, the SLC39A8 locus was weakly supported by the FinnGen cohort. The tissue expression analysis revealed a significant association between brain tissues and neck or shoulder pain.

Conclusion: In summary, this study has identified novel genetic variants for neck or shoulder pain. Sex-stratified GWAS also suggested that sex played a role in the occurrence of the phenotype.

Keywords: Genetic correlations; Genome-wide association study; Genomics; Neck or shoulder pain; Phenome-wide association analysis; UK Biobank.

Figure 1.

Manhattan plots of GWAS results for neck or shoulder pain in primary, female, and male analyses. Manhattan plots of the GWAS results for neck or shoulder pain across different analyses. Panel A shows the primary GWAS analysis for the overall samples (N = 430,193), panel B presents the female-specific analysis (N = 233,497), and panel C displays the male-specific analysis (N = 196,696). The x-axis represents chromosome positions across the 22 autosomes, and the y-axis shows the –log10 P values of SNP associations. The dotted line indicates the genome-wide significance threshold of 5 × 10⁻⁸.

Figure 2.

The regional plot of locus in the CA10 region from the primary GWAS. Regional plot of the susceptibility locus in the CA10 region based on the primary GWAS association analysis. The plot shows local SNP associations, with the lead SNP highlighted in purple. The x-axis represents the genomic position in megabases (Mb), while the y-axis displays the association strength of each SNP as –log10 P value.

Figure 3.

The regional plots of loci in the TCF4 and DCAF5 regions from the primary GWAS. Panel A shows the regional plot for the TCF4 locus, and panel B displays the regional plot for the DCAF5 locus. Each plot illustrates SNP associations in the respective regions from the primary GWAS analysis, with the lead SNP marked in purple. The x-axis represents the genomic position in Mb, while the y-axis displays the association strength of each SNP as –log10 P value.

Figure 4.

Tissue expression results from GTEx using FUMA. Panel A shows tissue expression results for 30 specific tissue types from GTEx, analyzed with FUMA. Panel B displays results for 53 tissue types. In both panels, the dashed line indicates the significance threshold, adjusted for multiple comparisons using Bonferroni correction. Significant tissue associations are highlighted in red.

Figure 5.

Genetic correlation results using LDSC on Complex-Traits Genetics Virtual Lab. This scatter plot illustrates the genetic correlations ($r_g$) between neck or shoulder pain and selected traits with $r_g$ values greater than 0.7, calculated using LDSC in the Complex-Traits Genetics Virtual Lab. The x-axis represents the genetic correlation coefficient ($r_g$), while the y-axis displays the phenotypes. Each dot indicates a trait, with its color gradient ranging from blue to red, where increasing redness reflects greater –log10 P values, indicating stronger statistical significance. For a full list of traits and their respective correlation values, see supplemental digital content (see Table 4, http://links.lww.com/PR9/A300).