Whole-genome sequencing study of 488,888 individuals identifies rare variants and genes associated with glaucoma

Whole-genome sequencing study of 488,888 individuals identifies rare variants and genes associated with glaucoma | medRxiv /* */ /* */ <!-- <!-- /*! * yepnope1.5.4 * (c) WTFPL, GPLv2 */ (function(a,b,c){function d(a){return"[object Function]"==o.call(a)}function e(a){return"string"==typeof a}function f(){}function g(a){return!a||"loaded"==a||"complete"==a||"uninitialized"==a}function h(){var a=p.shift();q=1,a?a.t?m(function(){("c"==a.t?B.injectCss:B.injectJs)(a.s,0,a.a,a.x,a.e,1)},0):(a(),h()):q=0}function i(a,c,d,e,f,i,j){function k(b){if(!o&&g(l.readyState)&&(u.r=o=1,!q&&h(),l.onload=l.onreadystatechange=null,b)){"img"!=a&&m(function(){t.removeChild(l)},50);for(var d in y[c])y[c].hasOwnProperty(d)&&y[c][d].onload()}}var j=j||B.errorTimeout,l=b.createElement(a),o=0,r=0,u={t:d,s:c,e:f,a:i,x:j};1===y[c]&&(r=1,y[c]=[]),"object"==a?l.data=c:(l.src=c,l.type=a),l.width=l.height="0",l.onerror=l.onload=l.onreadystatechange=function(){k.call(this,r)},p.splice(e,0,u),"img"!=a&&(r||2===y[c]?(t.insertBefore(l,s?null:n),m(k,j)):y[c].push(l))}function j(a,b,c,d,f){return q=0,b=b||"j",e(a)?i("c"==b?v:u,a,b,this.i++,c,d,f):(p.splice(this.i++,0,a),1==p.length&&h()),this}function k(){var a=B;return a.loader={load:j,i:0},a}var l=b.documentElement,m=a.setTimeout,n=b.getElementsByTagName("script")[0],o={}.toString,p=[],q=0,r="MozAppearance"in l.style,s=r&&!!b.createRange().compareNode,t=s?l:n.parentNode,l=a.opera&&"[object Opera]"==o.call(a.opera),l=!!b.attachEvent&&!l,u=r?"object":l?"script":"img",v=l?"script":u,w=Array.isArray||function(a){return"[object Array]"==o.call(a)},x=[],y={},z={timeout:function(a,b){return b.length&&(a.timeout=b[0]),a}},A,B;B=function(a){function b(a){var a=a.split("!"),b=x.length,c=a.pop(),d=a.length,c={url:c,origUrl:c,prefixes:a},e,f,g;for(f=0;f<d;f++)g=a[f].split("="),(e=z[g.shift()])&&(c=e(c,g));for(f=0;f<b;f++)c=x[f](c);return c}function g(a,e,f,g,h){var i=b(a),j=i.autoCallback;i.url.split(".").pop().split("?").shift(),i.bypass||(e&&(e=d(e)?e:e[a]||e[g]||e[a.split("/").pop().split("?")[0]]),i.instead?i.instead(a,e,f,g,h):(y[i.url]?i.noexec=!0:y[i.url]=1,f.load(i.url,i.forceCSS||!i.forceJS&&"css"==i.url.split(".").pop().split("?").shift()?"c":c,i.noexec,i.attrs,i.timeout),(d(e)||d(j))&&f.load(function(){k(),e&&e(i.origUrl,h,g),j&&j(i.origUrl,h,g),y[i.url]=2})))}function h(a,b){function c(a,c){if(a){if(e(a))c||(j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}),g(a,j,b,0,h);else if(Object(a)===a)for(n in m=function(){var b=0,c;for(c in a)a.hasOwnProperty(c)&&b++;return b}(),a)a.hasOwnProperty(n)&&(!c&&!--m&&(d(j)?j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}:j[n]=function(a){return function(){var b=[].slice.call(arguments);a&&a.apply(this,b),l()}}(k[n])),g(a[n],j,b,n,h))}else!c&&l()}var h=!!a.test,i=a.load||a.both,j=a.callback||f,k=j,l=a.complete||f,m,n;c(h?a.yep:a.nope,!!i),i&&c(i)}var i,j,l=this.yepnope.loader;if(e(a))g(a,0,l,0);else if(w(a))for(i=0;i (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0];var j=d.createElement(s);var dl=l!='dataLayer'?'&l='+l:'';j.src='//www.googletagmanager.com/gtm.js?id='+i+dl;j.type='text/javascript';j.async=true;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-P4HH5NV'); Skip to main content Home About Submit ALERTS / RSS Search for this keyword Advanced Search Whole-genome sequencing study of 488,888 individuals identifies rare variants and genes associated with glaucoma Xiaoyi Raymond Gao , Krishnakumar Kizhatil doi: https://doi.org/10.1101/2025.06.02.25328820 Xiaoyi Raymond Gao 1 Department of Ophthalmology and Visual Sciences, College of Medicine, The Ohio State University , Columbus, OH 43210, USA 2 Department of Biomedical Informatics, College of Medicine, The Ohio State University , Columbus, OH 43210, USA Find this author on Google Scholar Find this author on PubMed Search for this author on this site For correspondence: raymond.gao{at}osumc.edu Krishnakumar Kizhatil 1 Department of Ophthalmology and Visual Sciences, College of Medicine, The Ohio State University , Columbus, OH 43210, USA Find this author on Google Scholar Find this author on PubMed Search for this author on this site Abstract Full Text Info/History Metrics Data/Code Preview PDF Abstract Glaucoma is a leading cause of irreversible blindness worldwide, with primary open-angle glaucoma (POAG) being the most common form. While previous genome-wide association studies have identified common genetic variants associated with POAG, primarily through array-based genotyping and imputation, the role of rare variants remains poorly understood. Our study aims to address this gap in knowledge by conducting the largest whole-genome sequencing (WGS) analysis of glaucoma to date. We analyzed WGS data from 488,888 UK Biobank participants, comprising 19,440 POAG cases and 469,448 controls. To validate our findings, we used the FinnGen cohort and the Million Veteran Program. We confirmed associations of known glaucoma genes, including MYOC , OPTN , and identified more than 68 previously unreported genes for glaucoma, such as FMO4 , PRRC2C , MTOR , ANGLPL7 , AREL1 , and LINC02210-CRHR1 . Seven of these genes, i.e., MTOR , COL1A2 , DDR2 , LYN , NR1H3 , TGFB3 , and MAPT , are current drug targets. Our findings underscore the value of WGS for uncovering rare variants and novel genes implicated in glaucoma. By expanding the genetic architecture of this complex disease, our work paves the way for future research into disease mechanisms, and ultimately, the development of more targeted preventive and therapeutic strategies. Introduction Glaucoma remains the leading cause of irreversible blindness worldwide 1 , 2 , characterized by progressive optic nerve head excavation and irreversible visual field loss. Primary open-angle glaucoma (POAG), accounting for approximately 90% of glaucoma cases in North America, represents the most prevalent form of this condition 3 , 4 . POAG demonstrates high heritability, with numerous genetic loci identified through previous genome-wide association studies (GWASs) 5 – 7 . While these earlier GWASs have significantly advanced our understanding of glaucoma genetics, they have predominantly relied on genome-wide arrays and imputation techniques. This approach has several inherent limitations. Array-based studies primarily capture common genetic variants, which typically exhibit modest effect sizes. Furthermore, imputation methods often fail to adequately represent rare variants, leaving substantial gaps in our understanding of the complete genetic architecture of POAG. Consequently, the contribution of rare variants to glaucoma pathogenesis remains largely unexplored, despite their potential for larger effect sizes and greater clinical significance. The recent release of whole-genome sequencing (WGS) data from the UK Biobank (UKB) 8 , a prospective cohort of approximately half a million adult participants, presents an unprecedented opportunity to investigate rare genetic variants and to identify novel genes across numerous human traits and diseases 9 , 10 . Previous studies leveraging large-scale sequencing have successfully identified rare variants with substantial effect sizes that demonstrate considerable translational potential, such as GHRH variants for height determination and PCSK9 variants as targets for low-density lipoprotein reduction 11 , 12 . Despite this potential, the UK Biobank’s WGS data remains largely unreported specifically for glaucoma genetics. In this study, we analyzed WGS data from 488,888 UKB participants to identify rare variants and genes associated with POAG. We further validated our findings using summary statistics from the FinnGen cohort and the Department of Veterans Affairs (VA) Million Veteran Program (MVP). To our knowledge, this represents the largest sequencing study of glaucoma conducted to date. Our comprehensive approach has uncovered previously unreported rare variants and genes associated with glaucoma, substantially expanding our understanding of the biological mechanisms underlying this disease and revealing potential novel drug targets for therapeutic intervention. Results In this study, we analyzed WGS data from 488,888 UKB participants, of whom 464,778 (95%) were of European (EUR) ancestry. The cohort had a mean age of 57.5 years (standard deviation: 8.4 years) with 54% female participants. We employed a comprehensive suite of state-of-the-art analytical approaches to identify variants, genes, potential biological mechanisms, and drug targets associated with POAG. Single-Variant Analysis Our single-variant analysis identified 6,787 variants in 196 genes (excluding intergenic regions) significantly associated with POAG ( P < 5×10 −8 , Supplementary Table 1). Among these, we discovered 56 previously unreported genes for POAG, with 42 identified in the EUR analysis and 14 additional genes in the pan-ancestry analysis ( Table 1 ). View this table: View inline View popup Table 1. Genome-wide significant variants and their corresponding genes for primary open-angle glaucoma We confirmed significant associations with known glaucoma-related rare variants, including rs74315329 (allele frequency [AF] = 0.013%, P = 3.49×10 −50 ) in MYOC and rs28939688 (AF = 0.0005%, P = 1.25×10 −8 ) in OPTN . Additionally, we identified novel rare variants significantly associated with POAG, such as rs147235365 in FMO3 (AF = 0.018%, odds ratio [OR] = 1.84, P = 2.89×10 −8 ) and rs534598623 in PRRC2C (AF = 0.025%, OR = 2.70, P = 2.31×10 −32 ). The FMO3 variant was replicated in MVP ( P = 9.63×10 −5 ), while the PRRC2C variant was replicated in both FinnGen ( P = 7.74×10 −33 ) and MVP ( P = 7.53×10 −23 ). Three additional rare variants demonstrated significant POAG associations: rs142017159 in PRRX1 (AF = 0.05%, OR = 2.98, P = 1.40×10 −9 ), rs745475536 in FMO4 (AF = 0.03%, OR = 3.96, P = 5.03×10 −10 ), and rs756856153 in EEF1AKNMT (AF = 0.06%, OR = 4.50, P = 4.64×10 −22 ). These findings were replicated in independent cohorts: PRRX1 in MVP (minimum P of variants in the gene [minP] = 2.45×10 −6 ), FMO4 in FinnGen (minP = 7.22×10 −6 ), and EEF1AKNMT in FinnGen (minP = 1.37×10 −48 ). We also identified multiple common variants in previously unreported genes significantly associated with POAG, including rs5829384 ( MIR3125 ), rs34339006 ( DGKD ), rs66900704 ( MAT1A ), rs4934083 ( DYDC1 ), rs1972371 ( DYDC2 ), rs5786455 ( PRXL2A ), rs12587457 ( AREL1 ), rs56191889 ( MAPK8IP1P2 ), rs11658815 ( SEPTIN9 ), and rs75792643 ( WNT7B ). All these variants were replicated in either FinnGen or MVP or both ( P < 5×10 −5 ). Replicated variants showed consistent effect direction in replication datasets. In the pan-ancestry analysis, we identified additional significant associations, including common variants rs1127100 in ADGRB2 and rs6959106 in COMETT (both replicated in MVP, P < 5×10 −11 ). We also found rare variants rs60912069 in PLD5 (AF = 0.0005%, P = 3.32×10 −8 ) and rs1169584301 in ZNF578 (AF = 0.003%, P = 2.48×10 −8 ), with both genes showing associations in FinnGen (minP = 3.43×10 −5 ) and MVP (minP = 3.29×10 −5 ), respectively. Figure 1(a) presents a circular Manhattan plot of the genome-wide P-values for pan-ancestry results. The genomic control lambda values for EUR and pan-ancestry analyses were well-controlled at 0.86 and 0.87, respectively. Download figure Open in new tab Figure 1. Manhattan plots displaying the -log 10 ( P ) for the association between POAG and single variants and genes. (a) Single-variant pan-ancestry results. (b) Gene-based pan-ancestry results. Genetic variants or genes are plotted by genomic position. Gene-Based Analysis of Rare Variants Our REGENIE 13 gene-based analysis of rare variants identified 47 genes significantly associated with POAG ( P < 2.5×10 −6 ), of which 12 were previously unreported discoveries. Specifically, 46 genes were identified from the EUR analysis with one additional gene from the pan-ancestry analysis; six genes emerged from the loss-of-function (LOF) analysis, while 41 were identified from the combined LOF and missense analysis ( Table 2 ). View this table: View inline View popup Table 2. Genome-wide significant results for POAG from gene-based analysis Previously known POAG genes identified through common-variant studies, including TMCO1 , CAV2 , CAV1 , LMX1B , and SIX6 , showed significant gene-based rare-variant associations ( P < 2.5×10 −6 ). Notably, we identified several previously unreported genes for POAG, including MYOCOS , RFPL1S , MTOR , ANGPTL7 , AREL1 , IFT43 , SMG6-IT1 , and LINC02210-CRHR1 . Among these, MTOR and ANGPTL7 had been previously associated with intraocular pressure (IOP) 14 , 15 but not directly with POAG. Four of these novel genes, MTOR , ANGPTL7 , AREL1 , and LINC02210-CRHR1 , showed significant associations in either FinnGen or MVP or both (minP ranging from 4.90×10 −5 to 4.52×10 −28 ). Figure 1(b) presents a circular Manhattan plot of the genome-wide p-values for gene-based pan-ancestry results. Gene Expression Analysis To provide biological context for our identified previously unreported genes (68 genes, Tables 1 and 2 ), we evaluated their expression patterns using both bulk RNA and single-cell RNA (scRNA) datasets. We examined expression in key ocular tissues: the anterior segment drainage structures responsible for aqueous humor outflow and intraocular pressure regulation, as well as the retina and retinal ganglion cells (RGCs), the neurons that are damaged in glaucoma. We compared our gene list to genes expressed in purified mouse Schlemm’s canal endothelial cells (SCE) identified by bulk RNA-seq 16 (Supplementary Table 2). This bulk RNA-seq dataset represents the most comprehensive available resource for SCE, and mouse drainage structures closely resemble their human counterparts in gene expression, physiology, and morphology. Notably, 34% of our genes were expressed in SCE. Several newly identified POAG genes showed robust expression in SCE, including ATXN7 , COL1A2 , DGKD , FAM89B , GPM6B , IFT43 , IQGAP1 , KBTBD4 , LYN , MTOR , NBAS , NPRL2 , OXNAD1 , PFAS , and PRRC2C . More modest SCE expression was observed for PRRX1 , PTEN , PTPRM , RBMS3 , TCERG1 , TNS3 , and USP49 . For trabecular meshwork (TM) gene expression analysis, we utilized scRNA-seq data from mouse and human anterior segment tissues 16 – 18 (Supplementary Table 2). TM cells expressed 25% of our genes. Several genes were enriched in TM cell clusters, including COL1A2 , PRRX1 , FMO4 , MYOCOS , ADGRB2 , RBMS3 , FAM89B , IFT43 , EEF1AKNMT , PTPRM , ANGPTL7 , TNS3 , and GPM6B , while PRXL2A , PTEN , and NBAS were present at lower levels. We identified ten genes common to both SCE and TM, as well as genes uniquely expressed in either SCE (n=12) or TM (n=7), suggesting both shared and distinct functions between these cell types. Mining of human RGC scRNA-seq data 19 showed that 43% of our genes were expressed in these neurons (Supplementary Table 2). RGC-enriched genes included DPP6 , RBMS3 , PRRX1 , ANKS1B , FMO4 , PRXL2A , PLD , FAM89B , IQGAP1 , DYDC2 , ZNF215 , MAT1A , B4GALT4-AS1 , EEF1AKNMT , and PTPRM . Additional genes ( DYDC1 , BDH1 , LRRC37A3 , KBTBD4 , NBAS , OXNAD1 , ADGRB2 , TCERG1 , PRRC2C , AKAP14 , NPRL2 , and LRRC37A2 ) showed more modest expression in RGCs. Analysis of human retina bulk RNA expression revealed that more than 90% of the identified rare-variant genes were expressed at high (55.6%) or medium (36.1%) levels (Supplementary Figure 1). Pleiotropy Among Genes Identified Through Rare-Variant Analyses The identified rare-variant genes associated with POAG demonstrate significant pleiotropy, influencing a wide range of traits and conditions. Analysis using the GWAS Catalog 20 , 21 highlighted that these genes (70 queried) frequently associate with various phenotypes (Supplementary Table 3), notably in categories such as cardiovascular measurements (62% of the queried genes, such as CAV1 , CAV2 , LPP , LTBP2 , MTCH2 , PLCE1 , PRRX1 , SVEP1 , TGFB3 , TES , TXNRD2 ), cancer (50% of the queried genes, such as BCAS3 , CAV2 , COL1A2 , DDR2 , PTPRM , SIX1 ), hematological measurements (44% of the queried genes, such as LYN , PLCE1 , MTOR ), lipid or lipoprotein measurements (38% of the queried genes, such as FMO3 , NR1H3 , MTCH2 ), and height (65% of the queried genes, such as COL1A2 , DDR2 , MAPT-AS1 , MTOR , PRRX1 , TGFB3 ). Additional notable associations include Alzheimer’s, educational attainment, refractive error, and retinal problems or measurements. Top ranked genes with the greatest number of traits associated with include LPP (134 mapped traits), LINC02210-CRHR1 (91 mapped traits), and PLCE1 (88 mapped traits). This extensive pleiotropy underscores the complex genetic landscape underlying POAG and the broad systemic impact these genes may have, potentially informing future therapeutic strategies. Potential Drug Targets To identify potential therapeutic opportunities, we investigated drug targets among the identified POAG-associated genes using the Open Targets platform. Table 3 summarizes currently known drug targets for these genes, primarily identified through our gene-based analysis of rare variants. These genes are targeted for a variety of diseases and mechanisms. View this table: View inline View popup Table 3. Known drug targets for the identified glaucoma rare-variant genes. MTOR emerged as a particularly promising target, with 25 existing drugs including apitolisib, ridaforolimus, dactolisib, gedatolisib, vistusertib, and samotolisib. While primarily developed for oncology applications, MTOR -targeting therapeutics have expanded into cardiovascular, fibrotic, and infectious diseases. Current clinical development spans solid epithelial tumors, CNS malignancies, sarcomas, hematologic cancers, hereditary mTORopathies, and emerging non-oncological indications. COL1A2 , targeted by ocriplasmin and collagenase clostridium histolyticum, functions as a collagen hydrolytic enzyme and is explored in conditions like diabetic macular edema, retinal vein occlusion, and macular degeneration. NR1H3 , targeted by rovacolaz, bms-852927, hyodeoxycholic acid, abequolixron, and abequolixr, serves as a liver X receptor agonist and modulator, relevant to hypercholesterolemia and certain cancers. LYN is targeted by several drugs, including bafetinib, bosutinib, dasatinib, and ilorasertib, which function as SRC and tyrosine-protein kinase Lyn inhibitors primarily developed for acute leukemias and chronic myeloid leukemia. DDR2 is targeted by regorafenib, a discoidin domain-containing receptor 2 inhibitor currently being evaluated for acute myeloid leukemia and macular degeneration. TGFB3 -targeting agents, including luspatercept, bintrafusp alfa, and fresolimumab, inhibit transforming growth factor-beta signaling and are being investigated across solid tumors, bone-marrow failure syndromes, and fibrotic conditions. MAPT is targeted by tau inhibitors such as bepranemab, gosuranemab, and semorinemab, which are being actively studied for Alzheimer’s disease and related tauopathies. Notably, among these genes, MTOR , COL1A2 , LYN , and DDR2 have therapeutic investigations relevant to macular degeneration, while LYN and MAPT are associated with treatments targeting Alzheimer’s disease, suggesting potential mechanistic overlap with POAG pathophysiology. Discussion In this study, we conducted the largest WGS analysis of glaucoma to date using data from UKB. By employing complementary single-variant and gene-based analytical frameworks, we have significantly expanded our understanding of the genetic architecture of POAG, particularly regarding the contribution of rare variants that were largely missed in previous microarray-based studies. In addition to confirming known POAG-associated genes, we identified 68 previously unreported genes, demonstrating the enhanced discovery power of WGS data. Approximately half of these novel genes were also associated with glaucoma in independent cohorts from FinnGen, MVP, or both, providing crucial validation. Notably, seven of these genes represent drug targets for existing clinical treatments, highlighting immediate translational potential. WGS enabled the identification of rare-variant associations with POAG through both single-variant and gene-based analyses. Our single-variant analysis revealed many novel rare variants significantly associated with POAG, including rs147235365 in FMO3 , rs534598623 in PRRC2C , rs142017159 in PRRX1 , rs745475536 in FMO4 , and rs756856153 in EEF1AKNMT . Through gene-based analysis, we identified 45 genes harboring rare variants with significant POAG associations. Six of these genes were identified from LOF variants alone, while the majority (87%) were identified from a combination of LOF and missense variants, highlighting the importance of including missense variants in rare-variant analysis. Among the 45 genes, 12 of these genes were previously unreported for POAG (though ANGPTL7 and MTOR had been associated with intraocular pressure) and 73% overlapped with previously reported genes for POAG identified through array-based GWASs, reaffirming the importance of these genes. Though replication remains challenging as most existing GWASs rely on arrays and imputation, our study provides the first evidence of rare-variant associations with POAG for these genes. Beyond rare variants, WGS also identified numerous common variants and genes missed by previous large-scale GWAS meta-analyses. These include common variants in MIR3125 , MAT1A , DYDC1 , DYDC2 , PRXL2A , AREL1 , IQGAP1 , NSFP1 , SEPTIN9 , and WNT7B . These associations were replicated in FinnGen, MVP, or both cohorts ( P < 5×10 −5 ), demonstrating that a substantial number of common variants and genes remain undetected by array-based approaches and imputation. There has been growing interest in pleiotropy within human genetics studies. Through GWASs, thousands of genetic associations have been identified, and investigating whether traits share common genetic variants can illuminate underlying biological processes and reveal important therapeutic opportunities, including drug repositioning strategies 22 , 23 . Our study demonstrates that rare-variant genes associated with POAG exhibit extensive pleiotropy with both ocular and systemic traits. Among ocular phenotypes, several of our identified genes are also associated with refractive error, retinal degeneration, and various retinal measurements, suggesting shared pathways in ocular development and pathology. More broadly, numerous systemic traits were associated with our identified POAG genes, including Alzheimer’s disease, cardiovascular measurements, cancer, hematological parameters, and lipid or lipoprotein levels. This pleiotropic pattern suggests that POAG shares genetic architecture with multiple disease processes, potentially explaining epidemiological associations observed between glaucoma and systemic conditions. From a therapeutic perspective, pleiotropy indicates that drugs developed for one condition may have efficacy in treating related disorders. Notably, about 10% of our rare-variant genes, including MTOR , COL1A2 , DDR2 , LYN , NR1H3 , TGFB3 , and MAPT , are established drug targets with existing therapeutic compounds. This finding highlights immediate opportunities for drug repositioning in glaucoma treatment. Furthermore, the remaining genes in our dataset represent potential novel therapeutic targets that warrant further investigation for drug development efforts. While our analysis participants were primarily of EUR ancestry, we demonstrated that including subjects of other ancestries in a pan-ancestry analysis further enhanced statistical power. The inclusion of non-EUR participants, despite comprising only 5% of the UKB cohort, enabled the identification of 14 additional previously unreported genes for POAG. This underscores the importance of diverse ancestral representation in genetic studies and suggests that as more genetic data from diverse populations become available, we can anticipate further novel discoveries. This study has several limitations. Despite being the largest WGS dataset currently available, ancestral diversity remains low, with participants of EUR ancestry comprising approximately 95% of the UKB cohort. Larger, more diverse datasets, such as those being developed in the All of Us project, will be invaluable for further discovery and validation. Rare variants present intrinsic challenges due to their low frequency, making replication substantially more difficult than for common variants. Most rare variants identified in this study lack exact counterparts in FinnGen and MVP GWAS summary statistics. Additionally, our use of combined self-reported glaucoma and ICD-10/9 codes for phenotyping in UKB may lack homogeneity for specialized glaucoma subtypes, but given POAG accounts for the majority of glaucoma and previous studies have validated this approach for studying POAG genetics 24 , 25 . Furthermore, our analysis did not cover intergenic variants, which are functionally challenging to interpret. In conclusion, we have conducted the largest WGS study of POAG to date, demonstrating the efficacy of both single-variant and gene-based analyses. Our results strongly support the value of gene-based aggregation and pan-ancestry approaches for increasing study power, particularly for rare variant discovery. This study highlights the substantial value of WGS in enhancing our understanding of the biological mechanisms underlying this blinding disease and has uncovered potential novel therapeutic targets for glaucoma treatment. Materials and Methods UKB Resource The UK Biobank (UKB) is an ongoing large-scale prospective cohort study, the details of which have been described extensively elsewhere 26 , 27 . Briefly, UKB recruited over 500,000 adult participants aged 40-70 years at enrollment who were living in the United Kingdom and registered with the National Health Service at study baseline (2006-2010). Comprehensive data collection included medical information from both self-reports and electronic health records, family history, lifestyle information, and DNA samples. Glaucoma cases were identified using a combination of self-reported glaucoma (UKB data fields 6148, 20002) and ICD-10 or ICD-9 diagnosis codes for glaucoma (UKB data fields 131186, 131188, 41202, 41204, 41076, 41078, 41270). We excluded cases of secondary glaucoma resulting from eye trauma, inflammation, other eye disorders, drug-induced effects, or other specific glaucoma types. This approach for glaucoma case identification based on self-reports and ICD codes has been validated in previous studies 24 , 25 , and the proportion of non-primary open-angle glaucoma (POAG) cases in UKB is expected to be minimal 28 . Controls were defined as participants without glaucoma or self-reported eye problems. Our access to this resource was approved by UKB (application number 23424), and we obtained access to fully de-identified data. Whole-genome sequencing of all UKB participants was performed using the Illumina NovaSeq 6000 platform to an average coverage of 32.5×. Detailed protocols for sequencing, variant calling, and quality control have been described previously 29 . High-quality variants comprised over 98.8% of single nucleotide polymorphisms (SNPs) and 96.05% of indels (AA score > 0.5 and < 5 duplicate inconsistencies) 29 . We utilized SNPs and indels called using GraphTyper and retained samples with missing rates 95% and minor allele count (MAC) > 1 were included. Variant annotation was performed using VEP 2 and ANNOVAR 30 . After overlapping with phenotype and covariate data, the final dataset comprised 18,171 EUR cases and 446,607 EUR controls, and 19,440 pan-ancestry cases and 469,448 pan-ancestry controls. Single-variant and Gene-based Analyses Single-variant association analyses were performed using REGENIE 13 , a machine-learning method that accounts for population stratification and sample relatedness. We analyzed all non-intergenic variants with MAC ≥ 5 (REGENIE default threshold) and included age, sex, and the first 10 principal components (PCs) of genetic ancestry as covariates. Variants achieving P < 5 × 10 −8 were considered genome-wide significant, consistent with established GWAS standards. We performed both EUR-only and pan-ancestry analyses. For pan-ancestry analyses, we included an additional covariate representing five major ancestral groups (European, South Asian, East Asian, African, and Admixed American) identified by projecting PCs onto the 1000 Genomes Project reference panel. Gene-based association tests were also conducted using REGENIE 13 , which implements rare-variant collapsing and aggregation tests including SKAT-O 31 , burden 32 , and SKAT 33 , 34 methods. We constructed gene sets using predicted loss-of-function (LOF) variants, defined as stop gained, stop lost, start lost, splice donor, splice acceptor, and frameshift variants based on VEP 35 annotation and gnomAD LOF classification 36 . Additionally, we analyzed gene sets combining LOF and missense variants. Age, sex, and the first 10 PCs were included as covariates. Genes achieving P < 2.5 × 10 −6 were considered significant. Both EUR-only and pan-ancestry analyses were performed, with dummy variables for major ancestral groups added as additional covariates in the latter. Glaucoma Lookup in FinnGen and MVP For replication of our findings, we performed lookups of all genome-wide significant POAG variants and genes in publicly available summary statistics from the FinnGen and MVP resources. FinnGen is a large-scale biobank study focused on the Finnish population 37 . The study has enrolled over 500,000 participants who have been genotyped and phenotyped. The study leverages the power of nationwide biobanks, electronic health records, and population isolation to identify variants associated with various diseases. Data collection from Finnish biobanks and digital healthcare records began in 2017, with a recruited population averaging 63 years of age and predominantly hospital-based recruitment. Phenotypes were constructed using ICD-9 and ICD-10 codes. Genotyping was performed using custom Axiom FinnGen1 and legacy arrays, followed by imputation to 21.3 million markers based on whole-genome sequences from Finnish individuals. We utilized the DF12 release of their POAG association results, which included 10,832 cases and 473,757 controls, analyzed using SAIGE mixed models. The Department of Veterans Affairs Million Veteran Program (MVP) is an ongoing prospective cohort study and mega-biobank established in 2011 to investigate genetic influences on health and disease among veterans 38 . The program reached its milestone of one million enrolled participants in 2023. The study population is ancestrally diverse, including participants of European, African, Admixed American, and East Asian ancestry, with a mean age of 61.9 years and 91.2% male composition. Genotyping was performed using a custom ThermoFisher Axiom MVP 1.0 platform, followed by imputation to a hybrid reference panel comprising the African Genome Resources panel and 1000 Genomes Project (Phase 3 v5). We utilized the recently released POAG association results for European ancestry participants, which included 20,401 cases and 431,032 controls, analyzed using SAIGE mixed models. Gene Expression We utilized Genevestigator 39 , a web-based gene expression database, to query bulk RNA information in different human tissues, including retina. RNA information for Schlemm’s canal endothelium (SCE) were generated from mouse bulk RNA-seq data 16 . Single-cell expression data were curated from mouse and human TM cells using the Single Cell Portal and CellxGene resources, based on published datasets 16 – 18 . Single-cell expression data for RGC were obtained from previously published results 19 . GWAS Catalog Gene Lookup For checking broader phenotypic associations of the rare-variant genes, we used the GWAS Catalog (May 2025 version), a database of all published GWASs maintained by NHGRI and EBML-EBI 20 , 21 . The GWAS Catalog provides an excellent resource for studying pleiotropy in humans 40 . Drug Targets Prioritization To prioritize drug targets for the identified rare-variant genes, we used the Open Targets Platform 41 . For the identified genes, we queried the Open Targets for known drugs, their mechanisms of action (source ChEMBL), and disease information. The druggable genes provide key information on the relevance of these genes and potential drugs for repurposing for glaucoma management. Data availability Access to UK Biobank data, both phenotypic and genetic, is available to bona fide researchers through application on the UK Biobank website ( https://www.ukbiobank.ac.uk ). Our use of UK Biobank data was performed under application number 23424. The URLs for accessed databases: ChEMBL, https://www.ebi.ac.uk/chembl/ FinnGen, https://www.finngen.fi/ Genevestigator, https://genevestigator.com/ MVP, https://www.ncbi.nlm.nih.gov/projects/gap/ Open Target Platform, https://platform.opentargets.org UK Biobank, https://www.ukbiobank.ac.uk Code availability The programs used for data analysis: ANNOVAR, http://annovar.openbioinformatics.org/ FinnGen, https://www.finngen.fi/ REGENIE, https://rgcgithub.github.io/regenie/ VEP, https://useast.ensembl.org/info/docs/tools/vep/index.html R, https://www.r-project.org Author contributions X.R.G. conceived, planned and oversaw the present study. X.R.G. analyzed the data. K.K. queried gene expression databases. X.R.G. and K.K. wrote the manuscript. Conflict of Interest Statement None declared. Acknowledgements We would like to thank the study participants and investigators from the UK Biobank as well as the staff who aided in data collection and processing. We also want to acknowledge the participants and investigators of the FinnGen study and the Million Veteran Program. References ↵ Fan , B. J. & Wiggs , J. L . Glaucoma: genes, phenotypes, and new directions for therapy . J Clin Invest 120 , 3064 – 3072 ( 2010 ). doi: 10.1172/JCI4308543085 [pii] OpenUrl CrossRef PubMed Web of Science ↵ Blindness , G. B. D. , Vision Impairment, C. & Vision Loss Expert Group of the Global Burden of Disease, S. Causes of blindness and vision impairment in 2020 and trends over 30 years, and prevalence of avoidable blindness in relation to VISION 2020: the Right to Sight: an analysis for the Global Burden of Disease Study . Lancet Glob Health 9 , e144 – e160 ( 2021 ). doi: 10.1016/S2214-109X(20)30489-7 OpenUrl CrossRef ↵ Lang , G. K . Ophthalmology: A Pocket Textbook Atlas . 2nd edn , 635 ( Thieme 2007 ). ↵ Tham , Y. C. et al. Global prevalence of glaucoma and projections of glaucoma burden through 2040: a systematic review and meta-analysis . Ophthalmology 121 , 2081 – 2090 ( 2014 ). doi: 10.1016/j.ophtha.2014.05.013 OpenUrl CrossRef PubMed Web of Science ↵ Gharahkhani , P. et al. Genome-wide meta-analysis identifies 127 open-angle glaucoma loci with consistent effect across ancestries . Nature communications 12 , 1258 ( 2021 ). doi: 10.1038/s41467-020-20851-4 OpenUrl CrossRef Han , X. et al. Large-scale multitrait genome-wide association analyses identify hundreds of glaucoma risk loci . Nat Genet 55 , 1116 – 1125 ( 2023 ). doi: 10.1038/s41588-023-01428-5 OpenUrl CrossRef PubMed ↵ Verma , S. S. et al. A multi-cohort genome-wide association study in African ancestry individuals reveals risk loci for primary open-angle glaucoma . Cell 187 , 464 – 480 e410 ( 2024 ). doi: 10.1016/j.cell.2023.12.006 OpenUrl CrossRef PubMed ↵ Bycroft , C. et al. The UK Biobank resource with deep phenotyping and genomic data . Nature 562 , 203 – 209 ( 2018 ). doi: 10.1038/s41586-018-0579-z OpenUrl CrossRef PubMed ↵ Szustakowski , J. D. et al. Advancing human genetics research and drug discovery through exome sequencing of the UK Biobank . Nat Genet 53 , 942 – 948 ( 2021 ). doi: 10.1038/s41588-021-00885-0 OpenUrl CrossRef PubMed ↵ Backman , J. D. et al. Exome sequencing and analysis of 454,787 UK Biobank participants . Nature 599 , 628 – 634 ( 2021 ). doi: 10.1038/s41586-021-04103-z OpenUrl CrossRef ↵ Dewey , F. E. et al. Distribution and clinical impact of functional variants in 50,726 whole-exome sequences from the DiscovEHR study . Science 354 ( 2016 ). doi: 10.1126/science.aaf6814 OpenUrl Abstract / FREE Full Text ↵ Abul-Husn , N. S. et al. Genetic identification of familial hypercholesterolemia within a single US health care system . Science 354 ( 2016 ). https://doi.org:ARTN aaf7000 doi: 10.1126/science.aaf7000 OpenUrl Abstract / FREE Full Text ↵ Mbatchou , J. et al. Computationally efficient whole-genome regression for quantitative and binary traits . Nat Genet 53 , 1097 – 1103 ( 2021 ). doi: 10.1038/s41588-021-00870-7 OpenUrl CrossRef PubMed ↵ Gao , X. R. , Huang , H. , Nannini , D. R. , Fan , F. & Kim , H . Genome-wide association analyses identify new loci influencing intraocular pressure . Hum Mol Genet 27 , 2205 – 2213 ( 2018 ). doi: 10.1093/hmg/ddy111 OpenUrl CrossRef PubMed ↵ Gao , X. R. , Chiariglione , M. & Arch , A. J . Whole-exome sequencing study identifies rare variants and genes associated with intraocular pressure and glaucoma . Nature communications 13 , 7376 ( 2022 ). doi: 10.1038/s41467-022-35188-3 OpenUrl CrossRef PubMed ↵ Balasubramanian , R. et al. Transcriptomic profiling of Schlemm’s canal cells reveals a lymphatic-biased identity and three major cell states . eLife 13 ( 2024 ). doi: 10.7554/eLife.96459 OpenUrl CrossRef van Zyl , T. et al. Cell atlas of aqueous humor outflow pathways in eyes of humans and four model species provides insight into glaucoma pathogenesis . Proc Natl Acad Sci U S A 117 , 10339 – 10349 ( 2020 ). doi: 10.1073/pnas.2001250117 OpenUrl Abstract / FREE Full Text ↵ van Zyl , T. et al. Cell atlas of the human ocular anterior segment: Tissue-specific and shared cell types . Proc Natl Acad Sci U S A 119 , e2200914119 ( 2022 ). doi: 10.1073/pnas.2200914119 OpenUrl CrossRef PubMed ↵ Wang , S. K. et al. Single-cell multiome of the human retina and deep learning nominate causal variants in complex eye diseases . Cell Genom 2 ( 2022 ). doi: 10.1016/j.xgen.2022.100164 OpenUrl CrossRef PubMed ↵ Buniello , A. et al. The NHGRI-EBI GWAS Catalog of published genome-wide association studies, targeted arrays and summary statistics 2019 . Nucleic Acids Res 47 , D1005 – D1012 ( 2019 ). doi: 10.1093/nar/gky1120 OpenUrl CrossRef PubMed ↵ MacArthur , J. et al. The new NHGRI-EBI Catalog of published genome-wide association studies (GWAS Catalog) . Nucleic Acids Res 45 , D896 – D901 ( 2017 ). doi: 10.1093/nar/gkw1133 OpenUrl CrossRef PubMed ↵ Rastegar-Mojarad , M. , Ye , Z. , Kolesar , J. M. , Hebbring , S. J. & Lin , S. M . Opportunities for drug repositioning from phenome-wide association studies . Nature biotechnology 33 , 342 – 345 ( 2015 ). doi: 10.1038/nbt.3183 OpenUrl CrossRef PubMed ↵ Robinson , J. R. , Denny , J. C. , Roden , D. M. & Van Driest , S. L . Genome-wide and Phenome-wide Approaches to Understand Variable Drug Actions in Electronic Health Records . Clin Transl Sci 11 , 112 – 122 ( 2018 ). doi: 10.1111/cts.12522 OpenUrl CrossRef PubMed ↵ MacGregor , S. et al. Genome-wide association study of intraocular pressure uncovers new pathways to glaucoma . Nat Genet 50 , 1067 – 1071 ( 2018 ). doi: 10.1038/s41588-018-0176-y OpenUrl CrossRef PubMed ↵ Craig , J. E. et al. Multitrait analysis of glaucoma identifies new risk loci and enables polygenic prediction of disease susceptibility and progression . Nat Genet 52 , 160 – 166 ( 2020 ). doi: 10.1038/s41588-019-0556-y OpenUrl CrossRef PubMed ↵ Sudlow , C. , et al. UK Biobank: An Open Access Resource for Identifying the Causes of a Wide Range of Complex Diseases of Middle and Old Age . Plos Med 12 ( 2015 ). https://doi.org:ARTN e1001779 doi: 10.1371/journal.pmed.1001779 OpenUrl CrossRef PubMed ↵ Allen , N. E. , Sudlow , C. , Peakman , T. & Collins , R. UK Biobank Data: Come and Get It . Sci Transl Med 6 ( 2014 ). https://doi.org:ARTN 224ed4 doi: 10.1126/scitranslmed.3008601 OpenUrl FREE Full Text ↵ Chan , M. P. Y. et al. Glaucoma and intraocular pressure in EPIC-Norfolk Eye Study: cross sectional study . BMJ 358 , j3889 ( 2017 ). doi: 10.1136/bmj.j3889 OpenUrl Abstract / FREE Full Text ↵ Li , S. , Carss , K. J. , Halldorsson , B. V. , Cortes , A. & Consortium , U. B. W.-G. S . Whole-genome sequencing of half-a-million UK Biobank participants . medRxiv , 2023.2012.2006.23299426 ( 2023 ). doi: 10.1101/2023.12.06.23299426 OpenUrl Abstract / FREE Full Text ↵ Wang , K. , Li , M. & Hakonarson , H . ANNOVAR: functional annotation of genetic variants from high-throughput sequencing data . Nucleic Acids Res 38 , e164 ( 2010 ). doi: 10.1093/nar/gkq603 OpenUrl CrossRef PubMed ↵ Lee , S. , Wu , M. C. & Lin , X . Optimal tests for rare variant effects in sequencing association studies . Biostatistics (Oxford, England) 13 , 762 – 775 ( 2012 ). doi: 10.1093/biostatistics/kxs014 OpenUrl CrossRef PubMed Web of Science ↵ Li , B. & Leal , S. M . Methods for detecting associations with rare variants for common diseases: application to analysis of sequence data . Am J Hum Genet 83 , 311 – 321 ( 2008 ). S0002-9297(08)00408-4 [pii] doi: 10.1016/j.ajhg.2008.06.024 OpenUrl CrossRef PubMed Web of Science ↵ Wu , M. C. et al. Powerful SNP-set analysis for case-control genome-wide association studies . Am J Hum Genet 86 , 929 – 942 ( 2010 ). doi: 10.1016/j.ajhg.2010.05.002 OpenUrl CrossRef PubMed Web of Science ↵ Wu , M. C. et al. Rare-variant association testing for sequencing data with the sequence kernel association test . Am J Hum Genet 89 , 82 – 93 ( 2011 ). S0002-9297(11)00222-9 [pii] doi: 10.1016/j.ajhg.2011.05.029 OpenUrl CrossRef PubMed ↵ McLaren , W. et al. The Ensembl Variant Effect Predictor . Genome Biol 17 , 122 ( 2016 ). doi: 10.1186/s13059-016-0974-4 OpenUrl CrossRef PubMed ↵ Karczewski , K. J. et al. The mutational constraint spectrum quantified from variation in 141,456 humans . Nature 581 , 434 – 443 ( 2020 ). doi: 10.1038/s41586-020-2308-7 OpenUrl CrossRef PubMed ↵ Kurki , M. I. et al. FinnGen: Unique genetic insights from combining isolated population and national health register data . medRxiv , 2022.2003.2003.22271360 ( 2022 ). doi: 10.1101/2022.03.03.22271360 OpenUrl Abstract / FREE Full Text ↵ Verma , A. et al. Diversity and scale: Genetic architecture of 2068 traits in the VA Million Veteran Program . Science 385 , eadj1182 ( 2024 ). doi: 10.1126/science.adj1182 OpenUrl CrossRef PubMed ↵ Hruz , T. et al. Genevestigator v3: a reference expression database for the meta-analysis of transcriptomes . Adv Bioinformatics 2008 , 420747 ( 2008 ). doi: 10.1155/2008/420747 OpenUrl CrossRef PubMed ↵ Xiaoyi Raymond Gao Gao , X. R . Chapter 18 - Pleiotropy in eye disease and related traits in Genetics and Genomics of Eye Disease (ed Xiaoyi Raymond Gao ) 315 – 336 ( Academic Press , 2020 ). ↵ Buniello , A. et al. Open Targets Platform: facilitating therapeutic hypotheses building in drug discovery . Nucleic Acids Res 53 , D1467 – D1475 ( 2025 ). doi: 10.1093/nar/gkae1128 OpenUrl CrossRef View the discussion thread. Back to top Previous Next Posted June 03, 2025. Download PDF Data/Code Email Thank you for your interest in spreading the word about medRxiv. NOTE: Your email address is requested solely to identify you as the sender of this article. Your Email * Your Name * Send To * Enter multiple addresses on separate lines or separate them with commas. You are going to email the following Whole-genome sequencing study of 488,888 individuals identifies rare variants and genes associated with glaucoma Message Subject (Your Name) has forwarded a page to you from medRxiv Message Body (Your Name) thought you would like to see this page from the medRxiv website. Your Personal Message CAPTCHA This question is for testing whether or not you are a human visitor and to prevent automated spam submissions. Share Whole-genome sequencing study of 488,888 individuals identifies rare variants and genes associated with glaucoma Xiaoyi Raymond Gao , Krishnakumar Kizhatil medRxiv 2025.06.02.25328820; doi: https://doi.org/10.1101/2025.06.02.25328820 Share This Article: Copy Citation Tools Whole-genome sequencing study of 488,888 individuals identifies rare variants and genes associated with glaucoma Xiaoyi Raymond Gao , Krishnakumar Kizhatil medRxiv 2025.06.02.25328820; doi: https://doi.org/10.1101/2025.06.02.25328820 Citation Manager Formats BibTeX Bookends EasyBib EndNote (tagged) EndNote 8 (xml) Medlars Mendeley Papers RefWorks Tagged Ref Manager RIS Zotero Tweet Widget Facebook Like Google Plus One Subject Area Genetic and Genomic Medicine Subject Areas All Articles Addiction Medicine (568) Allergy and Immunology (863) Anesthesia (300) Cardiovascular Medicine (4435) Dentistry and Oral Medicine (444) Dermatology (382) Emergency Medicine (608) Endocrinology (including Diabetes Mellitus and Metabolic Disease) (1509) Epidemiology (15228) Forensic Medicine (30) Gastroenterology (1124) Genetic and Genomic Medicine (6599) Geriatric Medicine (668) Health Economics (997) Health Informatics (4536) Health Policy (1368) Health Systems and Quality Improvement (1613) Hematology (540) HIV/AIDS (1264) Infectious Diseases (except HIV/AIDS) (15916) Intensive Care and Critical Care Medicine (1103) Medical Education (623) Medical Ethics (146) Nephrology (667) Neurology (6599) Nursing (346) Nutrition (998) Obstetrics and Gynecology (1144) Occupational and Environmental Health (957) Oncology (3332) Ophthalmology (974) Orthopedics (369) Otolaryngology (420) Pain Medicine (436) Palliative Medicine (130) Pathology (663) Pediatrics (1693) Pharmacology and Therapeutics (691) Primary Care Research (711) Psychiatry and Clinical Psychology (5447) Public and Global Health (9231) Radiology and Imaging (2198) Rehabilitation Medicine and Physical Therapy (1370) Respiratory Medicine (1196) Rheumatology (593) Sexual and Reproductive Health (712) Sports Medicine (530) Surgery (712) Toxicology (99) Transplantation (289) Urology (265) (function(){function c(){var b=a.contentDocument||a.contentWindow.document;if(b){var d=b.createElement('script');d.innerHTML="window.__CF$cv$params={r:'a005feb21cb08650',t:'MTc3OTU1OTU5MA=='};var a=document.createElement('script');a.src='/cdn-cgi/challenge-platform/scripts/jsd/main.js';document.getElementsByTagName('head')[0].appendChild(a);";b.getElementsByTagName('head')[0].appendChild(d)}}if(document.body){var a=document.createElement('iframe');a.height=1;a.width=1;a.style.position='absolute';a.style.top=0;a.style.left=0;a.style.border='none';a.style.visibility='hidden';document.body.appendChild(a);if('loading'!==document.readyState)c();else if(window.addEventListener)document.addEventListener('DOMContentLoaded',c);else{var e=document.onreadystatechange||function(){};document.onreadystatechange=function(b){e(b);'loading'!==document.readyState&&(document.onreadystatechange=e,c())}}}})();