PLoS ONE plos plosone PLOS ONE 1932-6203 Public Library of Science San Francisco, CA USA 10.1371/journal.pone.0223246 PONE-D-19-03740 Research Article Research and analysis methodsMathematical and statistical techniquesStatistical methodsMetaanalysisPhysical sciencesMathematicsStatisticsStatistical methodsMetaanalysisBiology and life sciencesComputational biologyGenome analysisGenome-wide association studiesBiology and life sciencesGeneticsGenomicsGenome analysisGenome-wide association studiesBiology and life sciencesGeneticsHuman geneticsGenome-wide association studiesMedicine and health sciencesRheumatologyArthritisRheumatoid arthritisMedicine and health sciencesClinical medicineClinical immunologyAutoimmune diseasesRheumatoid arthritisBiology and life sciencesImmunologyClinical immunologyAutoimmune diseasesRheumatoid arthritisMedicine and health sciencesImmunologyClinical immunologyAutoimmune diseasesRheumatoid arthritisPeople and placesGeographical locationsEuropePhysical sciencesMaterials scienceMetallurgyAlloysBrassBiology and life sciencesGeneticsMolecular geneticsBiology and life sciencesMolecular biologyMolecular geneticsMedicine and health sciencesHealth careHealth services researchBiology and life sciencesGeneticsGenetics of disease Genetic associations with radiological damage in rheumatoid arthritis: Meta-analysis of seven genome-wide association studies of 2,775 cases Genetics of radiological damage in rheumatoid arthritis Traylor Matthew Formal analysis Investigation Methodology Writing – original draft Writing – review & editing 1 2 Knevel Rachel Formal analysis Investigation Methodology Writing – review & editing 3 4 5 Cui Jing Formal analysis Investigation Methodology Writing – review & editing 6 Taylor John Formal analysis Investigation Methodology Writing – review & editing 7 Harm-Jan Westra Formal analysis 3 4 Conaghan Philip G. Data curation Writing – review & editing 8 9 Cope Andrew P. Conceptualization Data curation Funding acquisition Writing – review & editing 10 Curtis Charles Data curation Writing – review & editing 11 12 Emery Paul Data curation Writing – review & editing 8 9 Newhouse Stephen Data curation Writing – review & editing 11 13 14 http://orcid.org/0000-0001-7951-6728 Patel Hamel Data curation Writing – review & editing 11 Steer Sophia Conceptualization Data curation Writing – review & editing 15 Gregersen Peter Data curation Writing – review & editing 16 Shadick Nancy A. Data curation Writing – review & editing 6 Weinblatt Michael E. Data curation Writing – review & editing 6 Van Der Helm-van Mil Annette Data curation Writing – review & editing 5 http://orcid.org/0000-0002-1720-7724 Barrett Jennifer H. Conceptualization Investigation Methodology Writing – original draft Writing – review & editing 9 17 Morgan Ann W. Conceptualization Data curation Investigation Methodology Writing – original draft Writing – review & editing 8 9 Lewis Cathryn M. Conceptualization Funding acquisition Investigation Methodology Writing – original draft Writing – review & editing 2 12 http://orcid.org/0000-0002-1268-9808 Scott Ian C. Conceptualization Formal analysis Funding acquisition Investigation Methodology Writing – original draft Writing – review & editing 18 19 * Department of Clinical Neurosciences, Stroke Research Group, University of Cambridge, Cambridge, United Kingdom Department of Medical and Molecular Genetics, King’s College London, London, United Kingdom Brigham and Women’s Hospital, Division of Genetics, Raychaudhuri Lab, Boston, MA, United States of America Broad institute, Cambridge, MA, United States of America Department of Rheumatology C1-R, Leiden University Medical Center, Albinusdreef, Leiden, the Netherlands Division of Rheumatology Immunology and Allergy Brigham & Women's Hospital Harvard Medical School Boston, MA, United States of America Leeds Institute of Cancer & Pathology, Worsley Building Level 11 (LIDA), Clarendon Way, Leeds, United Kingdom Leeds Institute of Rheumatic and Musculoskeletal Medicine, University of Leeds, Leeds, United Kingdom NIHR Leeds Biomedical Research Centre, Leeds Teaching Hospitals NHS Trust, Leeds, United Kingdom Academic Department of Rheumatology, Centre for Molecular and Cellular Biology of Inflammation, King's College London, London, United Kingdom NIHR Biomedical Research Centre at South London and Maudsley NHS Foundation Trust and King’s College London, London, United Kingdom SGDP Centre, Institute of Psychiatry, Psychology & Neuroscience, King’s College London, London, United Kingdom Department of Biostatistics and Health Informatics, Institute of Psychiatry, Psychology and Neuroscience, King’s College London, London, United Kingdom Farr Institute of Health Informatics Research, UCL Institute of Health Informatics, University College London, London, United Kingdom Department of Rheumatology, King’s College Hospital, Denmark Hill, London, United Kingdom The Feinstein Institute for Medical Research, Northwell Health, Manhasset, New York, United States of America School of Medicine, University of Leeds, Leeds, United Kingdom Primary Care Centre Versus Arthritis, Research Institute for Primary Care and Health Sciences, Primary Care Sciences, Keele University, Keele, United Kingdom Haywood Academic Rheumatology Centre, Haywood Hospital, Midlands Partnership NHS Foundation Trust, High Lane, Burslem, Staffordshire, United Kingdom Kuwana Masataka Editor Keio University, JAPAN

NAS has received less than $10,000 consultancies from Bristol myers squibb, and research grants from Mallinchrodt Pharmaceuticals and BWH (which is sponsored by Amgen, BMS, Sanofi/Regeneron, Dxterit, Crescendo and UCB). MEW has received less than $10,000 consultancies from Abbvie, Amgen, Novartis, Roche, Glaxo Smith Kline, Merck, Samsung, Crescendo Bioscience, Gilead, Pfizer and UCB, and over $10,000 from Lilly, and BMS. The BRASS study receives funding from Bristol myers squibb, Sanofi/Regeneron, AMGEN, and Crescendo Biosciences. This does not alter our adherence to PLOS ONE policies on sharing data and materials.

 * E-mail: i.scott@keele.ac.uk 9 10 2019 2019 14 10 e0223246 10 2 2019 17 9 2019 2019 Traylor et al This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Background

Previous studies of radiological damage in rheumatoid arthritis (RA) have used candidate-gene approaches, or evaluated single genome-wide association studies (GWAS). We undertook the first meta-analysis of GWAS of RA radiological damage to: (1) identify novel genetic loci for this trait; and (2) test previously validated variants.

 Methods

Seven GWAS (2,775 RA cases, of a range of ancestries) were combined in a meta-analysis. Radiological damage was assessed using modified Larsen scores, Sharp van Der Heijde scores, and erosive status. Single nucleotide polymophsim (SNP) associations with radiological damage were tested at a single time-point using regression models. Primary analyses included age and disease duration as covariates. Secondary analyses also included rheumatoid factor (RF). Meta-analyses were undertaken in trans-ethnic and European-only cases.

 Results

In the trans-ethnic primary meta-analysis, one SNP (rs112112734) in close proximity to HLA-DRB1, and strong linkage disequilibrium with the shared-epitope, attained genome-wide significance (P = 4.2x10-8). In the secondary analysis (adjusting for RF) the association was less significant (P = 1.7x10-6). In both trans-ethnic primary and secondary meta-analyses 14 regions contained SNPs with associations reaching P<5x10-6; in the European primary and secondary analyses 13 and 10 regions contained SNPs reaching P<5x10-6, respectively. Of the previously validated SNPs for radiological progression, only rs660895 (tagging HLA-DRB1*04:01) attained significance (P = 1.6x10-5) and had a consistent direction of effect across GWAS.

 Conclusions

Our meta-analysis confirms the known association between the HLA-DRB1 shared epitope and RA radiological damage. The lack of replication of previously validated non-HLA markers highlights a requirement for further research to deliver clinically-useful prognostic genetic markers.

 This work was supported by Versus Arthritis (Grant Reference Numbers: 19739 to ICS; 18475 and 18387 to PE, AWM and PC; 20011to APC), the National Institute for Health Research (NIHR; Clinical Lectureship to ICS), Academy of Medical Sciences (Starter Grant for Clinical Lecturers to ICS), British Medical Association (Doris Hillier Award to AWM) and the Ann Wilks Memorial Fund. SJN is supported by the NIHR University College London Hospitals Biomedical Research Centre, and by awards establishing the Farr Institute of Health Informatics Research at UCL Partners, from the Medical Research Council (MRC), Versus Arthritis, British Heart Foundation, Cancer Research UK, Chief Scientist Office, Economic and Social Research Council, Engineering and Physical Sciences Research Council, NIHR, National Institute for Social Care and Health Research, and Wellcome Trust (grant MR/K006584/1). We thank the MRC and Versus Arthritis for their joint funding of MATURA (grant codes 36661 and MR/K015346/1, respectively). Genotyping of the YEAR cohort was performed in collaboration with the PAMERA Consortium that was supported by the US NIH Pharmacogenomics Research Network (PGRN) and funded by NIGMS (U19 GM61388) and the RIKEN Center for Integrative Medical Sciences. It was funded in part by the Biobank Japan Project, funded by the Ministry of Education, Culture, Sports, Science and Technology of Japan. This paper represents independent research part-funded by the NIHR Biomedical Research Centres at Guy’s and St. Thomas’ NHS Foundation Trust and King’s College London, and at South London and Maudsley NHS Foundation Trust and King’s College London. High performance computing facilities were funded with capital equipment grants from the GSTT Charity (TR130505) and Maudsley Charity (980). This work was also supported by the NIHR infrastructure at Leeds. The views expressed are those of the authors and not necessarily those of the NHS, the NIHR or the Department of Health and Social Care. The funders had no role in the study design, data collection and analysis, data interpretation, the writing of the manuscript or the decision to submit the manuscript for publication. Data Availability Individual-level genotype and phenotype data from each of the separate GWAS are not publicly available, as the centres from which patients were recruited are reported in the primary publications outlining the individual genetic datasets, leading to the potential for patient confidentiality to be affected. Summary statistics will be made available through the NHGRI-EBI GWAS Catalog (https://www.ebi.ac.uk/gwas/downloads/summary-statistics). Further data requests can be made to the following non-author contacts: Ms Isabel Sinha (isabel.sinha@kcl.ac.uk) for CARDERA, GENRA, and SLRAS; Dr James Robinson (J.I.Robinson@leeds.ac.uk) for YEAR; Vivi Feathers (vfeathers@bwh.harvard.edu) for BRASS; Dr Annette Lee (Anlee@northwell.edu) for NARAC; and Dr E Niemantsverdriet (E.Niemantsverdriet@lumc.nl) for the Leiden EAC. Background

Rheumatoid arthritis (RA) is a heterogeneous disease, exhibiting a variable course between patients. Prospectively identifying patients likely to develop severe phenotypes could allow early intensive therapy to be focussed on poor prognosis cases. This approach should optimise clinical and cost-effectiveness, but requires accurate prognostic markers.

Radiological damage is one measure of RA severity. It is moderately heritable (heritability from common variants estimated at 45%-58%) suggesting genetic markers could represent useful prognostic biomarkers [1]. The strongest genetic association with RA radiological progression is the shared epitope (SE), which represents consensus amino acid sequences (QRRAA, RRRAA and QKRAA) spanning positions 70–74 in the HLA-DRβ1 molecule, encoded by various HLA-DRB1 SE alleles [2]. The SE has been demonstrated to associate with greater radiological damage in a broad range of RA populations [3,4], although as it associates with the presence of rheumatoid factor (RF) and antibodies to citrullinated peptide antigens (ACPA) [5], both of which independently associate with radiological damage [6], its impact may be mediated by autoantibody status. Van Steenbergen et al previously identified a further 16 “validated” non-HLA variants (in 11 genes) for RA radiological progression [7]. In the Leiden Early Arthritis Cohort (EAC) these variants, in combination with the SE, explained up to 18% of the variance in radiological progression, although as this cohort was used to identify many of the variants, this finding requires replication.

The gold standard to identify genetic associations with a phenotype or trait is to perform a meta-analysis of all available genome-wide association studies (GWAS). To date, this has not been performed for RA radiological damage. Five individual GWAS have identified four non-HLA variants − rs7607479 in SPAG16, rs451066 in RAD51L1-ZFP36L1, rs11908352 in SLC12A5, and rs2833522 in HUNK/SCAF4 –associating with RA radiological damage that passed multiple testing correction thresholds, and replicated externally [8–11]. These studies were limited by modest sample sizes, with the largest containing 646 patients. Combining GWAS in a meta-analysis should increase statistical power to detect novel loci.

To this end, we have carried out the largest GWAS of RA radiological damage, by peforming and then combining seven independent GWAS (totalling 2,775 patients). We aimed to identify novel genetic loci for radiological damage. We also tested previously validated single nucleotide polymorphisms (SNPs) for their association with radiological damage.

 Methods Patients

GWAS were undertaken in: (1) Combination Anti-Rheumatic Drugs in Early RA (CARDERA) Genetics Cohort; (2) Yorkshire Early Arthritis Registry (YEAR); (3) Brigham and Women’s Hospital RA Sequential Study (BRASS); (4) Leiden Early Arthritis Clinic (EAC); (5) North American RA Consortium (NARAC); (6) GENetics of RA in individuals of African ancestry (GENRA) study; (7) South London RA Study (SLRAS). These cohorts have been described in detail previously [12–17]. An overview is provided in Table 1 (with further details in S1 Table).

 Radiological measures

Hand and feet X-rays were scored using either the Scott modification of the Larsen method (scoring 0–200 for joint space narrowing and erosive damage [18]), Sharp van Der Heidje Scores (SvHS; scoring 0–448 for joint space narrowing and erosive damage [19]) or erosions (present/absent). Larsen and SvHS are highly correlated; both evaluate erosions [20].

 Genotyping, quality control and imputation

CARDERA was genotyped on the Immunochip, YEAR on the ImmunoChip and HumanOmniExpressExome Beadchip, BRASS on the Affymetrix 6.0, Leiden EAC on the Illumina iScan, GENRA on the Illumina MEGA array, NARAC on the Illumina Beadchip (HumanHap 550k), and SLRAS on the Illumina HumanOmniExpress. Prior to imputation all cohorts excluded SNPs with high levels of missingness, low minor allele frequency (MAF), and deviations from Hardy-weinberg equilibrium (HWE). Individuals were removed that did not segregate with reference populations, had high-levels of missingness, or whose phenotypic sex mismatched with sex inferred from genotype data. Genotype phasing and imputation were performed using SHAPEIT and IMPUTE2, respectively. Data were imputed to the 1,000 Genomes Phase 3 Panel, including all samples regardless of ancestry. Post-imputation markers with INFO scores <0.7 or MAF <0.05 were removed (the latter was undertaken as we had limited power to detect associations with low frequency variants). Genotypes were analysed as expected allele “dosages” in all analyses. Genotypes were converted to be reported on the forward strand. The number of variants available post-QC comprised: CARDERA: 3,181,676; YEAR: 6,209,766; Leiden EAC: 674,614; BRASS: 6,059,126; GENRA: 5,662,513; NARAC: 5,373,610; SLRAS: 5,715,821.”

 Statistical analysis X-ray time-point

As RA X-ray progression can be non-linear [21], and several cohorts had cross-sectional X-ray scores, we tested SNP associations with radiological damage at a single time-point. In the repeated measures early RA cohorts (CARDERA, YEAR, and Leiden EAC) associations with end-point X-ray scores were tested (when radiological damage was greatest). In the repeated measures established RA cohort (BRASS) associations with baseline X-ray scores were tested (when sample size was greatest).

 Statistical models

Log-transformed Larsen/SvHS, or binary erosive status were used as response variables. Outcomes were regressed on imputed genotype dosages assuming an additive genetic model using linear (in CARDERA, Leiden EAC, BRASS, SLRAS, and NARAC), negative binomial (in YEAR, due to over-dispersion) or logistic (in GENRA) regression models.

The same modelling covariates were included to provide consistency. Sex, age, disease duration, rheumatoid factor (RF) and (where available) treatment were tested for associations with X-ray scores in each cohort to determine the best predictors across studies. Only age and disease duration were associated with radiological scores in every cohort, and these were included as covariates. Ancestry-informative principal components (PCs) were included to account for population stratification. These were calculated using EIGENSTRAT. Different numbers were used in each study, with a minimum of 2 used [22].

Two analyses were undertaken: a primary analysis using these covariates, and a secondary analysis, including RF as an additional covariate to account for genetic variants exerting their effects through RF formation (which associates with both the SE and X-ray damage).

 Meta-analysis

SNP association results from GWAS were combined using a Z-score weighted approach in METAL [23]. METAL performs a meta-analysis using information on P-values, effect directions, and the number of cases evaluated at each SNP. This method was used because other meta-analysis methods, such as the inverse variance-weighted average method [24], require effect size data at each marker, and as our various GWAS utlised different statistical models and X-ray scoring systems, their beta-values were non-comparable.

We assessed QQ-plots and genomic inflation factors to confirm that genome-wide statistics had the expected distributions. Genomic control correction was used to adjust for any residual inflation of test statistics. In the overall meta-analysis of all SNPs, we only analysed SNPs that had been genotyped or imputed in at least half of all individuals in the total sample.

Two meta-analyses were performed: (1) a trans-ethnic meta-analysis (maximising sample size); (2) a European ancestry meta-analysis (reducing heterogeneity across populations).

 Associations with previously validated SNPs

Van Steenbergen et al reported 17 validated variants for radiological progression. These comprised variants in the following 12 loci: SPAG16, IL-15, C5orf30, HLA-DRB1, OPG, DKK-1, IL2RA, RAD51L1/ZFP36L1, GRZB, IL-4R, MMP-9, and CD40. They defined “validated” as being a SNP studied in several cohorts, with the association independently replicated or found significant in a meta-analysis of all published data [7]. We tested their association with radiological damage in our meta-analysis. We included all available SNPs, regardless of if they were present in less than half of all individuals. We used the HLA-DRB1*04:01 tagging SNP (rs660895) identified in the Eyre et al RA susceptibility meta-analysis [25] to represent the SE, as this is the commonest SE-encoding allele in RA cases [2].

 Significance thresholds

For the testing of previously validated SNPs we used a Bonferroni corrected P-value of 0.004167 (12 loci tested). For the genome-wide analyses we used the standard P-value threshold of <5x10-8 for genome-wide significance, and <5x10-6 for “suggestive” significance. In the genome-wide trans-ethnic analysis, based on sampling from a Chi-squared distribution with NCP=Nq21−q2, where q is trait variance and N is sample size, we had 80% power to detect a variant explaining 1.4% of the variance of X-ray damage at P<5x10-8 [26]. We made assumptions to enable us to perform a power calculation for this heterogeneous dataset. As most datasets used the quantitative Larsen scale, we simulated chi-squared statistics with an NCP given by N*qtl_variance/(1-qtl_variance) and calculated power based on the number of observations reaching genome-wide significance, using the principles reported by Yang et al [26]. We assumed we had 80% study power for qtl_variance values which produced genome-wide significant values for 80% of simulations.

 Ethics approval and consent to participate

Ethical approval was granted for each of the genetic studies as follows: CARDERA genetics cohort was approved by the National Research Ethics Service Committee East of England—Essex (reference: 11/EE/0544); YEAR by the Multi-Centre Research Ethics Committee (MREC) (reference 99/3/48); Leiden EAC by the Medical Ethics Committee Leiden University Medical Center; BRASS by the Institutional Review Board of Brigham and Women’s Hospital, Partners Health Care, Boston, MA; GENRA by the National Research Ethics Service Committee London—Dulwich (reference: 11/LO/1244); NARAC by the Via Christi Institutional Review Board and North Shore-LIJ Health System Institutional Review Board; SLRAS by the Guy's Hospital Local Research Committee (reference 99/11/06) and Lewisham Hospital Local Research Committee (reference 01/05/02). Informed consent was provided by all participating patients.

 Availability of data and materials

Individual-level genotype and phenotype data from each of the separate GWAS are not publically available, as the centres from which patients were recruited are reported in the primary publications outlining the individual genetic datasets, leading to the potential for patient confidentiality to be affected. Summary statistics will be made available through the NHGRI-EBI GWAS Catalog (https://www.ebi.ac.uk/gwas/downloads/summary-statistics). Further data requests can be made to the following non-author contacts: Ms Isabel Sinha (isabel.sinha@kcl.ac.uk) for CARDERA, GENRA, and SLRAS; Dr James Robinson (J.I.Robinson@leeds.ac.uk) for YEAR; Vivi Feathers (vfeathers@bwh.harvard.edu) for BRASS; Dr Annette Lee (Anlee@northwell.edu) for NARAC; and Dr E Niemantsverdriet (E.Niemantsverdriet@lumc.nl) for the Leiden EAC.

 Results Cohort characteristics

Cohort characteristics are presented in Table 1. The majority of cases were female (67.2–80.8%), and seropositive (57.4–100% RF-positive; 52.8–100% ACPA-positive). The mean age in all cohorts was between 54.5 and 60.9 years, except NARAC, which had a mean age of 40.8 years. As expected, the cohorts containing established RA patients had higher rates of radiological damage than those evaluating early RA patients. The total number of patients included in the trans-ethnic and European meta-analyses comprised 2,775 and 2,527 cases, respectively. The total number of SNPs assessed in the trans-ethnic meta-analysis was 4,802,696, and in the European meta-analysis was 2,723,488.

10.1371/journal.pone.0223246.t001 Cohort characteristics.
Characteristic CARDERA (n = 505) [12] YEAR(n = 403) [13] BRASS(n = 422) [14] SLRAS(n = 284) [17] GENRA (n = 196) [16] Leiden EAC (n = 595) [13] NARAC (n = 370) [15]
Ancestry European European European Mixed African European European
Recruitment Site England England North America England England Netherlands North America
Female, n (%) 345 (68.7) 278 (69.0) 341 (80.8) 227 (80.0) 164 (83.7) 400 (67.2) 272 (73.5)
Mean Age 54.5 (12.6) 60.3 (13.6) 58.9 (13.7) 60.9 (12.8) 56.2 (14.8) 57.1 (15.6) 40.8 (11.9)
Mean Disease Duration in Yrs (SD) 2.28 (0.41) 2.21 (1.17) 17.0 (12.7) 15.5 (11.6) 9.3 (10.2) 4.9 (2.2) 14.1 (10.6)
RF-Positive, n (%) 340 (67.3) 279 (69.2) 422 (100) 210 (75.5) 153 (78.1) 340 (57.4) Unavailable
ACPA-Positive, n (%) 342 (67.7) 195 (65.9) 422 (100) Unavailable 152 (77.6) 308 (52.8) 370 (100)
X-ray Scoring Larsen SvHS SvHS Larsen Erosions SvHS SvHSa
Follow-Up Duration 2 years 2 years 9 years Cross-sectional Cross-sectional 7 years Cross-sectional
Median X-ray Score (IQR)b 13 (3–25) 0 (0–5) 25 (5–64) 47 (25–77) Unavailable 18 (7–37) 21 (6–56)
Erosive, n (%) Unavailable 100 (24.8) Unavailable Unavailable 78 (39.8) 570 (95.8) 319 (86.0)

a = in NARAC SvHS were available for hand X-rays only

b = X-ray score at 2 years of follow-up in CARDERA/YEAR, 6 years of follow-up in Leiden EAC, baseline in BRASS, and at a single time-point in SLRAS/GENRA/NARAC; disease duration is at the time of the X-ray score tested for its association with genetic variants.

 Trans-ethnic meta-analysis

In the primary analysis (age and disease duration as covariates), one SNP (rs112112734, on chromosome 6, in close proximity to HLA-DRB5, HLA-DRB6 and HLA-DRB1) attained genome-wide significance (P = 4.2x10-8, regional association plot in Fig 1). The same direction of effect was observed in the 6 GWAS in which this marker was available (it was absent in the Leiden EAC). This SNP is in strong linkage disequilibrium (LD) with the HLA-DRB1 SE (R2 = 0.93 with the lead HLA-DRB1 SNP, rs9268839, from the Okada et al RA susceptibility meta-analysis [27]). Fourteen regions contained SNPs with associations reaching P<5x10-6 (S2 Table).

10.1371/journal.pone.0223246.g001 Regional association plot for region surrounding rs112112734 showing evidence of significance at <italic>P</italic><5x10<sup>-8</sup> in the primary trans-ethnic meta-analysis.

In the secondary analysis (age, disease duration and RF as covariates), no SNPs attained genome-wide significance. Fourteen regions contained SNPs with associations reaching P<5x10-6, one of which was rs112112734 (P = 1.7x10-6) (S3 Table). Plots of–log10(P-value) by genomic position for the trans-ethnic and European analyses are provided in Fig 2, and QQ plots in S1 Fig.

10.1371/journal.pone.0223246.g002 Manhattan plots for radiological damage.

Panel A = trans-ethnic primary analysis; Panel B = European primary analysis; Panel C = trans-ethnic secondary analysis; Panel D = European secondary analysis; primary analysis includes age, disease duration and genotypes as explanatory variables; secondary analysis also includes RF as an explanatory variable.

 European meta-analysis

In the primary analysis, thirteen regions contained SNPs reaching P<5x10-6 (S2 Table), with the most significant SNP being rs112112734 (P = 8.6x10-8).

In the secondary analysis, ten regions contained SNPs with associations reaching P<5x10-6 (S3 Table). rs112112734 was not amongst these.

 Previously validated SNPs

Two SNPs associated with radiological damage in our European meta-analysis (Table 2). These comprised: (1) rs660895 (tagging HLA-DRB1*04:01; P = 1.6x10-5) which had the same direction of effect across all 6 GWAS (the G allele, indicating an *04:01 copy, associating with increased damage), and (2) rs7607479 (in SPAG16), which was available in four GWAS, two of which had increased and two reduced radiological damage associated with the T allele. In the trans-ethnic meta-analysis, only rs660895 was significant (P = 7.0x10-5) with the same direction of effect observed in all but one GWAS. Only 2 SNPs in the trans-ethnic meta-analysis, and 4 SNPs in the European meta-analysis had a shared direction of effect across all available GWAS.

10.1371/journal.pone.0223246.t002 Previously validated genetic variants for radiological progression reported by Van Steenbergen et al [<xref ref-type="bibr" rid="pone.0223246.ref007">7</xref>], and their association with radiological damage.
Trans-ethnic European
Variant Gene Chr A1/A2 A1 Freq. Cohort Direction P A1 Freq. Cohort Direction P
rs7607479 SPAG16 2 T/C 0.53 -+?-?++ 4.4x10-3 0.55 -+?-?+ 4.0x10-3
rs4371699 IL-15 4 A/C 0.33 ++?+?++ 0.0869 0.38 ++?+?+ 0.0445
rs6821171 IL-15 4 T/G 0.66 +--+?++ 0.7913 0.65 +--+?+ 0.5901
rs7665842 IL-15 4 T/C 0.65 -++-?-+ 0.6102 0.63 -++-?- 0.4719
rs7667746 IL-15 4 T/C 0.60 -+?-?-+ 0.3014 0.55 -+?-?- 0.1528
rs26232 C5orf30 5 T/C 0.45 --+--++ 0.5763 0.46 --+--+ 0.4193
rs660895 HLA-DRB1*04:01 6 A/G 0.56 --+-- 7.0x10-5 0.54 ------ 1.6x10-5
rs1485305 OPG 8 A/T 0.50 +++-?+- 0.7832 0.53 +++-?+ 0.5594
rs1528873 DKK-1 10 A/C 0.55 ++?-?-- 0.4979 0.53 ++?-?- 0.6317
rs1896367 DKK-1 10 T/C 0.44 ++?+?+? 0.1337 0.44 ++?+?+ 0.1304
rs1896368 DKK-1 10 T/C 0.47 ++?+?+- 0.2077 0.50 ++?+?+ 0.1749
rs2104286 IL2RA 10 T/C 0.56 -+-++-? 0.8596 0.55 -+-++- 0.9270
rs451066 RAD51L1, ZFP36L1 14 A/G 0.41 -+-++-+ 0.6024 0.44 -+-++- 0.6415
rs8192916 GRZB 14 A/G 0.43 +-?+??- 0.7444 0.39 +-?+?? 0.7408
rs1119132 IL-4R 16 A/G 0.38 --+-+++ 0.1923 0.41 --++++ 0.1912
rs11908352 MMP-9 20 A/C 0.41 ++--+-+ 0.2055 0.43 ++--+- 0.2169
rs4810485 CD40 20 T/G 0.41 +--+-+- 0.4666 0.44 +--+-+ 0.4924

Cohort direction indicates the direction of the SNP A1 allele effect on X-ray damage across the cohorts (+ means it is associated with increased damage,—means it is associated with decreased damage, and ? means the SNP was unavailable in the cohort). Cohort order comprises YEAR, BRASS, CARDERA, SLRAS, Leiden, NARAC, GENRA in the trans-ethnic analysis and YEAR, BRASS, CARDERA, SLRAS, Leiden, and NARAC in the European analysis); results in the table are from the primary analysis (including age and gender as covariates). Note that (a) Stouffer’s meta-analysis method does not permit effect sizes to be calculated, and (b) the effect direction for the SLRAS cohort differs at two markers (rs660895 and rs1119132) because it is a mixed-ethnicity cohort and different individuals were included in the trans-ethnic and European analyses in this GWAS.

 Discussion

Our study has three key findings. Firstly, it confirms the known association between this trait and the HLA-region, with one SNP in this region (rs112112734, in high LD with the HLA-DRB1 SE) attaining genome-wide significance. Secondly, it demonstrates the challenges in replicating genetic variants for traits across GWAS. Of the 17 previously validated SNPs, only the HLA-DRB1*04:01 tagging SNP had a significant association and consistent direction of effect across GWAS. Thirdly, it highlights the difficulties in performing meta-analysis of GWAS of continuous disease outcomes like RA radiological damage, which involves combining summary statistics from highly heterogeneous patient cohorts.

The association between the SE and radiological damage in RA is well established [3]. As the SE associates with RF and ACPA, which themselves are linked with radiological damage, we undertook a secondary analysis including RF as a covariate (ACPA was not used, as ACPA status was unavailable in SLRAS, and two cohorts only included ACPA-positive cases). The association observed at chromosome 6 was less significant in this secondary analysis, and rs112112734 no longer reached genome-wide significance. This suggests the observed association between the HLA-region and X-ray damage in our meta-analysis may be, at least in part, mediated by autoantibody production. More recently, Viatte et al reported that amino acid polymorphisms at position 11 in HLA-DRβ1 also associate with erosions, independently of the shared epitope [28]; owing to an absence of imputed amino acid polymorphism data, and the fact that this amino acid polymorphism is not “tagged” by a single SNP, we were unable to evaluate this association within our meta-analysis. Future research should focus on fine mapping of the HLA locus to provide a more comprehensive understanding of the association between HLA alleles and X-ray damage.

Our failure to replicate associations for previously validated non-HLA markers is disappointing. There are several potential explanations for this. Firstly, the validated variants reported by Van Steenbergen et al were for radiological progression, and we tested their association with radiological damage (although only radiological “progressors” will accrue damage). Secondly, several of these variants were identified in ACPA-positive cases only, and our cohorts included cases with a range of frequencies of ACPA. Thirdly, not all SNPs were available in all cohorts, although only one SNP (rs8192916 in GRZB) had a sample size of <1,000 cases. Irrespective of the explanation, current data on seven GWAS strengthen the notion that these variants lack clinical utility at identifying severe phenotypes [7].

The strengths of our study are that it represents the largest analysis of genetic predictors of RA radiological damage, includes individuals from a range of ethnicities (increasing the generalisability of its results), and is the first meta-analysis of an RA prognostic trait. Its weaknesses are the marked heterogeneity of the included GWAS (which varied in their disease durations, X-ray scoring systems used, and statistical models), and its modest sample size, limiting our ability to detect variants of a small effect size. As our meta-analysis replicated the genetic locus with the largest effect size for radiological damage (the HLA region), we consider that our modest sample size is the most likely reason we did not identify non-HLA associations attaining genome-wide significance. An alternative explanation is that the trait of radiological damage has low heritability. Due to a modest sample size, and clinical heterogeneity, we could not determine heritability in our GWAS meta-analysis with confidence, although previous research has reported RA radiological damage to be moderately heritable (estimated heritability rate of 45–58%) [1].

 Conclusions

In conclusion, our meta-analysis replicates the association between the HLA-region and radiological damage in RA. It demonstrates the complexities of undertaking meta-analysis of GWAS of RA characteristics. For these to be more precisely defined, a collaborative international approach is required, standardising the collection of phenotypic data in genotyped patients, creating large homogeneous cohorts that are suitable for meta-analysis.

 Supporting information Genome-Wide association study details.

(PDF)

 Lead SNPs from regions showing evidence of significance at <italic>P</italic><5x10<sup>-6</sup> in the primary trans-ethnic and European meta-analysis.

(PDF)

 Lead SNPs from regions showing evidence of significance at <italic>P</italic><5x10<sup>-6</sup> in the secondary trans-ethnic and European meta-analysis.

(PDF)

 QQ plots for meta-analyses.

A = primary trans-ethnic meta-analysis (inflation factor 1.00); B = primary European meta-analysis (inflation factor 1.01); C = secondary trans-ethnic meta-analysis (inflation factor 1.00); D = secondary European meta-analysis (inflation factor 1.00).

(TIF)

 References Knevel R, Grondal G, Huizinga TWJ, Visser AW, Jonsson H, Vikingsson A, et al. Genetic predisposition of the severity of joint destruction in rheumatoid arthritis: a population-based study. Ann Rheum Dis. 2012;71: 707–709. doi: 10.1136/annrheumdis-2011-200627 22219137 Raychaudhuri S, Sandor C, Stahl EA, Freudenberg J, Lee H-S, Jia X, et al. Five amino acids in three HLA proteins explain most of the association between MHC and seropositive rheumatoid arthritis. Nat Genet. 2012;44: 291–296. doi: 10.1038/ng.1076 22286218 Gorman J, MD MPH, Lum R, Chen J, Suarez-Almazor M, MD P, et al. Impact of Shared Epitope Genotype and Ethnicity on Erosive Disease: A Meta-Analysis of 3,240 Rheumatoid Arthritis Patients. Arthritis Rheum. 2004;50: 400–412. doi: 10.1002/art.20006 14872482 Gonzalez-Gay MA, Garcia-Porrua C, Hajeer AH. Influence of human leukocyte antigen-DRB1 on the susceptibility and severity of rheumatoid arthritis. Semin Arthritis Rheum. 2002;31: 355–360. 12077707 Balsa A, Cabezon A, Orozco G, Cobo T, Miranda-Carus E, Lopez-Nevot MA, et al. Influence of HLA DRB1 alleles in the susceptibility of rheumatoid arthritis and the regulation of antibodies against citrullinated proteins and rheumatoid factor. Arthritis Res Ther. 2010;12: R62. doi: 10.1186/ar2975 20370905 Mewar D, Coote A, Moore DJ, Marinou I, Keyworth J, Dickson MC, et al. Independent associations of anti-cyclic citrullinated peptide antibodies and rheumatoid factor with radiographic severity of rheumatoid arthritis. Arthritis Res Ther. 2006;8: R128. doi: 10.1186/ar2017 16859535 van Steenbergen HW, Tsonaka R, Huizinga TW, le Cessie S, van der Helm-van Mil AH. Predicting the severity of joint damage in rheumatoid arthritis; the contribution of genetic factors. Ann Rheum Dis. 2015;74: 876–882. doi: 10.1136/annrheumdis-2013-204277 24431388 Arya R, Del Rincon I, Farook VS, Restrepo JF, Winnier DA, Fourcaudot MJ, et al. Genetic Variants Influencing Joint Damage in Mexican Americans and European Americans With Rheumatoid Arthritis. Genet Epidemiol. 2015;39: 678–688. doi: 10.1002/gepi.21938 26498133 de Rooy DPC, Zhernakova A, Tsonaka R, Willemze A, Kurreeman BAS, Trynka G, et al. A genetic variant in the region of MMP-9 is associated with serum levels and progression of joint damage in rheumatoid arthritis. Ann Rheum Dis. 2014;73: 1163–1169. doi: 10.1136/annrheumdis-2013-203375 23696630 Knevel R, Klein K, Somers K, Ospelt C, Houwing-Duistermaat JJ, van Nies JAB, et al. Identification of a genetic variant for joint damage progression in autoantibody-positive rheumatoid arthritis. Ann Rheum Dis. 2014;73: 2038–2046. doi: 10.1136/annrheumdis-2013-204050 23956247 de Rooy DPC, Tsonaka R, Andersson MLE, Forslind K, Zhernakova A, Frank-Bertoncelj M, et al. Genetic Factors for the Severity of ACPA-negative Rheumatoid Arthritis in 2 Cohorts of Early Disease: A Genome-wide Study. J Rheumatol. 2015;42: 1383–1391. doi: 10.3899/jrheum.140741 26077402 Scott IC, Rijsdijk F, Walker J, Quist J, Spain SL, Tan R, et al. Do Genetic Susceptibility Variants Associate with Disease Severity in Early Active Rheumatoid Arthritis?. J Rheumatol. 2015;42: 1131–1140. doi: 10.3899/jrheum.141211 25979711 Teare MD, Knevel R, Morgan MD, Kleszcz A, Emery P, Moore DJ, et al. Allele-dose association of the C5orf30 rs26232 variant with joint damage in rheumatoid arthritis. Arthritis Rheum. 2013;65: 2555–2561. doi: 10.1002/art.38064 23817893 Iannaccone CK, Lee YC, Cui J, Frits ML, Glass RJ, Plenge RM, et al. Using genetic and clinical data to understand response to disease-modifying anti-rheumatic drug therapy: data from the Brigham and Women’s Hospital Rheumatoid Arthritis Sequential Study. Rheumatology (Oxford). 2011;50: 40–46. doi: 10.1093/rheumatology/keq263 20847201 van der Linden MPM, Feitsma AL, le Cessie S, Kern M, Olsson LM, Raychaudhuri S, et al. Association of a single-nucleotide polymorphism in CD40 with the rate of joint destruction in rheumatoid arthritis. Arthritis Rheum. 2009;60: 2242–2247. doi: 10.1002/art.24721 19644859 Traylor M, Curtis C, Patel H, Breen G, Hyuck Lee S, Xu X, et al. Genetic and environmental risk factors for rheumatoid arthritis in a UK African ancestry population: the GENRA case-control study. Rheumatology (Oxford). 2017;56: 1282–1292. doi: 10.1093/rheumatology/kex048 28407095 Steer S, Lad B, Grumley JA, Kingsley GH, Fisher SA. Association of R602W in a protein tyrosine phosphatase gene with a high risk of rheumatoid arthritis in a British population: evidence for an early onset/disease severity effect. Arthritis Rheum. 2005;52: 358–360. doi: 10.1002/art.20737 15641088 Scott DL, Houssien DA, Laasonen L. Proposed modification to Larsen’s scoring methods for hand and wrist radiographs. Br J Rheumatol. 1995;34: 56. doi: 10.1093/rheumatology/34.1.56 7881840 van der Heijde D, Dankert T, Nieman F, Rau R, Boers M. Reliability and sensitivity to change of a simplification of the Sharp/van der Heijde radiological assessment in rheumatoid arthritis. Rheumatology (Oxford). 1999;38: 941–947. doi: 10.1093/rheumatology/38.10.941 10534543 Pincus T, Larsen A, Brooks RH, Kaye J, Nance EP, Callahan LF. Comparison of 3 quantitative measures of hand radiographs in patients with rheumatoid arthritis: Steinbrocker stage, Kaye modified Sharp score, and Larsen score. J Rheumatol. 1997;24: 2106–2112. 9375867 Plant MJ, Jones PW, Saklatvala J, Ollier WE, Dawes PT. Patterns of radiological progression in early rheumatoid arthritis: results of an 8 year prospective study. J Rheumatol. 1998;25: 417–426. 9517757 Price AL, Patterson NJ, Plenge RM, Weinblatt ME, Shadick NA, Reich D. Principal components analysis corrects for stratification in genome-wide association studies. Nat Genet. 2006;38: 904–909. doi: 10.1038/ng1847 16862161 Willer CJ, Li Y, Abecasis GR. METAL: fast and efficient meta-analysis of genomewide association scans. Bioinformatics. 2010;26: 2190–2191. doi: 10.1093/bioinformatics/btq340 20616382 Lee CH, Cook S, Lee JS, Han B. Comparison of Two Meta-Analysis Methods: Inverse-Variance-Weighted Average and Weighted Sum of Z-Scores. Genomics Inform. 2016;14: 173–180. doi: 10.5808/GI.2016.14.4.173 28154508 Eyre S, Bowes J, Diogo D, Lee A, Barton A, Martin P, et al. High-density genetic mapping identifies new susceptibility loci for rheumatoid arthritis. Barton A Morgan A, Wilson G, Hyrich K, Moitra RK, Prouse PJ, Shawe DJ, Crisp AJ, Gaston JS, Hall FC, Hazleman BL, Jenner JR, Lillicrap MS, Ostor A, Silverman B, Speed C, Bruce IN, Hyrich K, Ho P, Gorodkin R, Armstrong D, Chuck AJ, Hailwood S, Kumar N, Ba IJ, editor. Nat Genet. 2012;44: 1336–1340. doi: 10.1038/ng.2462 23143596 Yang J, Wray NR, Visscher PM. Comparing apples and oranges: equating the power of case-control and quantitative trait association studies. Genet Epidemiol. 2010;34: 254–257. doi: 10.1002/gepi.20456 19918758 Okada Y, Wu D, Trynka G, Raj T, Terao C, Ikari K, et al. Genetics of rheumatoid arthritis contributes to biology and drug discovery. Eyre S Diogo D, Lee A, Barton A, Martin P, Zhernakova A, Stahl E, Viatte S, McAllister K, Amos CI, Padyukov L, Toes RE, Huizinga TW, Wijmenga C, Trynka G, Franke L, Westra HJ, Alfredsson L, Hu X, Sandor C, de Bakker PI, Davila S, Khor CC, Heng KK, Andrew BJ, editor. Nature. 2014;506: 376–381. doi: 10.1038/nature12873 24390342 Viatte S, Plant D, Han B, Fu B, Yarwood A, Thomson W, et al. Association of HLA-DRB1 haplotypes with rheumatoid arthritis severity, mortality, and treatment response. JAMA. 2015;313: 1645–1656. doi: 10.1001/jama.2015.3435 25919528