Polygenic Risk and Rare Variants in Endotypes of Idiopathic Pulmonary Fibrosis

Polygenic Risk and Rare Variants in Endotypes of Idiopathic Pulmonary Fibrosis | 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 Polygenic Risk and Rare Variants in Endotypes of Idiopathic Pulmonary Fibrosis View ORCID Profile Anna Duckworth , Leigh Jackson , View ORCID Profile Harry Green , Atlas Khan , Chen Wang , View ORCID Profile Andrew Condescu , View ORCID Profile Gareth Hawkes , View ORCID Profile Imre Noth , Fernando J Martinez , View ORCID Profile Ganesh Raghu , View ORCID Profile Chad A. Newton , Matthew Moll , View ORCID Profile Michael Cho , View ORCID Profile Michael Gibbons , View ORCID Profile Chris J. Scotton , Columbia Genomics Consortium , View ORCID Profile Krzysztof Kiryluk , Christine Kim Garcia , View ORCID Profile David Zhang doi: https://doi.org/10.1101/2025.05.22.25328177 Anna Duckworth 1 Department of Biomedical and Clinical Sciences, University of Exeter , Exeter, UK 2 NIHR Exeter Biomedical Research Centre, University of Exeter , Exeter, UK 3 Academic Department of Respiratory Medicine, Royal Devon University Hospitals NHS Foundation Trust , Exeter, UK PhD Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Anna Duckworth Leigh Jackson 1 Department of Biomedical and Clinical Sciences, University of Exeter , Exeter, UK PhD Find this author on Google Scholar Find this author on PubMed Search for this author on this site Harry Green 1 Department of Biomedical and Clinical Sciences, University of Exeter , Exeter, UK PhD Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Harry Green Atlas Khan 10 Division of Pulmonary, Allergy, Critical Care, and Sleep Medicine, Department of Veterans Affairs , West Roxbury, MA PhD Find this author on Google Scholar Find this author on PubMed Search for this author on this site Chen Wang 10 Division of Pulmonary, Allergy, Critical Care, and Sleep Medicine, Department of Veterans Affairs , West Roxbury, MA PhD Find this author on Google Scholar Find this author on PubMed Search for this author on this site Andrew Condescu 1 Department of Biomedical and Clinical Sciences, University of Exeter , Exeter, UK Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Andrew Condescu Gareth Hawkes 1 Department of Biomedical and Clinical Sciences, University of Exeter , Exeter, UK PhD Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Gareth Hawkes Imre Noth 4 Division of Pulmonary and Critical Care, Department of Medicine, University of Virginia , Charlottesville, VA MD Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Imre Noth Fernando J Martinez 5 Division of Pulmonary, Allergy, and Critical Care, Department of Medicine, University of Massachusetts , Worcester, MA MD Find this author on Google Scholar Find this author on PubMed Search for this author on this site Ganesh Raghu 6 Division of Pulmonary, Critical Care, and Sleep Medicine, Department of Medicine, University of Washington Medical Center , Seattle, WA MD Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Ganesh Raghu Chad A. Newton 7 Division of Pulmonary and Critical Care, Department of Medicine, University of Texas Southwestern Medical Center , Dallas, TX MD, MSci Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Chad A. Newton Matthew Moll 8 Channing Division of Network Medicine, Brigham and Women’s Hospital, Harvard Medical School , Boston, MA 9 Division of Pulmonary and Critical Care Medicine, Department of Medicine , Mass General Brigham, Boston, MA 10 Division of Pulmonary, Allergy, Critical Care, and Sleep Medicine, Department of Veterans Affairs , West Roxbury, MA MD, MPH Find this author on Google Scholar Find this author on PubMed Search for this author on this site Michael Cho 8 Channing Division of Network Medicine, Brigham and Women’s Hospital, Harvard Medical School , Boston, MA 9 Division of Pulmonary and Critical Care Medicine, Department of Medicine , Mass General Brigham, Boston, MA MD, MPH Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Michael Cho Michael Gibbons 1 Department of Biomedical and Clinical Sciences, University of Exeter , Exeter, UK 2 NIHR Exeter Biomedical Research Centre, University of Exeter , Exeter, UK 3 Academic Department of Respiratory Medicine, Royal Devon University Hospitals NHS Foundation Trust , Exeter, UK MB, ChB, PhD Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Michael Gibbons Chris J. Scotton 1 Department of Biomedical and Clinical Sciences, University of Exeter , Exeter, UK 2 NIHR Exeter Biomedical Research Centre, University of Exeter , Exeter, UK 3 Academic Department of Respiratory Medicine, Royal Devon University Hospitals NHS Foundation Trust , Exeter, UK PhD Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Chris J. Scotton Krzysztof Kiryluk 11 Division of Nephrology, Department of Medicine, Columbia University Irving Medical Center , New York, NY MD, MS Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Krzysztof Kiryluk Christine Kim Garcia 12 Precision Medicine Institute, Columbia University Irving Medical Center , New York, NY 13 Division of Pulmonary , Allergy, and Critical Care, Department of Medicine, Columbia University Irving Medical Center , New York, NY MD, PhD Find this author on Google Scholar Find this author on PubMed Search for this author on this site David Zhang 13 Division of Pulmonary , Allergy, and Critical Care, Department of Medicine, Columbia University Irving Medical Center , New York, NY MD, MS Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for David Zhang For correspondence: dz2409{at}cumc.columbia.edu Abstract Full Text Info/History Metrics Supplementary material Data/Code Preview PDF Summary Background Idiopathic pulmonary fibrosis (IPF) and telomere length (TL) are both strongly linked to rare and common genetic variation. Shortened TL itself may be causal for IPF. Whether rare and common variants compete or cooperate to confer genetic risk of IPF uniformly is unknown. Methods We used whole genome sequencing (WGS) data from a discovery case-control cohort sequenced at Columbia (777 IPF, 2905 controls) and validated findings using WGS data from Trans-Omics for Precision Medicine (TOPMed, 1148 IPF, 5202 controls) and the UK Biobank (UKBB, 2739 IPF, 395331 controls). In all cohorts, we identified rare damaging variants in disease-associated genes and computed control-normalized polygenic risk scores for IPF (IPF-PRS) and telomere length (TL-PRS). Telomere length of blood leukocytes was measured using a qPCR assay for two cohorts. We determined the association of the MUC5B rs35705950 polymorphism, an IPF-PRS excluding MUC5B (IPF-PRS-no MUC5B ), and a TL-PRS with IPF risk in the overall cohort and in subgroups stratified by genetic endotypes (rare variant carriers, non-carriers stratified by TL cutoffs). We calculated cross-validated area under the receiver operator curve (AUC) and compared the liability of IPF explained by genetic variables. Findings We identified independent associations between IPF risk and rare variants, the MUC5B SNP, and both polygenic scores in the discovery cohort and replicated these findings in the TOPMed and UKBB cohorts. The adjusted effect size of the TL-PRS, which includes >180 SNPs not previously associated with IPF, was comparable to the IPF-PRS-no MUC5B in the discovery (ORTL-PRS 1.63 [95% CI 1.47, 1.81] vs. ORIPF-PRS 1.60 [1.44, 1.77]) and replication cohorts (TOPMed ORTL-PRS 1.47 [1.36, 1.59] vs. ORIPF-PRS 1.37 [1.25, 1.50]; UKBB ORTL-PRS 1.24 [1.19, 1.29] vs. ORIPF-PRS 1.25 [1.21, 1.30]). The TL-PRS incrementally improved disease prediction beyond known IPF common and rare genetic predictors and clinical variables in discovery (combined AUC: 0.89, pDelong = 0.006), TOPMed (combined AUC: 0.89, pDelong = 0.01), and UKBB cohorts (combined AUC: 0.77, pDelong = 0.03). Rare and common variants jointly contributed to genetic liability of IPF. The TL-PRS increased liability of IPF explained by 13% in the discovery cohort and 8% and 13% in the TOPMed and UKBB cohorts, respectively. In IPF subjects with damaging rare variants, the TL-PRS was consistently associated with disease risk whereas the IPF-PRS-no MUC5B was not. The TL-PRS also conferred nominally greater odds of disease risk than the IPF-PRS-no MUC5B in patients with shorter TL, in the discovery and UKBB cohorts. Together, 23-43% of IPF cases have damaging rare variants or telomeres <10 th percentile, where the TL-PRS represents a major unrecognized genetic risk factor. Interpretation Common and rare genetic variation confer context-specific genetic risk in IPF competitively and cooperatively. In contrast to known IPF common risk variants, the TL-PRS, which includes >180 genetic loci not previously associated with IPF, increases the risk of disease specifically in certain IPF endotypes. Polygenic risk from telomere-associated common variants is a key feature of IPF genetic heterogeneity. Funding National Institutes of Health (NIH), Medical Research Council (MRC), National Institute for Health and Care Research (NIHR) Evidence before this study We performed a search on PubMed for “common variants”, “rare variants”, “polygenic score”, “endotype”, and “IPF” on April 20 th , 2025, to identify integrated genetic studies of rare and common variants in IPF. We found no original articles that comprehensively examined common and rare IPF variants together. Nearly all articles analyzed common or rare variants in isolation; one article included both common and rare variant analyses but reported results separately without studying their combined effects. We identified numerous reviews that discuss or conceptualize the relative contributions of rare and common genetic risk to IPF risk; no studies provided or cited empiric data. Although “IPF endotypes” have been defined using transcriptomics and proteomics, we did not find any articles that utilized this terminology based on genetic factors, although several studies distinguish IPF with rare variants or telomere length below 10 th percentile. Added value of this study We describe the first comprehensive survey of common and rare risk variants together in IPF and identify subtype-specific genetic risk factors that substantially improve genetic explanation and disease prediction. We uncover complex relationships between polygenic factors and rare variants, including preliminary evidence of polygenic modifiers in IPF carriers of rare damaging variants that might serve as an explanation for incomplete penetrance. Genetic studies in IPF have been limited by sample size leading to “missing heritability”. We demonstrate value in leveraging large-scale genetic studies of causal molecular traits like telomere length to overcome these limitations and improve genetic understanding of IPF. These telomere-associated common variants are context-specific risk factors in certain endotypes, highlighting previously unrecognized genetic heterogeneity that will be important for future discovery of novel, reproducible genetic risk factors in IPF. Implications of all the available evidence A genetic basis for disease heterogeneity allows for research that focuses on relevant endotypes instead of “all-comer” disease and advances precision medicine approaches to IPF. Polygenic factors that can modify the effects of a high-risk rare variant represent a target for understanding disease-modifying pathways in IPF. Introduction Idiopathic pulmonary fibrosis (IPF) is a lethal, progressive, fibrosing disorder with no known cure. Studies have identified numerous rare and common genetic influences on the risk of developing IPF including those that affect telomere biology 1 – 6 . Telomeres are hexamer repeats which serve as protective caps at the end of chromosomes and naturally shorten with age or cellular replication 7 . IPF risk variants in telomere maintenance genes, including TERT, TERC, and RTEL1 , cause telomere shortening and have been identified in both genome-wide association studies (GWAS) of common risk variants 8 , 9 as well as exome sequencing studies 2 , 10 , 11 . Large-scale GWAS of telomere length in healthy individuals have similarly yielded telomere-associated common variants 12 , 13 . Our previous Mendelian randomization study utilized these telomere-associated SNPs to implicate telomere shortening as being causal for IPF 4 . About 20-30% of IPF patients have short telomere length below the 10 th percentile without harboring a rare damaging telomere-gene variant; polygenic risk from telomere-associated SNPs may account for unexplained short telomere length in these cases 6 . Shortened telomere length itself, with or without a rare variant, is linked to worse survival 14 – 16 , rapid progression 6 , 17 , adverse response to immunosuppression 18 – 20 , and complications after transplant 21 . IPF subjects with rare damaging telomere-gene variants or unexplained short telomeres may represent distinct endotypes of disease at higher clinical risk of worse outcomes. Prior studies have begun to uncover genetic heterogeneity in IPF related to the common MUC5B promoter polymorphism 22 , other common risk variants and rare mutations 6 , 14 , 23 . Despite these advances, the unaccounted genetic risk in IPF is sizable. Existing studies demonstrate that 75% of cases with familial IPF do not have a genetic diagnosis 6 , 24 and that known common risk variants explain only about 10% of disease liability in the general population 25 . However, these studies utilize all-comer IPF cohorts and focus on rare or common variants in isolation, obfuscating the potential role of gene interaction and disease heterogeneity in genetic risk. Comprehensive deconvolution of these factors may help resolve missing heritability in IPF. In this study, we perform the first integrated assessment of rare damaging variants and common risk variants in IPF by stratifying on heterogenous endotypes of disease. We leverage existing large-scale genetic studies of telomere length heritability to identify novel polygenic risk factors that increase the explained genetic liability of IPF and significantly improve disease prediction. We uncover a complex relationship between common and rare variants in IPF that drives genetic heterogeneity. Our findings support an endotype-aware approach to enhancing genetic discovery in future IPF studies. Methods Please see the online supplement for detailed methods. Patient Cohorts The Columbia discovery cohort with IPF cases and controls has been described previously 6 , 11 . The institutional review board at Columbia University Medical Center (AAAS0753, AAAS7495, and AAAP0052) approved this study. Replication cohorts with IPF cases and controls from the Trans-Omics for Precision Medicine (TOPMed) program 26 and the UK Biobank (UKBB) 27 were used. For the TOPMed cohort, individuals with IPF (phs001607) were classified as cases, and participants of the MESA (phs001416) and Framingham Heart (phs000974) studies were classified as controls. For the UK Biobank cohort, International Classification of Diseases (ICD10) code J84.1 was used to define IPF cases, and exclusion of all J84 codes defined controls. Genome Sequencing, Rare Variant Definitions, and Genomic Analysis Whole genome sequencing (WGS) for the Columbia cohort was performed according to standard protocols on Illumina’s NovaSeq 6000 platform with raw sequencing reads aligned to the hg19 reference genome. WGS data from the discovery cohort and the TOPMed and UK Biobank cohorts were similarly aligned, called and joint genotyped on their respective pipelines. Rare qualifying variants in disease-associated genes predicted to be deleterious were identified using in silico tools as previously described 6 , 11 . Cases and controls within each cohort were pruned for relatedness using KING 28 . Principal components were computed using plink 29 to account for population substructure. Genetic ancestry was inferred using peddy 30 using a model trained on 1000 Genomes Project 31 data. Polygenic Risk Scores We used a pruning and thresholding approach to include autosomal risk variants identified from the summary statistics of GWAS studies that exceeded genome-wide significance to compute polygenic risk scores for IPF and telomere length. We used independent published GWAS studies 9 , 13 and identified 16 SNPs related to IPF ( Table S1 ) and 190 SNPs related to telomere length ( Table S2 ) to compute weighted scores as previously described 6 . Three genome-wide significant loci were associated with both IPF and telomere length (Figure S1, Table S3). Given its large effect, we studied the MUC5B rs35705950 promoter polymorphism separately from polygenic scores as previously described 32 , 33 . For primary analysis, we defined an IPF polygenic risk score using 12 SNPs that excluded the three overlapping telomere-associated SNPs and the MUC5B SNP, hereafter termed the “IPF-PRS-no MUC5B ”. We defined a telomere length polygenic score using 190 SNPs ( Table S2 ), hereafter termed the “TL-PRS”. For each cohort, polygenic risk scores (PRS) were normalized to controls and represented as z-scores. For concordance with the IPF-PRS-no MUC5B , we negatively inverted the TL-PRS SNP betas so that a higher polygenic score predicts lower telomere length and increased risk of IPF. For sensitivity analysis we examined multiple alternative polygenic scores (Table S4) including an IPF polygenic score that retains three overlapping telomere-associated SNPs and a telomere length polygenic score that excludes these. We also tested a telomere length polygenic score from an independent GWAS study 12 and an alternative IPF polygenic score using LASSO regression excluding a 500 kb region flanking the MUC5B rs35705950 polymorphism 33 . Since both GWAS studies of IPF and telomere length included only European subjects, we also performed sensitivity analyses on European-only and non-European subjects. Telomere Length Measurement For the Columbia cohort and the UK Biobank, peripheral leukocyte telomere length was measured via qPCR as previously described 34 , 35 . In both cohorts, genomic DNA was isolated from blood leukocytes at time of study enrollment and quality control measures were performed. Age-adjusted percentiles were determined using a multi-ancestry panel of control individuals for the Columbia cohort. For the UK Biobank, internal age-adjusted percentiles were computed using measured ancestry-specific telomere length vigintiles across 5-year age-bands due to differences by race and ethnicity 35 . Genetic Liability To estimate the proportion of disease risk explained by genetic variables, we utilized the liability threshold model which conceptually transforms the observed probability of a binary trait to a continuous liability scale whereby exceeding a critical threshold results in development of that trait 36 . We estimated the genetic liability explained in the general population across a range of disease prevalences 37 , 38 for each genetic predictor and each IPF endotype. We estimated the proportion of variance explained by each genetic predictor by calculating the correlation attributed to the predictor in a linear model and comparing full and reduced models adjusted for other genetic predictors, age, sex, and principal components of ancestry. We converted the proportion of variance explained to a liability scale accounting for ascertainment in the case-control cohort across a range of observed prevalences of IPF in the general population as previously described 39 . Statistics We performed logistic regression to assess the association of genetic variables with IPF diagnosis in each cohort adjusting for age, sex, and principal components of ancestry. We selected five principal components based on visualization of flattening of variance explained on scree plot (Figure S2) . We assessed gene interaction by assessing the significance of pair-wise interaction terms between genetic variables. To assess disease prediction, we calculated area under the receiver operating curve (AUC) with 10-fold cross-validation using R packages pROC and caret . Comparison of AUCs was performed using DeLong’s test. Comparisons of non-parametric continuous data were performed using Wilcoxon rank sum test for two groups or Kruskal-Wallis test for multiple groups. For meta-analyses we used a random-effects model using R package metafor . To estimate genetic correlation between traits, we performed cross-trait linkage disequilibrium (LD) score regression 40 using published GWAS summary statistics. To minimize bias from population stratification, we focused on studies of individuals of European ancestry. We used LD scores estimated from the 1000 Genomes Project 31 European reference panel for regression weights. All p-values less than 0.05 were considered significant with Bonferroni correction applied for multiple comparisons. Statistical analyses were performed using R statistical analysis software, version 4.4.0 ( www.r-project.org ). Role of the funding source The study sponsor had no role in study design or in data collection, analysis, and interpretation. Results Subject characteristics The discovery cohort included 777 unrelated IPF cases and 2905 non-IPF controls as previously described 11 . Case-control cohorts from TOPMed and the UK Biobank (UKBB) were used for replication. The TOPMed cohort included 1148 unrelated IPF cases and 5202 unrelated, population-based controls from the MESA and Framingham Heart studies as previously described 11 . The UK Biobank cohort included 2739 unrelated IPF cases and 395,331 unrelated controls ( Figure 1A ) . The IPF cohorts were older (median age 64-67), male-predominant (61-72%), and mostly of European ancestry (84-96%) (Table S6) . Download figure Open in new tab Figure 1. Study cohorts and proportion of IPF endotypes. A. Study flow diagram of IPF cohorts with schematic accounting of cases and controls. B. Relative proportion of each IPF cohort classified by endotype. Rare variant carriers include patients with inherited rare damaging mutations in IPF-associated genes including TERT, TERC, PARN, RTEL1, DKC1, TINF2, NAF1, SFTPC, SFTPA1/2, and KIF15 . Peripheral blood telomere length measured by qPCR and presented as age-adjusted percentiles. Individuals without rare variants were subdivided based on telomere length: 50 th percentile. Telomere length percentiles are not available for the TOPMed cohort. Abbreviations: WGS, whole genome sequencing; UTSW, University of Texas Southwestern; FPF, familial pulmonary fibrosis; IPFnet, IPF Clinical Research Network; MESA, Multi-Ethnic Study of Atherosclerosis; TL, telomere length. Rare variants, telomere length, and endotype classification We identified carriers of rare deleterious qualifying variants in IPF-associated genes ( TERT, TERC, RTEL1, PARN, DKC1, TINF2, NAF1, ZCCHC8, SFTPC, SFPTA1/2 , and KIF15 ) as previously described 6 in all cohorts. In total we identified 94 (12%) carriers in the Columbia cohort, 143 (12%) carriers in the TOPMed cohort, and 108 (3.9%) in the UKBB cohort ( Table S7 ). Telomere length measurement was available for the Columbia and UKBB cohorts. For these cohorts, we subdivided IPF cases into endotypes including rare variant carriers, and non-carriers stratified by TL (50 th percentile) ( Figure 1B , Table S8 ). Most IPF non-carriers had TL below average for age; rare variant carriers and non-carriers with TL <10 th percentile represented 23-43% of the IPF cases. Association of polygenic scores with IPF We found a significant difference in the distribution of all PRS between IPF and controls (all p<0.0001) in the Columbia, TOPMed, and UKBB cohorts ( Figure S3 ). There was heterogeneity in the TL-PRS amongst IPF cases with different telomere lengths (Kruskal-Wallis p = 5.9×10 −5 , Figure S6 ). In multivariable analysis, we find significant independent associations between IPF risk and rare variants (OR 12.0, 95% CI 7.57-19.5, p=1.0×10 −24 ), MUC5B SNP (OR 2.00, 95% CI 1.85-2.15, p=4.0×10 −72 ), the IPF-PRS-no MUC5B (OR 1.60, 95% CI 1.44-1.77, p=9.4×10 −19 ), and the TL-PRS (OR 1.63, 95% CI 1.47-1.81, p=5.5×10 −21 ) adjusting for age, sex, genetic variables, and principal components of ancestry ( Table 1 ). We did not find consistent evidence of a significant pair-wise interaction term between genetic variables ( Figure S7 ). In the discovery cohort, AUC analysis demonstrated improved disease prediction when genetic variables were added to a clinical model of age and sex ( Figure 2A-B ). The inclusion of the TL-PRS in a combined model with clinical variables and common and rare variables significantly improved disease prediction in the discovery cohort (AUC: 0.88 to 0.89, DeLong’s p = 0.006). Analysis in TOPMed and UKBB replication cohorts affirmed that inclusion of clinical variables with all rare and common genetic variables, including the TL-PRS, led to the best prediction of IPF (TOPMed combined AUC = 0.89, UKBB combined AUC = 0.77) ( Table 1 , Figure 2C-F ). Download figure Open in new tab Figure 2. Receiver operator curves (ROC) of clinical and genetic predictors of IPF. Data shown using (A, B) Columbia cohort, (C, D) TOPMed cohort, and (E, F) the UK Biobank. Area under ROC calculated with 10-fold cross validation. All models with genetic predictors include 5 PC of ancestry. Clinical model includes age and sex. (A, C, E) ROC curves combining common variant polygenic risk scores and clinical predictors. In all cohorts, DeLong’s test demonstrates significant improvement in prediction with the addition of individual genetic predictors to clinical predictors (all p < 2.0 x 10 − 16 ). (B, D, F) A model combining common and rare genetic variables with clinical predictors results in the best disease prediction (Columbia AUC 0.89, TOPMed AUC 0.89, UKBB AUC 0.77). The TL-PRS incrementally improves disease prediction beyond known IPF common and rare variants and clinical predictors (Columbia pDelong = 0.006; TOPMed pDelong = 0.01, UKBB pDelong = 0.03). MUC5B SNP, rs35705950 polymorphism; IPF-PRS-no MUC5B, IPF polygenic risk score excluding MUC5B SNP and overlapping telomere-associated loci; TL-PRS, telomere length polygenic score. View this table: View inline View popup Download powerpoint Table 1. Associations between polygenic scores and IPF in multiple cohorts Endotype-specific polygenic effects on IPF risk Since we found independent effects from polygenic scores, we explored their relevance to different IPF endotypes, including rare variants carriers and non-carriers with different telomere lengths. In the discovery cohort ( Figure 3A ), the MUC5B polymorphism was similarly associated with IPF across all endotypes (overall OR MUC5B 2.02, 95% CI [1.88, 2.17]). The IPF-PRS-no MUC5B was associated with IPF risk amongst non-carriers (ORIPF-PRS 1.69, 95% CI [1.54, 1.86]) but not amongst rare variant carriers (ORIPF-PRS 1.23, 95% CI 1.00, 1.51]). The TL-PRS was associated with IPF risk in rare variant carriers and non-carriers, with the highest odds ratio in the TL 50 th percentile group (ORTL-PRS 1.23, 95% CI [1.06, 1.44]). In sensitivity analyses, the use of alternative polygenic scores, including an IPF-PRS that retains the overlapping telomere-associated loci, yielded similar endotype-specific associations ( Figure S8 ). Download figure Open in new tab Figure 3. Associations of genetic predictors and polygenic scores with IPF risk across endotypes of disease. Odds ratios and 95% confidence intervals shown using data from (A) Columbia cohort on left and (B) UK Biobank on right. All associations adjusted for age, sex and 5 PCs of ancestry. Genetic predictors are displayed as control-normalized z-transformed scores; each one unit increase in OR represents one standard deviation increase in genetic predictor. The top panels show a similar effect of the MUC5B polymorphism on IPF risk across IPF endotypes. The middle panels show a diminished effect of the IPF-PRS-no MUC5B on disease risk in rare variant carriers. The bottom panels show heterogenous effects of the TL-PRS on IPF risk in rare variant carriers and non-carriers with various telomere lengths. For both the Columbia cohort and the UK Biobank, the TL-PRS had the greatest effect in non-carriers with telomere lengths <10 th percentile. Replication analysis in the TOPMed and UKBB cohorts confirmed endotype-specific genetic risk factors. The effect of IPF-PRS-no MUC5B on disease risk was similarly attenuated in rare variant carriers vs non-carriers in the TOPMed replication cohort (carriers ORIPF-PRS 1.30, 95% CI [1.08, 1.57]) ( Figure S9 ), and in the UKBB replication cohort (carriers ORIPF-PRS 1.07, 95% CI [0.88, 1.30]) ( Figure 3B ). The TL-PRS had a similarly heterogenous effect on disease risk in non-carriers in the UKBB with significant associations in those with shortest TL 50 th percentile (ORTL-PRS 0.95, 95% CI [0.93, 1.06]). Overall, the TL-PRS was consistently and independently associated with IPF risk in rare variant carriers and non-carriers with TL <10 th , between 10-24 th , and between 25-49 th percentiles in discovery and UKBB cohorts, representing 65-75% of cases. To understand the portability of these polygenic scores across ancestry, we performed a stratified analysis based on European ancestry. In European individuals, all associations remained consistent (Figure S10). In non-European individuals, the MUC5B SNP associations remained consistent across cohorts in IPF overall, but the IPF-PRS-no MUC5B and TL-PRS associations were not consistent although the precision of estimates was limited by small sample size ( Figure S11 ). Proportion of liability explained by common and rare variants To conceptualize the relative contributions from each genetic variable, we compared the proportion of IPF risk conferred using liability estimates 36 across a range of reported IPF prevalences 37 in the general population as well as in individuals older than 65 38 ( Figure 4A ) . Download figure Open in new tab Figure 4. Liability of developing IPF in the general population explained by known rare and common genetic risk factors. Stacked bar plots demonstrate estimated genetic liability explained by rare and common variant risk factors. (A) Using the Columbia cohort, proportion of liability estimated by each genetic predictor is shown assuming a range of observed prevalences of IPF. There is a dominant effect of rare variants on liability explained in IPF rare variant carriers. The MUC5B SNP explains the most liability amongst IPF non-carriers. The TL-PRS accounts for more liability in non-carriers with shorter telomere lengths than those with longer telomere length. Data from the TOPMed and UK Biobank cohorts (B, C, D) are compared to the Columbia cohort assuming a disease prevalence of 63 in 100,000. Panel B shows the liability explained by common variants in rare variant carriers; in all cohorts the TL-PRS explains a greater proportion of genetic liability than the IPF-PRS-no MUC5B . Panel C shows the liability explained by common variants in IPF non-carriers with telomere length <10 th percentile; in both cohorts the TL-PRS explains more liability than the IPF-PRS-no MUC5B . Panel D shows liability explained by all genetic variables in IPF overall. Across multiple cohorts, rare variants and the TL-PRS together improve the genetic liability explained by ∼30%. For IPF rare variant carriers, we reported the liability explained by rare variants and polygenic factors separately due to potential collinearity between genetic factors in this group. Rare variants alone explained most of the liability (40-60%) far exceeding polygenic factors in rare variant carriers. When comparing polygenic risk factors in rare variant carriers, the TL-PRS explained more disease liability than the IPF-PRS-no MUC5B (1.1-2.0% vs 0.2-0.4%). Amongst IPF subjects without a rare damaging variant, the MUC5B SNP explained a major fraction of liability. The TL-PRS explained more liability than the IPF-PRS-no MUC5B , especially for non-carriers with TL <10 th percentile (1.8-3.6% vs 1.0-2.0%), and those with TL 10-24 th percentile (1.2-2.3% vs 0.9-1.8%). The endotype-specific genetic liability explained by TL-PRS persisted in sensitivity analyses using alternative polygenic scores and in non-Europeans (Figures S13, S14, and S15) . Across all IPF cases, we identified the overall liability explained by MUC5B polymorphism (3.1-6.9%), rare variants (0.9-2.1%), the IPF-PRS-no MUC5B (0.5-1.2%), and the TL-PRS (0.6-1.3%). The TL-PRS, comprising >180 SNPs not previously associated with IPF, increased the genetic liability of IPF explained overall by 13%. We also observed similar overall and endotype-specific trends in genetic liability explained in the TOPMed and UKBB replication cohorts ( Figure 4B-D ). Genetic correlation To assess the genetic overlap between IPF and telomere length in the context of other epidemiologically-associated traits, we estimated pair-wise genetic correlation amongst IPF 9 , telomere length 13 , smoking 41 , GERD 42 , monocyte count 43 , rheumatoid arthritis 44 , and forced vital capacity (FVC) 45 utilizing summary statistics from large-scale GWAS studies for all traits ( Figure S16, S17 ). Telomere length was the only trait with significant genetic correlation with IPF after correcting for multiple comparison testing (r=-0.35, p=3.6×10 −6 ). Discussion Our study utilized three independent cohorts comprising over 4,500 IPF cases and 400,000 controls to systematically characterize the interplay of rare and common genetic risk factors in genetic endotypes of IPF ( Figure 5 ) . We observed outsized effects from polygenic risk of telomere shortening, especially in 23-43% of IPF cases with a damaging rare variant or very short telomere length. Our study highlights the utility of understanding genetic heterogeneity for uncovering novel IPF genetic risk factors. Download figure Open in new tab Figure 5. Graphical summary of study. Genetic association of rare and common variants stratified by genetic endotype performed across three independent case-control cohorts of IPF comprising >4,500 IPF cases and >400,000 controls. The MUC5B polymorphism ( yellow oval ), short telomere risk SNPs ( green circle ), IPF risk SNPs ( purple circle ), and rare variants ( red box ) were all independently associated with risk of IPF in all cohorts. Three genetic endotypes of IPF were identified including rare variant carriers (4-12%), non-carriers with unexplained short telomere length (19-31%), and other non-carriers (57-78%). Endotype-specific combinations of genetic risk factors were identified. Short telomere risk SNPs ( green circle ) include >180 SNPs not previously associated with IPF and contribute greater proportion of genetic risk than IPF risk SNPs ( purple circle ) in IPF with unexplained short telomeres or rare variants. Accounting for all common and rare genetic risk factors improved disease prediction in all cohorts and explained more liability of disease. Studying the genetic basis of associated molecular phenotypes can substantially improve mechanistic understanding of diseases and lead to therapies that focus on treating causal traits. Successful examples of this approach include genetic studies of low-density lipoprotein (LDL) cholesterol levels for coronary artery disease 46 , fetal hemoglobin levels for hemoglobinopathies 47 , or serum IgA levels for IgA nephropathy 48 . Similarly, our approach leveraged telomere length GWAS studies involving hundreds of thousands of participants to identify novel IPF genetic associations, capitalizing on robust polygenic scores from well-powered analyses. Genetic studies of molecular traits like telomere length often have larger sample sizes and yield more informative genetic findings compared to studies of a rare diagnosis like IPF. Alternative polygenic scores using thousands of SNPs for IPF risk 33 and 20 SNPs 12 for telomere length heritability affirmed the value of a well-powered polygenic score and supported our primary conclusions. We highlight a complex relationship between polygenic risk factors and rare variants in IPF. Non- MUC5B IPF common risk variants have diminished effect in carriers of rare damaging variants, suggesting that these two genetic variables “compete” to confer risk of IPF. In contrast, the MUC5B SNP and telomere-associated common variants “cooperate” with rare risk variants. Most of these rare variants are also found in telomere maintenance genes, suggesting that rare and common variants that govern telomere length confer IPF risk additively. Rare telomere-gene variants confer upwards of 40-fold increased odds of IPF and are linked to monogenic forms of disease 10 , 11 but feature variable penetrance. Studies of familial pulmonary fibrosis kindreds often identify rare variant carriers who are asymptomatic 24 and have found that the presence of the MUC5B SNP is linked to radiographic evidence of early fibrotic lung disease 49 . Polygenic modification has also been proposed to explain incomplete penetrance in other monogenic disorders including cardiovascular disease 50 , hereditary cancer 50 , metabolic disease 51 , and chronic kidney disease 52 . Our findings pave the way to study polygenic modifiers as an explanation for variable penetrance in families of IPF rare variant carriers. Historically, the genetic link between telomere shortening and IPF has been attributed to rare variants 1 – 3 , 5 , 53 . We find that telomere-associated common variants can explain a substantial portion of IPF genetic risk as well. In IPF patients with unexplained short telomere length, the polygenic risks of IPF and of telomere shortening converge, highlighting a parallel genetic pathway for future studies of disease mechanism of this specific endotype. Furthermore, telomere length testing and genetic testing for IPF are both available clinically 54 , allowing for potential precision medicine based clinical care in the future. Interestingly, telomere-associated common variants confer risk of IPF even amongst those with telomere lengths above the 10 th percentile, up to the 50 th percentile. A spectrum of telomere-related polygenic risk appears to be relevant in the 65-75% of IPF patients with telomere lengths shorter than expected for a given age. These genetic influences on telomere length are likely independent of epigenetic modification of telomere “set-length” itself 55 by which aging and environmental exposures lead to attrition 7 , 56 – 58 . Given the abundant evidence linking rare variants or short telomere lengths to reduced survival in IPF 16 , 59 , these findings suggest that rare and common telomere-associated variants not only underlie genetic heterogeneity, but also drive heterogeneity of disease outcomes. We find that the overall genetic architecture of IPF is significantly correlated with that of telomere length in contrast to other epidemiologically associated traits. This parallel analysis utilized existing GWAS summary statistics to examine the genetic overlap between these traits and complements our prior Mendelian randomization study implicating telomere shortening as causal for IPF 4 . While genome-wide significant loci from GWAS studies of IPF and telomere length overlap to a minimal degree, the extent of genetic correlation between these two traits suggest that many other variants below significance threshold are also overlapping. Our findings suggest that the extent of this overlap may be related to genetic heterogeneity of the IPF GWAS cohort. Rare variant carriers, which are enriched in familial pulmonary fibrosis, have attenuated effects from some common variants on disease risk. As such, a sporadic IPF cohort without rare variant carriers could be enriched for polygenic discovery. Similarly, a hypothetical GWAS analysis of an IPF cohort without short telomeres would likely yield different results from an IPF cohort in which all patients have very short telomere lengths. Notably, a previous IPF GWAS 60 did not identify the genetic locus in TERT whereas a similarly powered contemporaneous GWAS did 61 . Imbalance of genetic endotypes may have led to discrepant results in these studies. Our findings highlight the importance of understanding genetic heterogeneity when analyzing genetic association in all-comer IPF cohorts. Our study has several limitations. Due to the variability in clinical phenotyping of cohorts, some relevant risk factors were not uniformly available including smoking, environmental exposures, and other comorbid conditions. Telomere length genetically correlates with some of these risk factors. Confounding or effect modification from non-genetic factors is not definitively excluded and the impact of gene by environment will require further investigation. Since all major GWAS studies on IPF focused on European ancestry individuals, polygenic scores and associations may not be portable across non-European ancestries. Our sensitivity analyses using non-European cases and controls were limited by sample size and suggested a consistent but non-significant trend for some associations. Future studies with diverse IPF cohorts will be needed to identify pan-ancestry genetic effects. The UKBB IPF cases were relatively depleted of TERT and other rare variants compared to clinical cohorts. This may be related to enrollment bias in the UKBB which preferentially recruited healthy older individuals, potentially excluding some individuals with pathogenic rare variants who tend to have younger onset of severe disease. Clinical IPF cohorts may also be biased towards enrolling those with a genetic etiology; a recent analysis of the US-wide Pulmonary Fibrosis Foundation Registry revealed a comparable 7% prevalence of rare variants in IPF cases using the same definition 23 . We grouped all rare variant carriers together due to limited sample size. As such, we were unable to draw definitive conclusions for specific genes, although we observed consistent associations in the most well-represented genes. In conclusion, polygenic background and rare variation contribute to genetic risk of IPF both independently and in tandem. While attenuated, polygenic modifiers of disease risk exist even amongst IPF carriers of rare damaging variants. We find that genetically predicted short telomeres intersects with IPF risk not only in the purview of damaging rare variants, but also in the context of polygenic risk in certain endotypes. Accounting for these novel genetic risk factors both improves disease prediction and explains additional genetic liability. Taken together, our findings underscore the importance of understanding IPF heterogeneity from rare and common genetic influences that may be relevant for future studies. Contributors DZ conceived the project and designed the study. DZ, AD, LJ, HG, AC, and GH performed the analysis. AK, CW, CKG and KK generated genetic data for the discovery cohort. CKG, IN, FJM, GR, CAN, and the Columbia Genomics Consortium enrolled and contributed samples for the discovery cohort. MM and MC provided analytic support for alternative polygenic scores. MG and CJS provided supervisory support to AD and facilitated access to UK Biobank. DZ, AD, and CKG interpreted the results and drafted the manuscript. Declaration of interests AD reports grant support from the MRC and NIHR. LJ reports grant support from the MRC and NIHR. HG reports grant support from the NIHR. AC reports grant support from the NIHR. GH reports grant support from the MRC and Innovative Health Initiative Joint Undertaking. CN reports grant support from the NIH, editorial board participation for CHEST, committee participation for the American Thoracic Society, working group participation for the Pulmonary Fibrosis Foundation, and consulting fees from Boehringer Ingelheim and Medpace, Inc, unrelated to current work. IN reports grant support from the NIH and Veracyte, and consulting fees for Boehringer Ingelheim and Sanofi, unrelated to current work. FJM reports grant support from the NIH, other support from Boehringer Ingelheim, Biogen, Bristol-Myers Squibb, DevPro, GlaxoSmithKline, Nitto, Promedior/Roche, Vicore, Chiesi, and consulting fees from AstraZeneca, Boehringer Ingelheim, Bristol-Myers Squibb, Chiesi, Endeavor, Excalibur, GlaxoSmithKline, Lung Therapeutics/Aileron, Novartis, RS Biotherapeutics, Two XR, Hoffman Laroche, participation in data safety monitoring board for Boehringer Ingelh, Endeavor Biomedicine, and Pliant unrelated to current work. MM reports grant support from the NIH and consulting fees from 2ndMD, TheaHealth, Axon Advisors, Dialectica, Sanofi, and Verona Pharma, unrelated to the current work. MC reports grant support from the NIH and Bayer and consulting fees from Apogee and BMS, unrelated to the current work. KK reports grant support from the NIH and the IgA Nephropathy Foundation and consulting fees from HIBIO, unrelated to current work. CKG reports grant support from the NIH and the Department of Defense; research support from AstraZeneca; and equity or stocks from Rejuvenation Technologies. DZ reports grant support from the NIH and the Francis Family Foundation, committee participation for the American Thoracic Society, and consulting fees from Boehringer Ingelheim. AK, CW, MG, GR, and CJS declare no competing interests. Data sharing Genotype data for discovery cohort allowable under consent is available in the Database of Genotypes and Phenotypes (dbGAP) under the following projects: Pulmonary Fibrosis and Telomerase Dysfunction, phs002692; Genomics of Glomerular Disorders, phs002480; Genomic Translation for ALS Care (GTAC), phs02973. The TOPMed cohort genetic and phenotypic data are available under dbGAP (Multi-ethnic Study of Atherosclerosis, phs0001416; Framingham Heart Study, phs000974; Idiopathic Pulmonary Fibrosis, phs001607). Genetic and phenotypic data from the UK Biobank is available through applications to the UK Biobank. Data Availability Genotype data for discovery cohort allowable under consent is available in the Database of Genotypes and Phenotypes (dbGAP) under the following projects: Pulmonary Fibrosis and Telomerase Dysfunction, phs002692; Genomics of Glomerular Disorders, phs002480; Genomic Translation for ALS Care (GTAC), phs02973. The TOPMed cohort genetic and phenotypic data are available under dbGAP (Multi-ethnic Study of Atherosclerosis, phs0001416; Framingham Heart Study, phs000974; Idiopathic Pulmonary Fibrosis, phs001607). Genetic and phenotypic data from the UK Biobank is available through applications to the UK Biobank. Acknowledgements The authors thank the research participants for their participation and enrollment in study cohorts. The authors thank the investigators and institutions who supported the NHLBI cohorts (IPF, MESA, and the Framingham Heart Study). The authors would like to acknowledge the Collaborative Group of Genetic Studies of IPF for access to summary statistics of prior IPF GWAS. The research utilized data from the UK Biobank resource carried out under UK Biobank application number 103356. UK Biobank protocols were approved by the National Research Ethics Service Committee. This study was funded by the National Institute for Health and Care Research Exeter Biomedical Research Centre. The views expressed are those of the author(s) and not necessarily those of the NIHR or the Department of Health and Social Care. The Columbia Genomics Consortium includes data and investigators involved with the following projects: Cure Glomerulonephropathy (CureGN, www.cureGN.org ; Ali Gharavi, Krzysztof Kiryluk, and Simone Sanna-Cherchi), non-cureGN (Ali Gharavi, Krzysztof Kiryluk, Simone Sanna-Cherchi), Genomic Translation for ALS Care (GTAC; Matthew Harms and David Goldstein), and Columbia University Biobank cohorts for COVID-19 (Krzysztof Kiryluk, Muredach Reilly, Soumitra Sengupta, Eldad Hod, Wendy Chung, Jennifer Williamson), atopic disease (Joshua Milner and Jordan Orange), prenatal disease (Ronald Wapner), and diagnostic sequencing (Muredach Reilly) The “Genomics of Glomerular Disorders” project (dbGAP phs002480) includes genetic data for the participants of the CureGN Study ( www.curegn.org ) supported by the National Institute of Health (NIH)/National Institute of Diabetes and Digestive and Kidney Diseases (NIDDK). The sequence data was generated in collaboration with AstraZeneca as part of the High Impact, Interdisciplinary Science Grant RC2-DK116690 from the NIH/NIDDK. The “Genomic Translation for ALS Care” project (dbGAP phs020973) includes the following investigators and funding sources: PI Matthew Harms (Columbia University) and site investigators Stanley Appel (Houston Methodist); Robert Baloh (Cedars Sinai); Richard Bedlack (Duke Univ); Siddharthan Chandran (Univ. of Edinburgh); Laura Foster (Univ of Colorado); Summer Gibson, (Univ Utah); David Goldstein (Columbia University); Stephen A. Goutman (Univ of Michigan); Chafic Karam (Oregon Health Sciences); David Lacomis (Univ. of Pittsburgh); George Manousakis (Univ. of Minnesota); Timothy Miller (Washington Univ St. Louis); Cristiane Moreno (Columbia University); Suvankar Pal (Univ. of Edinburgh); Dhruv Sareen (Cedars Sinai); Zachary Simmons (Penn State Hershey); Leo Wang (Univ of Washington). Funding was provided by the ALS Association (National); ALS Association (Greater New York Chapter), and Biogen. The “Pulmonary Fibrosis and Telomerase Dysfunction” project (dbGAP phs002692) was supported by grant HL093096 from NIH/NHLBI to Christine Kim Garcia (Columbia University) with assistance from David Goldstein (Columbia University) and Chad A. Newton (UT Southwestern). Footnotes Corrected Figures 2 and 3 which were submitted in reverse References 1. ↵ Tsakiri KD , Cronkhite JT , Kuan PJ , et al. Adult-onset pulmonary fibrosis caused by mutations in telomerase . Proc Natl Acad Sci U S A 2007 ; 104 ( 18 ): 7552 – 7 . DOI: 10.1073/pnas.0701009104 . OpenUrl Abstract / FREE Full Text 2. ↵ Stuart BD , Choi J , Zaidi S , et al. Exome sequencing links mutations in PARN and RTEL1 with familial pulmonary fibrosis and telomere shortening . Nat Genet 2015 ; 47 ( 5 ): 512 – 7 . DOI: 10.1038/ng.3278 . OpenUrl CrossRef PubMed 3. ↵ Armanios MY , Chen JJ , Cogan JD , et al. Telomerase mutations in families with idiopathic pulmonary fibrosis . N Engl J Med 2007 ; 356 ( 13 ): 1317 – 26 . DOI: 10.1056/NEJMoa066157 . OpenUrl CrossRef PubMed Web of Science 4. ↵ Duckworth A , Gibbons MA , Allen RJ , et al. Telomere length and risk of idiopathic pulmonary fibrosis and chronic obstructive pulmonary disease: a mendelian randomisation study . Lancet Respir Med 2021 ; 9 ( 3 ): 285 – 294 . DOI: 10.1016/S2213-2600(20)30364-7 . OpenUrl CrossRef PubMed 5. ↵ Diaz de Leon A , Cronkhite JT , Katzenstein AL , et al. Telomere lengths, pulmonary fibrosis and telomerase (TERT) mutations . PLoS One 2010 ; 5 ( 5 ): e10680 . DOI: 10.1371/journal.pone.0010680 . OpenUrl CrossRef PubMed 6. ↵ Zhang D , Newton CA , Wang B , et al. Utility of whole genome sequencing in assessing risk and clinically relevant outcomes for pulmonary fibrosis . Eur Respir J 2022 ; 60 ( 6 ). DOI: 10.1183/13993003.00577-2022 . OpenUrl Abstract / FREE Full Text 7. ↵ Rossiello F , Jurk D , Passos JF, d’Adda di Fagagna F. Telomere dysfunction in ageing and age-related diseases . Nat Cell Biol 2022 ; 24 ( 2 ): 135 – 147 . DOI: 10.1038/s41556-022-00842-x . OpenUrl CrossRef PubMed 8. ↵ Allen RJ , Stockwell A , Oldham JM , et al. Genome-wide association study across five cohorts identifies five novel loci associated with idiopathic pulmonary fibrosis . Thorax 2022 ; 77 ( 8 ): 829 – 833 . DOI: 10.1136/thoraxjnl-2021-218577 . OpenUrl Abstract / FREE Full Text 9. ↵ Allen RJ , Guillen-Guio B , Oldham JM , et al. Genome-Wide Association Study of Susceptibility to Idiopathic Pulmonary Fibrosis . Am J Respir Crit Care Med 2020 ; 201 ( 5 ): 564 – 574 . DOI: 10.1164/rccm.201905-1017OC . OpenUrl CrossRef PubMed 10. ↵ Petrovski S , Todd JL , Durheim MT , et al. An Exome Sequencing Study to Assess the Role of Rare Genetic Variation in Pulmonary Fibrosis . Am J Respir Crit Care Med 2017 ; 196 ( 1 ): 82 – 93 . DOI: 10.1164/rccm.201610-2088OC . OpenUrl CrossRef PubMed 11. ↵ Zhang D , Povysil G , Kobeissy PH , et al. Rare and Common Variants in KIF15 Contribute to Genetic Risk of Idiopathic Pulmonary Fibrosis . Am J Respir Crit Care Med 2022 ; 206 ( 1 ): 56 – 69 . DOI: 10.1164/rccm.202110-2439OC . OpenUrl CrossRef PubMed 12. ↵ Li C , Stoma S , Lotta LA , et al. Genome-wide Association Analysis in Humans Links Nucleotide Metabolism to Leukocyte Telomere Length . Am J Hum Genet 2020 ; 106 ( 3 ): 389 – 404 . DOI: 10.1016/j.ajhg.2020.02.006 . OpenUrl CrossRef PubMed 13. ↵ Codd V , Wang Q , Allara E , et al. Polygenic basis and biomedical consequences of telomere length variation . Nat Genet 2021 ; 53 ( 10 ): 1425 – 1433 . DOI: 10.1038/s41588-021-00944-6 . OpenUrl CrossRef PubMed 14. ↵ Dressen A , Abbas AR , Cabanski C , et al. Analysis of protein-altering variants in telomerase genes and their association with MUC5B common variant status in patients with idiopathic pulmonary fibrosis: a candidate gene sequencing study . Lancet Respir Med 2018 ; 6 ( 8 ): 603 – 614 . DOI: 10.1016/S2213-2600(18)30135-8 . OpenUrl CrossRef PubMed 15. Dai J , Cai H , Li H , et al. Association between telomere length and survival in patients with idiopathic pulmonary fibrosis . Respirology 2015 ; 20 ( 6 ): 947 – 52 . DOI: 10.1111/resp.12566 . OpenUrl CrossRef PubMed 16. ↵ Stuart BD , Lee JS , Kozlitina J , et al. Effect of telomere length on survival in patients with idiopathic pulmonary fibrosis: an observational cohort study with independent validation . Lancet Respir Med 2014 ; 2 ( 7 ): 557 – 65 . DOI: 10.1016/S2213-2600(14)70124-9 . OpenUrl CrossRef PubMed 17. ↵ Newton CA , Oldham JM , Ley B , et al. Telomere length and genetic variant associations with interstitial lung disease progression and survival . Eur Respir J 2019 ; 53 ( 4 ). DOI: 10.1183/13993003.01641-2018 . OpenUrl Abstract / FREE Full Text 18. ↵ Adegunsoye A , Morisset J , Newton CA , et al. Leukocyte telomere length and mycophenolate therapy in chronic hypersensitivity pneumonitis . Eur Respir J 2021 ; 57 ( 3 ). DOI: 10.1183/13993003.02872-2020 . OpenUrl Abstract / FREE Full Text 19. Newton CA , Zhang D , Oldham JM , et al. Telomere Length and Use of Immunosuppressive Medications in Idiopathic Pulmonary Fibrosis . Am J Respir Crit Care Med 2019 ; 200 ( 3 ): 336 – 347 . DOI: 10.1164/rccm.201809-1646OC . OpenUrl CrossRef PubMed 20. ↵ Zhang D , Adegunsoye A , Oldham JM , et al. Telomere length and immunosuppression in non-idiopathic pulmonary fibrosis interstitial lung disease . Eur Respir J 2023 ; 62 ( 5 ). DOI: 10.1183/13993003.00441-2023 . OpenUrl Abstract / FREE Full Text 21. ↵ Newton CA , Kozlitina J , Lines JR , Kaza V , Torres F , Garcia CK . Telomere length in patients with pulmonary fibrosis associated with chronic lung allograft dysfunction and post-lung transplantation survival . J Heart Lung Transplant 2017 ; 36 ( 8 ): 845 – 853 . DOI: 10.1016/j.healun.2017.02.005 . OpenUrl CrossRef PubMed 22. ↵ Seibold MA , Wise AL , Speer MC , et al. A common MUC5B promoter polymorphism and pulmonary fibrosis . N Engl J Med 2011 ; 364 ( 16 ): 1503 – 12 . DOI: 10.1056/NEJMoa1013660 . OpenUrl CrossRef PubMed Web of Science 23. ↵ Alonso-Gonzalez A , Jaspez D , Lorenzo-Salazar JM , et al. Rare variants and survival of patients with idiopathic pulmonary fibrosis . medRxiv 2024 . DOI: 10.1101/2024.10.12.24315151 . OpenUrl Abstract / FREE Full Text 24. ↵ Zhang D , Newton CA . Familial Pulmonary Fibrosis: Genetic Features and Clinical Implications . Chest 2021 ; 160 ( 5 ): 1764 – 1773 . DOI: 10.1016/j.chest.2021.06.037 . OpenUrl CrossRef PubMed 25. ↵ Leavy OC , Ma SF , Molyneaux PL , et al. Proportion of Idiopathic Pulmonary Fibrosis Risk Explained by Known Common Genetic Loci in European Populations . Am J Respir Crit Care Med 2021 ; 203 ( 6 ): 775 – 778 . DOI: 10.1164/rccm.202008-3211LE . OpenUrl CrossRef 26. ↵ Taliun D , Harris DN , Kessler MD , et al. Sequencing of 53,831 diverse genomes from the NHLBI TOPMed Program . Nature 2021 ; 590 ( 78451 ): 290 – 299 . DOI: 10.1038/s41586-021-03205-y . OpenUrl CrossRef PubMed 27. ↵ Bycroft C , Freeman C , Petkova D , et al. The UK Biobank resource with deep phenotyping and genomic data . Nature 2018 ; 562 ( 7726 ): 203 – 209 . DOI: 10.1038/s41586-018-0579-z . OpenUrl CrossRef PubMed 28. ↵ Manichaikul A , Mychaleckyj JC , Rich SS , Daly K , Sale M , Chen WM . Robust relationship inference in genome-wide association studies . Bioinformatics 2010 ; 26 ( 22 ): 2867 – 73 . DOI: 10.1093/bioinformatics/btq559 . OpenUrl CrossRef PubMed Web of Science 29. ↵ Purcell S , Neale B , Todd-Brown K , et al. PLINK: a tool set for whole-genome association and population-based linkage analyses . Am J Hum Genet 2007 ; 81 ( 3 ): 559 – 75 . DOI: 10.1086/519795 . OpenUrl CrossRef PubMed 30. ↵ Pedersen BS , Quinlan AR . Who’s Who? Detecting and Resolving Sample Anomalies in Human DNA Sequencing Studies with Peddy . Am J Hum Genet 2017 ; 100 ( 3 ): 406 – 413 . DOI: 10.1016/j.ajhg.2017.01.017 . OpenUrl CrossRef PubMed 31. ↵ Genomes Project C , Auton A , Brooks LD , et al. A global reference for human genetic variation . Nature 2015 ; 526 ( 7571 ): 68 – 74 . DOI: 10.1038/nature15393 . OpenUrl CrossRef PubMed 32. ↵ McGroder CF , Hansen S , Hinckley Stukovsky K , et al. Incidence of interstitial lung abnormalities: the MESA Lung Study . Eur Respir J 2023 ; 61 ( 6 ). DOI: 10.1183/13993003.01950-2022 . OpenUrl Abstract / FREE Full Text 33. ↵ Moll M , Peljto AL , Kim JS , et al. A Polygenic Risk Score for Idiopathic Pulmonary Fibrosis and Interstitial Lung Abnormalities . Am J Respir Crit Care Med 2023 ; 208 ( 7 ): 791 – 801 . DOI: 10.1164/rccm.202212-2257OC . OpenUrl CrossRef PubMed 34. ↵ Cronkhite JT , Xing C , Raghu G , et al. Telomere shortening in familial and sporadic pulmonary fibrosis . Am J Respir Crit Care Med 2008 ; 178 ( 7 ): 729 – 37 . DOI: 10.1164/rccm.200804-550OC . OpenUrl CrossRef PubMed Web of Science 35. ↵ Codd V , Denniff M , Swinfield C , et al. Measurement and initial characterization of leukocyte telomere length in 474,074 participants in UK Biobank . Nat Aging 2022 ; 2 ( 2 ): 170 – 179 . DOI: 10.1038/s43587-021-00166-9 . OpenUrl CrossRef PubMed 36. ↵ Lee SH , Goddard ME , Wray NR , Visscher PM . A better coefficient of determination for genetic profile analysis . Genet Epidemiol 2012 ; 36 ( 3 ): 214 – 24 . DOI: 10.1002/gepi.21614 . OpenUrl CrossRef PubMed 37. ↵ Nalysnyk L , Cid-Ruzafa J , Rotella P , Esser D . Incidence and prevalence of idiopathic pulmonary fibrosis: review of the literature . Eur Respir Rev 2012 ; 21 ( 126 ): 355 – 61 . DOI: 10.1183/09059180.00002512 . OpenUrl Abstract / FREE Full Text 38. ↵ Raghu G , Chen SY , Yeh WS , et al. Idiopathic pulmonary fibrosis in US Medicare beneficiaries aged 65 years and older: incidence, prevalence, and survival, 2001-11 . Lancet Respir Med 2014 ; 2 ( 7 ): 566 – 72 . DOI: 10.1016/S2213-2600(14)70101-8 . OpenUrl CrossRef PubMed 39. ↵ Lee SH , Wray NR , Goddard ME , Visscher PM . Estimating missing heritability for disease from genome-wide association studies . Am J Hum Genet 2011 ; 88 ( 3 ): 294 – 305 . DOI: 10.1016/j.ajhg.2011.02.002 . OpenUrl CrossRef PubMed Web of Science 40. ↵ Bulik-Sullivan B , Finucane HK , Anttila V , et al. An atlas of genetic correlations across human diseases and traits . Nat Genet 2015 ; 47 ( 11 ): 1236 – 41 . DOI: 10.1038/ng.3406 . OpenUrl CrossRef PubMed 41. ↵ Saunders GRB , Wang X , Chen F , et al. Genetic diversity fuels gene discovery for tobacco and alcohol use . Nature 2022 ; 612 ( 7941 ): 720 – 724 . DOI: 10.1038/s41586-022-05477-4 . OpenUrl CrossRef PubMed 42. ↵ An J , Gharahkhani P , Law MH , et al. Gastroesophageal reflux GWAS identifies risk loci that also associate with subsequent severe esophageal diseases . Nat Commun 2019 ; 10 ( 1 ): 4219 . DOI: 10.1038/s41467-019-11968-2 . OpenUrl CrossRef PubMed 43. ↵ Barton AR , Sherman MA , Mukamel RE , Loh PR . Whole-exome imputation within UK Biobank powers rare coding variant association and fine-mapping analyses . Nat Genet 2021 ; 53 ( 8 ): 1260 – 1269 . DOI: 10.1038/s41588-021-00892-1 . OpenUrl CrossRef PubMed 44. ↵ Ishigaki K , Sakaue S , Terao C , et al. Multi-ancestry genome-wide association analyses identify novel genetic mechanisms in rheumatoid arthritis . Nat Genet 2022 ; 54 ( 11 ): 1640 – 1651 . DOI: 10.1038/s41588-022-01213-w . OpenUrl CrossRef PubMed 45. ↵ Shrine N , Izquierdo AG , Chen J , et al. Multi-ancestry genome-wide association analyses improve resolution of genes and pathways influencing lung function and chronic obstructive pulmonary disease risk . Nat Genet 2023 ; 55 ( 3 ): 410 – 422 . DOI: 10.1038/s41588-023-01314-0 . OpenUrl CrossRef PubMed 46. ↵ Teslovich TM , Musunuru K , Smith AV , et al. Biological, clinical and population relevance of 95 loci for blood lipids . Nature 2010 ; 466 ( 7307 ): 707 – 13 . DOI: 10.1038/nature09270 . OpenUrl CrossRef PubMed Web of Science 47. ↵ Uda M , Galanello R , Sanna S , et al. Genome-wide association study shows BCL11A associated with persistent fetal hemoglobin and amelioration of the phenotype of beta-thalassemia . Proc Natl Acad Sci U S A 2008 ; 105 ( 5 ): 1620 – 5 . DOI: 10.1073/pnas.0711566105 . OpenUrl Abstract / FREE Full Text 48. ↵ Liu L , Khan A , Sanchez-Rodriguez E , et al. Genetic regulation of serum IgA levels and susceptibility to common immune, infectious, kidney, and cardio-metabolic traits . Nat Commun 2022 ; 13 ( 1 ): 6859 . DOI: 10.1038/s41467-022-34456-6 . OpenUrl CrossRef PubMed 49. ↵ McGroder CF , Zhang D , Choudhury M , et al. Radiographic Lung Abnormalities in First-Degree Relatives of Patients With Different Subtypes of Pulmonary Fibrosis . Chest 2023 ; 163 ( 6 ): 1471 – 1475 . DOI: 10.1016/j.chest.2023.01.012 . OpenUrl CrossRef PubMed 50. ↵ Fahed AC , Wang M , Homburger JR , et al. Polygenic background modifies penetrance of monogenic variants for tier 1 genomic conditions . Nat Commun 2020 ; 11 ( 1 ): 3635 . DOI: 10.1038/s41467-020-17374-3 . OpenUrl CrossRef 51. ↵ Goodrich JK , Singer-Berk M , Son R , et al. Determinants of penetrance and variable expressivity in monogenic metabolic conditions across 77,184 exomes . Nat Commun 2021 ; 12 ( 1 ): 3505 . DOI: 10.1038/s41467-021-23556-4 . OpenUrl CrossRef PubMed 52. ↵ Khan A , Shang N , Nestor JG , et al. Polygenic risk alters the penetrance of monogenic kidney disease . Nat Commun 2023 ; 14 ( 1 ): 8318 . DOI: 10.1038/s41467-023-43878-9 . OpenUrl CrossRef PubMed 53. ↵ Newton CA , Batra K , Torrealba J , et al. Telomere-related lung fibrosis is diagnostically heterogeneous but uniformly progressive . Eur Respir J 2016 ; 48 ( 6 ): 1710 – 1720 . DOI: 10.1183/13993003.00308-2016 . OpenUrl Abstract / FREE Full Text 54. ↵ Zhang D , Eckhardt CM , McGroder C , et al. Clinical Impact of Telomere Length Testing for Interstitial Lung Disease . Chest 2024 ; 166 ( 5 ): 1071 – 1081 . DOI: 10.1016/j.chest.2024.06.006 . OpenUrl CrossRef PubMed 55. ↵ Xing C , Garcia CK . Epigenetic inheritance of telomere length obscures identification of causative PARN locus . J Med Genet 2016 ; 53 ( 5 ): 356 – 8 . DOI: 10.1136/jmedgenet-2015-103685 . OpenUrl FREE Full Text 56. ↵ Chiang YJ , Calado RT , Hathcock KS , Lansdorp PM , Young NS , Hodes RJ . Telomere length is inherited with resetting of the telomere set-point . Proc Natl Acad Sci U S A 2010 ; 107 ( 22 ): 10148 – 53 . DOI: 10.1073/pnas.0913125107 . OpenUrl Abstract / FREE Full Text 57. Kozlitina J , Garcia CK . Red blood cell size is inversely associated with leukocyte telomere length in a large multi-ethnic population . PLoS One 2012 ; 7 ( 12 ): e51046 . DOI: 10.1371/journal.pone.0051046 . OpenUrl CrossRef PubMed 58. ↵ Astuti Y , Wardhana A , Watkins J , Wulaningsih W , Network PR . Cigarette smoking and telomere length: A systematic review of 84 studies and meta-analysis . Environ Res 2017 ; 158 : 480 – 489 . DOI: 10.1016/j.envres.2017.06.038 . OpenUrl CrossRef PubMed 59. ↵ Adegunsoye A , Newton CA , Oldham JM , et al. Telomere length associates with chronological age and mortality across racially diverse pulmonary fibrosis cohorts . Nat Commun 2023 ; 14 ( 1 ): 1489 . DOI: 10.1038/s41467-023-37193-6 . OpenUrl CrossRef 60. ↵ Noth I , Zhang Y , Ma SF , et al. Genetic variants associated with idiopathic pulmonary fibrosis susceptibility and mortality: a genome-wide association study . Lancet Respir Med 2013 ; 1 ( 4 ): 309 – 317 . DOI: 10.1016/S2213-2600(13)70045-6 . OpenUrl CrossRef PubMed 61. ↵ Fingerlin TE , Murphy E , Zhang W , et al. Genome-wide association study identifies multiple susceptibility loci for pulmonary fibrosis . Nat Genet 2013 ; 45 ( 6 ): 613 – 20 . DOI: 10.1038/ng.2609 . OpenUrl CrossRef PubMed View the discussion thread. Back to top Previous Next Posted June 04, 2025. Download PDF Supplementary Material 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 Polygenic Risk and Rare Variants in Endotypes of Idiopathic Pulmonary Fibrosis 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 Polygenic Risk and Rare Variants in Endotypes of Idiopathic Pulmonary Fibrosis Anna Duckworth , Leigh Jackson , Harry Green , Atlas Khan , Chen Wang , Andrew Condescu , Gareth Hawkes , Imre Noth , Fernando J Martinez , Ganesh Raghu , Chad A. Newton , Matthew Moll , Michael Cho , Michael Gibbons , Chris J. Scotton , Columbia Genomics Consortium , Krzysztof Kiryluk , Christine Kim Garcia , David Zhang medRxiv 2025.05.22.25328177; doi: https://doi.org/10.1101/2025.05.22.25328177 Share This Article: Copy Citation Tools Polygenic Risk and Rare Variants in Endotypes of Idiopathic Pulmonary Fibrosis Anna Duckworth , Leigh Jackson , Harry Green , Atlas Khan , Chen Wang , Andrew Condescu , Gareth Hawkes , Imre Noth , Fernando J Martinez , Ganesh Raghu , Chad A. Newton , Matthew Moll , Michael Cho , Michael Gibbons , Chris J. Scotton , Columbia Genomics Consortium , Krzysztof Kiryluk , Christine Kim Garcia , David Zhang medRxiv 2025.05.22.25328177; doi: https://doi.org/10.1101/2025.05.22.25328177 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 (297) Cardiovascular Medicine (4421) Dentistry and Oral Medicine (443) Dermatology (382) Emergency Medicine (606) Endocrinology (including Diabetes Mellitus and Metabolic Disease) (1507) Epidemiology (15212) Forensic Medicine (30) Gastroenterology (1121) Genetic and Genomic Medicine (6581) Geriatric Medicine (667) Health Economics (996) Health Informatics (4520) Health Policy (1366) Health Systems and Quality Improvement (1611) Hematology (539) HIV/AIDS (1264) Infectious Diseases (except HIV/AIDS) (15906) Intensive Care and Critical Care Medicine (1103) Medical Education (620) Medical Ethics (144) Nephrology (667) Neurology (6580) Nursing (345) Nutrition (998) Obstetrics and Gynecology (1141) Occupational and Environmental Health (956) Oncology (3324) Ophthalmology (970) Orthopedics (369) Otolaryngology (420) Pain Medicine (435) Palliative Medicine (129) Pathology (663) Pediatrics (1689) Pharmacology and Therapeutics (691) Primary Care Research (710) Psychiatry and Clinical Psychology (5433) Public and Global Health (9212) Radiology and Imaging (2193) Rehabilitation Medicine and Physical Therapy (1368) Respiratory Medicine (1194) Rheumatology (593) Sexual and Reproductive Health (709) Sports Medicine (529) Surgery (709) Toxicology (99) Transplantation (288) 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:'9ff66981cb6ff047',t:'MTc3OTM5NjE5Mw=='};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())}}}})();