Overlap between COPD genetic association results and transcriptional quantitative trait loci

Overlap between COPD genetic association results and transcriptional quantitative trait loci | 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 Overlap between COPD genetic association results and transcriptional quantitative trait loci Aabida Saferali , Wonji Kim , Robert P. Chase , NHLBI TransOmics in Precision Medicine (TOPMed) , Chris Vollmers , Edwin K. Silverman , View ORCID Profile Michael H. Cho , Peter J. Castaldi , View ORCID Profile Craig P. Hersh doi: https://doi.org/10.1101/2024.07.08.24310079 Aabida Saferali 1 Channing Division of Network Medicine , Brigham and Women’s Hospital Find this author on Google Scholar Find this author on PubMed Search for this author on this site Wonji Kim 1 Channing Division of Network Medicine , Brigham and Women’s Hospital Find this author on Google Scholar Find this author on PubMed Search for this author on this site Robert P. Chase 1 Channing Division of Network Medicine , Brigham and Women’s Hospital Find this author on Google Scholar Find this author on PubMed Search for this author on this site Chris Vollmers 2 Department of Biomolecular Engineering , Cellular, Cellular, and Developmental Biology, University of California Santa Cruz Find this author on Google Scholar Find this author on PubMed Search for this author on this site Edwin K. Silverman 1 Channing Division of Network Medicine , Brigham and Women’s Hospital 2 Department of Biomolecular Engineering , Cellular, Cellular, and Developmental Biology, University of California Santa Cruz Find this author on Google Scholar Find this author on PubMed Search for this author on this site Michael H. Cho 1 Channing Division of Network Medicine , Brigham and Women’s Hospital 3 Division of Pulmonary and Critical Care Medicine , Brigham and Women’s Hospital Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Michael H. Cho Peter J. Castaldi 1 Channing Division of Network Medicine , Brigham and Women’s Hospital 4 Division of General Medicine and Primary Care , Brigham and Women’s Hospital Find this author on Google Scholar Find this author on PubMed Search for this author on this site Craig P. Hersh 1 Channing Division of Network Medicine , Brigham and Women’s Hospital 3 Division of Pulmonary and Critical Care Medicine , Brigham and Women’s Hospital Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Craig P. Hersh For correspondence: craig.hersh{at}channing.harvard.edu Abstract Full Text Info/History Metrics Supplementary material Data/Code Preview PDF Abstract Rationale Genome-wide association studies (GWAS) have identified multiple genetic loci associated with chronic obstructive pulmonary disease (COPD). When integrated with GWAS results, expression quantitative trait locus (eQTL) studies can provide insight into biological mechanisms involved in disease by identifying single nucleotide polymorphisms (SNPs) that contribute to whole gene expression. However, there are multiple genetically driven regulatory and isoform-specific effects which cannot be detected in traditional eQTL analyses. Here, we identify SNPs that are associated with alternative splicing (sQTL) in addition to eQTLs to identify novel functions for COPD associated genetic variants. Methods We performed RNA sequencing on whole blood from 3743 subjects in the COPDGene Study. RNA sequencing data from lung tissue of 1241 subjects from the Lung Tissue Research Consortium (LTRC), and whole genome sequencing data on all subjects. Associations between all SNPs within 1000 kb of a gene (cis-) and splice and gene expression quantifications were tested using tensorQTL. In COPDGene a total of 11,869,333 SNPs were tested for association with 58,318 splice clusters, and 8,792,206 SNPs were tested for association with 70,094 splice clusters in LTRC. We assessed colocalization with COPD-associated SNPs from a published GWAS[ 1 ]. Results After adjustment for multiple statistical testing, we identified 28,110 splice-sites corresponding to 3,889 unique genes that were significantly associated with genotype in COPDGene whole blood, and 58,258 splice-sites corresponding to 10,307 unique genes associated with genotype in LTRC lung tissue. We found 7,576 sQTL splice-sites corresponding to 2,110 sQTL genes were shared between whole blood and lung, while 20,534 sQTL splice-sites in 3,518 genes were unique to blood and 50,682 splice-sites in 9,677 genes were unique to lung. To determine what proportion of COPD-associated SNPs were associated with transcriptional splicing, we performed colocalization analysis between COPD GWAS and sQTL data, and found that 38 genomic windows, corresponding to 38 COPD GWAS loci had evidence of colocalization between QTLs and COPD. The top five colocalizations between COPD and lung sQTLs include NPNT , FBXO38 , HHIP , NTN4 and BTC . Conclusions A total of 38 COPD GWAS loci contain evidence of sQTLs, suggesting that analysis of sQTLs in whole blood and lung tissue can provide novel insights into disease mechanisms. Introduction Chronic obstructive pulmonary disease (COPD) is a complex disease characterized by irreversible airflow obstruction on lung function testing. The leading environmental risk factor for COPD is cigarette smoking, however, genetic factors have also been shown to play a role in disease susceptibility[ 2 – 5 ]. Genome-wide association studies (GWAS) have been used to identify genetic variants associated with COPD and lung function[ 1 , 6 – 8 ]. However, as for most complex trait GWAS associations, the causal mechanisms are currently unknown. While it has been found that expression quantitative trait loci (eQTL) are enriched among GWAS loci, a large proportion of disease heritability remains unexplained by eQTLs [ 9 ]. Previous work has shown that splicing quantitative trait loci (sQTLs), in which genetic variants affect alternative splicing, can account for at least as many GWAS loci as eQTLs[ 10 ]. A recent genome wide association study for COPD including 35,735 cases and 222,076 controls from the UK Biobank and the International COPD Genetics Consortium identified 82 loci associated with COPD with genome wide significance[ 1 ]. Using S-PrediXcan[ 11 ], the authors discovered that 49 GWAS loci had evidence for genetically regulated expression associated with COPD using data from the Lung-eQTL consortium[ 1 ]. As S-PrediXcan is also influenced by linkage disequilibrium, most of the COPD GWAS loci are likely not explained using existing eQTLs. Genomic loci identified as being eQTLs may also be sQTLs, as splicing is a common mechanism to alter total gene expression levels. In our previous work, we generated sQTLs in 376 subjects from the COPDGene study and found that these data could explain seven COPD GWAS associations, including the identification of FBXO38 as a novel COPD susceptibility gene at 5q32 [ 10 ]. Here, we expand upon our findings by developing a large database of eQTLs and sQTLs in RNA from lung tissue from 1,241 subjects and in RNA from blood from 3,743 subjects followed by colocalization analysis with COPD GWAS results. Materials and Methods Study Population This study included 3,713 non-Hispanic white and African American subjects from the COPDGene study and 1,241 subjects from the Lung Tissue Research Consortium (LTRC) ( Table 1 ). COPDGene enrolled individuals between the ages of 45 and 80 years with a minimum of 10 pack-years of lifetime smoking history from 21 centers across the United States [ 12 ]. These subjects returned for a second study visit 5 years after the initial visit at which time they completed additional questionnaires, pre-and post-bronchodilator spirometry, chest computed tomography of the chest, and provided blood for complete blood counts (CBCs) and RNA sequencing. Samples were collected as part of the LTRC from individuals who were undergoing clinically indicated thoracic surgery procedures using a standardized protocol described in the original study design, which included pulmonary function testing, questionnaires, and chest CT [ 13 ]. View this table: View inline View popup Download powerpoint Table 1: Clinical characteristics of LTRC and COPDGene study individuals included in the analysis. RNA sequencing, alignment and count generation The protocols for RNASeq data generation and processing for COPDGene and LTRC have been previously described [ 14 ] [ 13 ]. Briefly, for LTRC, mRNA sequencing (RNAseq) was performed through the NHLBI TOPMed program at the University of Washington. Poly-A selection and cDNA synthesis was performed using the TruSeq Stranded mRNA kit (Illumina), and sequencing was performed on the NovaSeq6000 instrument. Sequences were aligned to GRCh38 using STAR (v2.6.1d) with the GENCODE release 29 reference. Gene-level expression quantification was performed using RSEM (v1.3.1). For COPDGene, globin reduction, ribosomal RNA depletion, and cDNA library prep was performed on total RNA from whole blood using the TruSeq Stranded Total RNA with Ribo-Zero Globin kit (Illumina, Inc., San Diego, CA), and sequencing was performed on Illumina platforms. Sequences were aligned to GRCh38 using STAR 2 pass alignment (v.2.5.2b). Gene-level expression quantification was performed using Salmon (v1.3.0) for pseudoalignment to GENCODE release 37 transcriptome, followed by summarization of isoform-level counts to gene-level counts using tximport (v.1.8.5) [ 15 , 16 ]. Quantification of splicing ratios was performed in COPDGene and LTRC using Leafcutter with default parameters [ 17 ]. Intron ratios were calculated by determining how many reads support a given exon-intron junction in relation to the number of reads in that region. Whole Genome Sequencing All samples were sequenced through the TOPMed program. This analysis uses Freeze 8 data. eQTL and sQTL Analysis Gene expression counts were filtered to include only genes with at least 1 count per million in at least 20% of subjects, and the remaining counts were TMM normalized [ 18 ]. Leafcutter ratios were filtered to remove introns detected in less than 40% of individuals and introns with a standard deviation of less than 0.005 across subjects, and the remaining ratios were scale normalized (ie mean centered and divided by the standard error). TensorQTL [ 19 ] was used to test for association between genotypes of all SNPs within 1000 kb of the gene boundary (cis-) and quantifications of splicing or gene expression using linear models, adjusting for gender, batch, principal components of splicing or gene expression data and principal components of genetic ancestry. Calculation of principal components of genetic ancestry has been previously described [ 20 ]. A total of 8,792,206 variants (biallelic SNPs with MAF > 0.01) were tested for association with 58,258 splice sites (corresponding to 10,615 unique genes) and expression of 16,264 genes. Results were annotated using ANNOVAR [ 21 ] with annotations derived from dbSNP build 150. Colocalization analysis Published GWAS data for COPD case-control status [ 1 ] were used for this analysis. Testing windows were generated by identifying all GWAS variants with p< 1x10 -5 and calculating non-overlapping windows of 1MB on either side of each SNP. Only windows containing sQTLs or eQTLs with FDR<0.05 were tested. For each window, Bayesian colocalization tests were performed using the Moloc R package [ 22 ] to quantify the probability that the GWAS and sQTL or eQTL associations were due to a shared causal variant. Windows with a colocalization posterior probability (CPP) of greater than 0.8 were reported. Fine mapping was performed on QTL results from selected regions of interestusing SuSieR version 12.35, with in sample LD [ 23 ]. Long read RNA-seq analysis in human lung samples from the LTRC We conducted targeted Oxford Nanopore Technologies (ONT) long read sequencing on RNA from 170 human lung samples from the LTRC on genes selected from colocalization analysis. The enrichment and library generation procedures are described in detail in the Supplemental Methods. The final library was loaded onto a PromethION R10.4 flow cell and run at 400bp/s. Approximately once per day, flow cells were flushed and treated with DNAse I, then loaded with additional library to increase sequencing throughput. Resulting raw reads were basecalled using the SUP model of guppy (v6) and consensus called and demultiplexed using C3POa (v2.3). R2C2 reads were analyzed to identify and quantify isoforms using version 3.5 of Mandalorion ( https://github.com/rvolden/Mandalorion-Episode-III ). Mandalorian was run twice to identify high abundance isoforms (>10% of total isoform expression; -O 0,40,0,40 -r 0.1 -i 1 - w 1 -n 2 -R 5) and high and low abundance isoforms (-O 0,40,0,40 -r 0.01 -i 1 -w 1 -n 2 -R 5). Results Quantification of gene expression and RNA splicing in COPDGene blood and LTRC lung Using RNASeq data from LTRC lung tissue (n=1241) and COPDGene whole blood (n=3713) we identified splice sites using Leafcutter [ 24 ], which identifies and quantifies intron exclusion. After filtering out splice sites with low usage, we identified a total of 223,128 splice sites, corresponding to 15,121 genes in LTRC, and 160,658 splice sites corresponding to 12,096 genes in COPDGene ( Table 2 ). In both LTRC and COPDGene, the majority (50.1% and 51.0%, respectively) of identified splice sites were annotated in GENCODE, followed by cryptic 3’, cryptic 5’, cryptic unanchored splice sites (meaning both splice donor and acceptor were unannotated) and novel annotated pairs ( Table 3 ). Gene expression of 16,266 genes in LTRC and 15,507 genes in COPDGene met expression thresholds ( Table 2 ). View this table: View inline View popup Download powerpoint Table 2: Summary of expressionQTLs and spliceQTLs tested View this table: View inline View popup Download powerpoint Table 3: Annotations of Leafcutter Splice Sites Identified in COPDGene and LTRC Identification of eQTL and sQTLs in human lung tissue and whole blood We next tested for association between genotype and gene expression or splicing to identify eQTLs and sQTLs in lung and blood. In LTRC lung tissue we identified 58,258 splice sites (corresponding to 10,615 genes) associated with at least one SNP with q-value<0.05; in COPDGene blood 60,291 splice sites (corresponding to 8,671 genes) were associated with at least one SNP ( Table 2 ). In addition, we identified 12,225 genes associated with at least one SNP (eQTLs) in LTRC, and 15,279 eQTL genes in COPDGene. We found that 14,064 sQTL splice- site-SNP pairs (13%) were found in both blood and lung, while 6,353 eQTL gene-SNP pairs were shared between both tissues (25%) ( Figure 1 ). In addition, we found that 5,787 sQTL gene-SNP pairs overlapped with eQTL gene-SNP pairs in LTRC (47%), while 7,455 sQTL gene-SNP pairs overlapped with eQTL gene-SNP pairs in COPDGene (49%). Download figure Open in new tab Figure 1: Overlap between LTRC lung and COPDGene blood eQTLs and sQTLs that were significant at FDR<0.05 Functional annotation of sQTLs and eQTLs Next we categorized eQTLs and sQTLs-SNPs on the basis of their location relative to the gene with which they were associated ( Table 4 ). The genomic distribution of eQTLs and sQTLs was similar, with the largest proportion of variants located upstream of the gene region in both COPDGene (32.1% and 34.7 %, respectively) and LTRC (31.8% and 29.4%, respectively). The next most frequent SNPs were intronic, downstream of gene, intergenic, and 3’ UTR variants. Only a small percentage of lead sQTL-SNPs directly modified a splice site. There was no difference in variant position in either eQTL vs sQTL and in COPDGene blood vs LTRC lung. View this table: View inline View popup Download powerpoint Table 4: Annotation of QTL variants in relation to the gene body Colocalization of QTLs with COPD Case-Control GWAS data We next sought to identify eQTLs and sQTLs which contribute to COPD risk by performing genetic colocalization between the QTL data and COPD case-control GWAS data. Based on GWAS data, 239 genomic windows with COPD GWAS p-values < 5x10 -5 were identified, and of these, 237 contained sQTLs or eQTLs with q-value<0.05. We also included colocalization results for 3’ UTR alternative polyadenylation QTLs (apaQTLs) from our previous study [ 25 ]. We identified 38 windows with a colocalization posterior probability of association (PPA) > 0.8 with either eQTL, sQTL or apaQTL data and GWAS p-value < 5.0x10 -8 ( Table 5 ). We found that for 19 loci the strongest colocalization (largest PPA) with GWAS data was in LTRC, and for 19 loci the strongest colocalization was in COPDGene. In LTRC, the largest number of GWAS loci colocalized with sQTLs (9 loci), followed by eQTLs (7 loci) then apaQTLs (3 loci). In COPDGene, the majority of colocalizations were with sQTLs (15 loci), with only one 1 locus colocalizing most strongly with eQTLs, and 3 with apaQTLs. We compared the colocalization findings with the target genes identified from the original GWAS analysis to determine whether the QTLs identified novel targets from previous analyses. We found that for 7 loci all genes identified in the current QTL analysis were previously identified, and for 26 loci one or more new targets were found (Supplementary Table 1). For further characterization we focused on sQTL colocalizations in LTRC lung, with the top five colocalizations (by highest PPA) being Nephronectin ( NPNT) , F-box protein 38 ( FBXO38) , Hedgehog interacting protein ( HHIP) , Netrin 4 (NTN4) and Betacellulin ( BTC) . We have previously published on NPNT colocalizations in the lung [ 26 ], and for HHIP significant evidence suggests that the mechanism underlying the association is an eQTL effect [ 27 ]. NTN4 appears to be a promoter usage eQTL instead of an sQTL. Therefore, we highlight the results for FBXO38 and BTC below. All colocalization results are available online at ( https://copd-moloc.bwh.harvard.edu/ ). View this table: View inline View popup Table 5: Summary of Colocalization Analysis Characterization of sQTL for FBXO38 We first sought to replicate the association we previously characterized in 365 subjects from COPDGene between the rs7730971 (5:148411297:C:G) variant and FBXO38 splicing in whole blood which colocalized with COPD GWAS findings [ 10 ]. Here, we identified two splicing clusters (ie a group of splice junctions with shared start or stop positions [ 24 ]) in lung tissue in FBXO38 which were associated with COPD-related variants. First, we confirmed our previous finding that rs7730971 was significantly associated with inclusion of a 158 bp cryptic exon located between exons 9 and 10 ( Figure 2 ). While significant colocalization was not detected using moloc, we previously found colocalization in this locus using eCaviar [ 28 ]. The G allele, which is associated with increased risk of COPD, is also associated with increased inclusion of the cryptic exon ( Figure 2b ). SpliceAI [ 29 ] indicates that rs7730971-G is predicted to slightly increase the splice acceptor strength of a splice site 217 bp upstream of the variant, which corresponds to the 5’ splice acceptor of the cryptic exon, confirming that this is the likely causal variant. Using long-read sequencing we identified one isoform meeting expression thresholds which includes the 158 bp cryptic exon ( Figure 2c ). This transcript includes a premature stop codon in the cryptic exon, and because this stop is more than 50 bases from the transcriptional stop, it would likely be subject to nonsense mediated decay [ 30 ]. This isoform is more abundant in the GG genotype compared to AA (5 reads vs 1). Supporting the finding that the transcript containing the cryptic exon is subject to nonsense mediated decay, we found that rs7730971 is also an eQTL for FBXO38 , with the G allele associated with decreased expression ( Figure 2d ). We additionally identified a new colocalization between genetic variants in the FBXO38/HTR4 region and inclusion of an exon at chr5: 148415241-148415387 (Supplementary Data). Download figure Open in new tab Figure 2: Replication of FBXO38 sQTL findings in lung tissue. a) Locus association plot for COPD GWAS and FBXO38 sQTL. The lead SNP associated with FBXO38 splicing, rs7730971, is highlighted in purple and used as the LD reference. b) IGV sashimi plot showing the region spanning chr5:148409934-148414781 for 191 subjects from each genotype of rs7730971. c) Long read sequencing data showing all FBXO38 isoforms representing at least 1% of total FBXO38 expression. The cryptic exon is identified with a red arrow. D) Boxplot of total gene expression values for FBXO38 . Colocalization analysis of a genetic signal at BTC Another significant colocalization between sQTLs and COPD GWAS findings was identified in LTRC lung tissue at the BTC locus where we found evidence of a shared genetic signal between variants associated with alternative inclusion of exon 4 of BTC , and COPD risk GWAS data (PPA=0.95) ( Figure 3a ). The lead colocalized variant was rs62316278 (4:74748514:C:T), and the COPD risk allele (C) is associated with increased inclusion of exon 4 ( Figure 3b ). This variant is within the 95% credible set for sQTL data using SuSie fine mapping, along with 42 additional variants. Of the variants in the 95% credible set, we found using SpliceAI that rs11938093-T (4:74750631:A:T) is associated with the gain of a splice donor 58 bp upstream of the SNP, corresponding to the splice donor of exon 4, as well as the gain of a splice acceptor 88 bp downstream of the SNP, corresponding to the splice acceptor of exon 4. Long read sequencing identified four high abundance isoforms for BTC (representing at least 10% of BTC expression each) ( Figure 3c ), and the proportion of isoforms containing exon 4 was higher in CC vs TT subjects (84% vs 48%, p=0.0003). These isoforms correspond to NM_001729 (BTC-201, ENST00000395743.8) and NM_001316963 (not included in ENSEMBL). NM_001729 (including exon 4) is the primary version of BTC, and codes for a 178 amino acid protein, while NM_001316963 codes for 129 amino acids. Download figure Open in new tab Figure 3: sQTLs for BTC colocalize with GWAS data for COPD. a) Locus association plot for COPD GWAS and BTC sQTL. The lead colocalized SNP, rs62316278, is highlighted in purple and used as the LD reference. b) IGV sashimi plot showing the region spanning chr4:74748364-74755961 for 86 subjects from each genotype of rs62316278. c) Long read sequencing data showing all BTC isoforms representing at least 10% of total BTC expression. D) Proportion of BTC expression of isoforms containing exon 4 by copies of rs62316278-T. Discussion In this study we build upon our previous work characterizing COPD associated sQTLs in blood RNASeq data from COPDGene by generating a large dataset of eQTLs and sQTLs in human blood and lung tissue and identifying gene expression and splicing events, and we identify a substantial number of QTLs that suggest a functional mechanism for COPD GWAS loci. We found that approximately 50% of splice sites identified were not currently annotated, indicating the vast amount of currently uncharacterized splicing variability present in the transcriptome. Among the 223,128 splice sites identified in LTRC lung tissue and 160,658 in COPDGene blood, we found that 58,258 (26%) and 60,291 (38%) splice sites, respectively, were associated with at least one variant within 1 MB (FDR<5%). In addition, of the 16,266 genes expressed in LTRC and 15,507 genes expressed in COPDGene, 12,225 (75%) and 15,279 (99%) of genes, respectively, were associated with at least one SNP. The majority of eQTL and sQTL SNPs were located upstream of the gene body or in intronic regions, suggesting that many sQTLs function through long range or indirect effects, as opposed to modifying splice donors or acceptors directly. We identified 38 loci (corresponding to 33 of the original 82 GWAS loci) with significant colocalization with either eQTL, sQTL or apaQTL data, and of these, 9 loci colocalized most strongly with LTRC sQTLs, and 15 with COPDGene sQTLs. We confirmed our previous sQTL findings in the FBXO38/HTR4 region, and identified BTC as additional novel target with strong COPD colocalization. Here, we validated in lung tissue our previous findings from blood that rs7730971 is associated with splicing of a cryptic exon in FBXO38 . Open reading frame analysis of the full length transcript sequence indicates that the cryptic exon contains a premature stop codon, and therefore this transcript is likely subject to nonsense mediated decay. We also found that rs7730971 is associated with gene expression of FBXO38 , with decreased expression with the G allele, which is also the variant associated with a bioinformatically predicted increase in nonsense mediated decay. Therefore, the likely mechanism underlying the eQTL association is degradation of FBXO38 as result of increased inclusion of a cryptic exon which results in a transcript with an early stop codon. This is an example of a mechanism by which an eQTL can be mediated through an sQTL. The allele associated with decreased expression of FBXO38 is associated with increased COPD risk, suggesting that FBXO38 plays a protective role against COPD. We found an additional colocalization between rs10037493, the most significant COPD GWAS SNP in the locus, and an additional FBXO38 exon. The long read sequences containing this exon correspond to two predicted isoforms, each encoding shorter proteins than the most abundant isoform. The COPD risk allele is associated with the shortened isoforms, indicating that the full length FBXO38 isoform is protective. These shortened isoforms lack the F-box domain, which is a component of all members of F-box proteins, including FBXO38. F-box proteins are a component of the ubiquitin ligase complex and also function as transcription factors [ 31 ]. FBXO38 specifically is a coactivator of the Kruppel-like factor 7 (KLF7) zinc finger transcription factor [ 32 , 33 ]. While little is known about the function of FBXO38 and its potential role in COPD, the lack of the F-box protein, which is responsible for protein-protein interactions, in disease associated isoforms indicates that FBXO38 interactions are critical for protection against COPD. We identified an additional colocalization between the COPD GWAS and a novel candidate gene, BTC . We specifically found that rs62316278, the lead GWAS SNP in the BTC region, is also associated with splicing of exon 4, with the risk allele (C), increasing exon 4 inclusion. The primary form of BTC , NM_001729, includes exon 4, and rs62316278-C is associated with an increased proportion of NM_001729 relative to NM_001316963, a protein coding isoform which lacks exon 4. This suggests that reduced inclusion of exon 4 is protective for COPD. BTC is a member of the epidermal growth factor (EGF) family of peptide ligands, and a ligand for epidermal growth factor receptor (EGFR). Human BTC encodes a 178-amino acid product corresponding to the BTC precursor protein (pro-BTC) and contains several domains including a signal peptide, an EGF motif and transmembrane domains [ 34 ]. The mature sequence of BTC is cleaved from the extracellular domain of BTC to produce an 80 amino acid protein. Based on the structure of other members of the EGF family, exon 4 is predicted to make up the third loop of the EGF-like motif and the transmembrane domain [ 34 ]. The EGF domain is critical to binding with EGF ligands, and therefore the isoform lacking exon 4 could be predicted to have impaired function. Several previous studies have linked BTC expression to COPD, and BTC has been found to be higher in ex-smokers with COPD than without COPD, has been associated with emphysema in alpha-1 antitrypsin deficiency [ 35 ] and has been found elevated in acute exacerbations in COPD [ 36 ]. More targeted work is needed to investigate the function of BTC isoforms in COPD. The major strength of this study is the large sample size which allowed us to comprehensively characterize alternative splicing in whole blood and lung tissue. Our sample size significantly exceeds that of other commonly used resources such as The Genotype Tissue Expression Project (GTEx), which includes 515 lung samples and 670 blood samples. While we sought colocalization with GOLD-defined COPD, we expect that other respiratory- or smoking- related genetic associations would benefit from the use of this resource. One potential weakness is that our RNASeq was performed using whole lung tissue and whole blood samples, which contain a variety of cell types. Therefore, some of the changes in transcriptional splicing detected may actually be reflecting differences in inter-individual cell proportions. Another limitation is the use of Moloc, which attempts colocalization with the most significant signal in the region, and may not be optimal in the setting of multiple QTL or GWAS signals in the region. Additional work characterizing splicing using single-cell short or long read RNASeq is required. In conclusion, we discovered that multiple COPD GWAS associations colocalize with sQTLs, and identify or replicate several candidate genes as COPD targets for follow-up. Data Availability LTRC genotyping data are available on dbGaP with accession number phs001662.v1.p1 LTRC RNA-seq data are available through TOPMed, https://topmed.nhlbi.nih.gov.COPDGene data are available on dbGaP with accession numbers phs000179 and phs000765. https://copd-moloc.bwh.harvard.edu/ COPDGene® Investigators – Core Units Administrative Center : James D. Crapo, MD (PI); Edwin K. Silverman, MD, PhD (PI); Barry J. Make, MD; Elizabeth A. Regan, MD, PhD Genetic Analysis Center : Terri H. Beaty, PhD; Peter J. Castaldi, MD, MSc; Michael H. Cho, MD, MPH; Dawn L. DeMeo, MD, MPH; Adel El Boueiz, MD, MMSc; Marilyn G. Foreman, MD, MS; Auyon Ghosh, MD; Lystra P. Hayden, MD, MMSc; Craig P. Hersh, MD, MPH; Jacqueline Hetmanski, MS; Brian D. Hobbs, MD, MMSc; John E. Hokanson, MPH, PhD; Wonji Kim, PhD; Nan Laird, PhD; Christoph Lange, PhD; Sharon M. Lutz, PhD; Merry-Lynn McDonald, PhD; Dmitry Prokopenko, PhD; Matthew Moll, MD, MPH; Jarrett Morrow, PhD; Dandi Qiao, PhD; Elizabeth A. Regan, MD, PhD; Aabida Saferali, PhD; Phuwanat Sakornsakolpat, MD; Edwin K. Silverman, MD, PhD; Emily S. Wan, MD; Jeong Yun, MD, MPH Imaging Center : Juan Pablo Centeno; Jean-Paul Charbonnier, PhD; Harvey O. Coxson, PhD; Craig J. Galban, PhD; MeiLan K. Han, MD, MS; Eric A. Hoffman, Stephen Humphries, PhD; Francine L. Jacobson, MD, MPH; Philip F. Judy, PhD; Ella A. Kazerooni, MD; Alex Kluiber; David A. Lynch, MB; Pietro Nardelli, PhD; John D. Newell, Jr., MD; Aleena Notary; Andrea Oh, MD; Elizabeth A. Regan, MD, PhD; James C. Ross, PhD; Raul San Jose Estepar, PhD; Joyce Schroeder, MD; Jered Sieren; Berend C. Stoel, PhD; Juerg Tschirren, PhD; Edwin Van Beek, MD, PhD; Bram van Ginneken, PhD; Eva van Rikxoort, PhD; Gonzalo Vegas SanchezFerrero, PhD; Lucas Veitel; George R. Washko, MD; Carla G. Wilson, MS; PFT QA Center , Salt Lake City, UT: Robert Jensen, PhD Data Coordinating Center and Biostatistics, National Jewish Health, Denver, CO : Douglas Everett, PhD; Jim Crooks, PhD; Katherine Pratte, PhD; Matt Strand, PhD; Carla G. Wilson, MS Epidemiology Core, University of Colorado Anschutz Medical Campus, Aurora, CO: John E. Hokanson, MPH, PhD; Erin Austin, PhD; Gregory Kinney, MPH, PhD; Sharon M. Lutz, PhD; Kendra A. Young, PhD Version Date: March 26, 2021 Mortality Adjudication Core : Surya P. Bhatt, MD; Jessica Bon, MD; Alejandro A. Diaz, MD, MPH; MeiLan K. Han, MD, MS; Barry Make, MD; Susan Murray, ScD; Elizabeth Regan, MD; Xavier Soler, MD; Carla G. Wilson, MS Biomarker Core : Russell P. Bowler, MD, PhD; Katerina Kechris, PhD; Farnoush BanaeiKashani, PhD COPDGene® Investigators – Clinical Centers Ann Arbor VA : Jeffrey L. Curtis, MD; Perry G. Pernicano, MD Baylor College of Medicine, Houston, TX : Nicola Hanania, MD, MS; Mustafa Atik, MD; Aladin Boriek, PhD; Kalpatha Guntupalli, MD; Elizabeth Guy, MD; Amit Parulekar, MD; Brigham and Women’s Hospital, Boston, MA : Dawn L. DeMeo, MD, MPH; Craig Hersh, MD, MPH; Francine L. Jacobson, MD, MPH; George Washko, MD Columbia University, New York, NY : R. Graham Barr, MD, DrPH; John Austin, MD; Belinda D’Souza, MD; Byron Thomashow, MD Duke University Medical Center, Durham, NC : Neil MacIntyre, Jr., MD; H. Page McAdams, MD; Lacey Washington, MD HealthPartners Research Institute, Minneapolis, MN : Charlene McEvoy, MD, MPH; Joseph Tashjian, MD Johns Hopkins University, Baltimore, MD : Robert Wise, MD; Robert Brown, MD; Nadia N. Hansel, MD, MPH; Karen Horton, MD; Allison Lambert, MD, MHS; Nirupama Putcha, MD, MHS Lundquist Institute for Biomedical Innovation at Harbor UCLA Medical Center, Torrance, CA : Richard Casaburi, PhD, MD; Alessandra Adami, PhD; Matthew Budoff, MD; Hans Fischer, MD; Janos Porszasz, MD, PhD; Harry Rossiter, PhD; William Stringer, MD Michael E. DeBakey VAMC, Houston, TX: Amir Sharafkhaneh, MD, PhD; Charlie Lan, DO Minneapolis VA : Christine Wendt, MD; Brian Bell, MD; Ken M. Kunisaki, MD, MS Morehouse School of Medicine, Atlanta, GA : Eric L. Flenaugh, MD; Hirut Gebrekristos, PhD; Mario Ponce, MD; Silanath Terpenning, MD; Gloria Westney, MD, MS National Jewish Health, Denver, CO : Russell Bowler, MD, PhD; David A. Lynch, MB Reliant Medical Group, Worcester, MA : Richard Rosiello, MD; David Pace, MD Temple University, Philadelphia, PA : Gerard Criner, MD; David Ciccolella, MD; Francis Cordova, MD; Chandra Dass, MD; Gilbert D’Alonzo, DO; Parag Desai, MD; Michael Jacobs, PharmD; Steven Kelsen, MD, PhD; Victor Kim, MD; A. James Mamary, MD; Nathaniel Version Date: March 26, 2021 Marchetti, DO; Aditi Satti, MD; Kartik Shenoy, MD; Robert M. Steiner, MD; Alex Swift, MD; Irene Swift, MD; Maria Elena Vega-Sanchez, MD University of Alabama, Birmingham, AL : Mark Dransfield, MD; William Bailey, MD; Surya P. Bhatt, MD; Anand Iyer, MD; Hrudaya Nath, MD; J. Michael Wells, MD University of California, San Diego, CA : Douglas Conrad, MD; Xavier Soler, MD, PhD; Andrew Yen, MD University of Iowa, Iowa City, IA : Alejandro P. Comellas, MD; Karin F. Hoth, PhD; John Newell, Jr., MD; Brad Thompson, MD University of Michigan, Ann Arbor, MI : MeiLan K. Han, MD MS; Ella Kazerooni, MD MS; Wassim Labaki, MD MS; Craig Galban, PhD; Dharshan Vummidi, MD University of Minnesota, Minneapolis, MN : Joanne Billings, MD; Abbie Begnaud, MD; Tadashi Allen, MD University of Pittsburgh, Pittsburgh, PA : Frank Sciurba, MD; Jessica Bon, MD; Divay Chandra, MD, MSc; Joel Weissfeld, MD, MPH University of Texas Health, San Antonio, San Antonio, TX : Antonio Anzueto, MD; Sandra Adams, MD; Diego Maselli-Caceres, MD; Mario E. Ruiz, MD; Harjinder Singh Data and Code Availability LTRC genotyping data are available on dbGaP with accession number phs001662.v1.p1 LTRC RNA-seq data are available through TOPMed, https://topmed.nhlbi.nih.gov . COPDGene data are available on dbGaP with accession numbers phs000179 and phs000765. Funding/Acknowledgements This work was funded by K01HL157613, R01HL157879, P01HL114501, X01HL139404, R01HL124233, R01HL126596, R01HL153248, R01HL149861, R01 HL111527HL135142, and NIGMS R35 GM140844. Molecular data for the Trans-Omics in Precision Medicine (TOPMed) program was supported by the National Heart, Lung and Blood Institute (NHLBI). Whole Genome Sequencing and RNASeq for "NHLBI TOPMed: The Lung Tissue Research Consortium (phs001662)” was performed at Northwest Genome Center (NWGC, HHSN268201600032I, RNASeq) and Broad Genomics (HHSN268201600034I, WGS) Core support including centralized genomic read mapping and genotype calling, along with variant quality metrics and filtering were provided by the TOPMed Informatics Research Center (3R01HL-117626-02S1; contract HHSN268201800002I). Core support including phenotype harmonization, data management, sample-identity QC, and general program coordination were provided by the TOPMed Data Coordinating Center (R01HL-120393; U01HL-120393; contract HHSN268201800001I). We gratefully acknowledge the studies and participants who provided biological samples and data for TOPMed.. The COPDGene study ( NCT00608764 ) is supported by grants from the NHLBI (U01HL089897 and U01HL089856), by NIH contract 75N92023D00011, and by the COPD Foundation through contributions made to an Industry Advisory Committee that has included AstraZeneca, Bayer Pharmaceuticals, Boehringer-Ingelheim, Genentech, GlaxoSmithKline, Novartis, Pfizer and Sunovion. This study utilized biological specimens and data provided by the Lung Tissue Research Consortium (LTRC) supported by the National Heart, Lung, and Blood Institute (NHLBI). Footnotes Author contributions References 1. ↵ Sakornsakolpat P , Prokopenko D , Lamontagne M , Reeve NF , Guyatt AL , Jackson VE , et al. Genetic landscape of chronic obstructive pulmonary disease identifies heterogeneous cell- type and phenotype associations . Nat Genet . 2019 ; 51 ( 3 ): 494 – 505 . Epub 2019/02/26. doi: 10.1038/s41588-018-0342-2 . PubMed PMID: 30804561 ; PubMed Central PMCID: PMCPMC6546635 . OpenUrl CrossRef PubMed 2. ↵ Cohen BH , Ball WC , Jr. , Brashears S , Diamond EL , Kreiss P , Levy DA , et al. Risk factors in chronic obstructive pulmonary disease (COPD) . Am J Epidemiol . 1977 ; 105 ( 3 ): 223 – 32 . Epub 1977/03/01. doi: 10.1093/oxfordjournals.aje.a112378 . PubMed PMID: 300564 . OpenUrl CrossRef PubMed Web of Science 3. Kueppers F , Miller RD , Gordon H , Hepper NG , Offord K . Familial prevalence of chronic obstructive pulmonary disease in a matched pair study . Am J Med . 1977 ; 63 ( 3 ): 336 – 42 . Epub 1977/09/01. doi: 10.1016/0002-9343(77)90270-4 . PubMed PMID: 302643 . OpenUrl CrossRef PubMed Web of Science 4. McCloskey SC , Patel BD , Hinchliffe SJ , Reid ED , Wareham NJ , Lomas DA . Siblings of patients with severe chronic obstructive pulmonary disease have a significant risk of airflow obstruction . Am J Respir Crit Care Med . 2001 ; 164 ( 8 Pt 1):1419-24. Epub 2001/11/13. doi: 10.1164/ajrccm.164.8.2105002 . PubMed PMID: 11704589 . OpenUrl CrossRef PubMed Web of Science 5. ↵ Silverman EK , Chapman HA , Drazen JM , Weiss ST , Rosner B , Campbell EJ , et al. Genetic epidemiology of severe, early-onset chronic obstructive pulmonary disease. Risk to relatives for airflow obstruction and chronic bronchitis . Am J Respir Crit Care Med . 1998 ; 157 ( 6 Pt 1):1770-8. Epub 1998/06/25. doi: 10.1164/ajrccm.157.6.9706014 . PubMed PMID: 9620904 . OpenUrl CrossRef PubMed Web of Science 6. ↵ Hobbs BD , de Jong K , Lamontagne M , Bosse Y , Shrine N , Artigas MS , et al. Genetic loci associated with chronic obstructive pulmonary disease overlap with loci for lung function and pulmonary fibrosis . Nat Genet . 2017 ; 49 ( 3 ): 426 – 32 . Epub 2017/02/07. doi: 10.1038/ng.3752 . PubMed PMID: 28166215 ; PubMed Central PMCID: PMCPMC5381275 . OpenUrl CrossRef PubMed 7. Shrine N , Guyatt AL , Erzurumluoglu AM , Jackson VE , Hobbs BD , Melbourne CA , et al. New genetic signals for lung function highlight pathways and chronic obstructive pulmonary disease associations across multiple ancestries . Nat Genet . 2019 ; 51 ( 3 ): 481 – 93 . Epub 2019/02/26. doi: 10.1038/s41588-018-0321-7 . PubMed PMID: 30804560 ; PubMed Central PMCID: PMCPMC6397078 . OpenUrl CrossRef PubMed 8. ↵ Shrine N , Izquierdo AG , Chen J , Packer R , Hall RJ , Guyatt AL , 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 – 22 . Epub 2023/03/15. doi: 10.1038/s41588-023-01314-0 . PubMed PMID: 36914875 ; PubMed Central PMCID: PMCPMC10011137 research projects outside of the submitted work. I.P.H. has funded research collaborations with GSK, Boehringer Ingelheim and Orion. M.H.C. has received grant funding from GSK and Bayer, and speaking or consulting fees from AstraZeneca, Illumina and Genentech. B.D.H. has received grant funding from Bayer and speaking or consulting fees from AstraZeneca. I.S. has funded research collaborations with GSK, Boehringer Ingelheim and Orion outside of the submitted work. R.J.P., M.D.T., C.J. and L.V.W. have a funded research collaboration with Orion for collaborative research projects outside of the submitted work. The other authors declare no competing interests . OpenUrl CrossRef PubMed 9. ↵ Gamazon ER , Segre AV , van de Bunt M , Wen X , Xi HS , Hormozdiari F , et al. Using an atlas of gene regulation across 44 human tissues to inform complex disease- and trait-associated variation . Nat Genet . 2018 ; 50 ( 7 ): 956 – 67 . Epub 2018/06/30. doi: 10.1038/s41588-018-0154-4 . PubMed PMID: 29955180 ; PubMed Central PMCID: PMCPMC6248311 . OpenUrl CrossRef PubMed 10. ↵ Saferali A , Yun JH , Parker MM , Sakornsakolpat P , Chase RP , Lamb A , et al. Analysis of genetically driven alternative splicing identifies FBXO38 as a novel COPD susceptibility gene . PLoS Genet . 2019 ; 15 ( 7 ): e1008229 . Epub 2019/07/04. doi: 10.1371/journal.pgen.1008229 . PubMed PMID: 31269066 ; PubMed Central PMCID: PMCPMC6634423 . OpenUrl CrossRef PubMed 11. ↵ Barbeira AN , Dickinson SP , Bonazzola R , Zheng J , Wheeler HE , Torres JM , et al. Exploring the phenotypic consequences of tissue specific gene expression variation inferred from GWAS summary statistics . Nat Commun . 2018 ; 9 ( 1 ): 1825 . Epub 2018/05/10. doi: 10.1038/s41467-018-03621-1 . PubMed PMID: 29739930 ; PubMed Central PMCID: PMCPMC5940825 . OpenUrl CrossRef PubMed 12. ↵ Regan EA , Hokanson JE , Murphy JR , Make B , Lynch DA , Beaty TH , et al. Genetic epidemiology of COPD (COPDGene) study design . COPD . 2010 ; 7 ( 1 ): 32 – 43 . Epub 2010/03/11. doi: 10.3109/15412550903499522 . PubMed PMID: 20214461 ; PubMed Central PMCID: PMCPMC2924193 . OpenUrl CrossRef PubMed Web of Science 13. ↵ Ghosh AJ , Hobbs BD , Yun JH , Saferali A , Moll M , Xu Z , et al. Lung tissue shows divergent gene expression between chronic obstructive pulmonary disease and idiopathic pulmonary fibrosis . Respir Res . 2022 ; 23 ( 1 ): 97 . Epub 2022/04/23. doi: 10.1186/s12931-022-02013-w . PubMed PMID: 35449067 ; PubMed Central PMCID: PMCPMC9026726 . OpenUrl CrossRef PubMed 14. ↵ Parker MM , Chase RP , Lamb A , Reyes A , Saferali A , Yun JH , et al. RNA sequencing identifies novel non-coding RNA and exon-specific effects associated with cigarette smoking . BMC Medical Genomics . 2017 ; 10 ( 1 ): 58 -. OpenUrl 15. ↵ Patro R , Duggal G , Love MI , Irizarry RA , Kingsford C . Salmon provides fast and bias- aware quantification of transcript expression . Nat Methods . 2017 ; 14 ( 4 ): 417 – 9 . Epub 2017/03/07. doi: 10.1038/nmeth.4197 . PubMed PMID: 28263959 ; PubMed Central PMCID: PMCPMC5600148 . OpenUrl CrossRef PubMed 16. ↵ Soneson C , Love MI , Robinson MD . Differential analyses for RNA-seq: transcript-level estimates improve gene-level inferences . F1000Res . 2015 ;4:1521. Epub 2016/03/01. doi: 10.12688/f1000research.7563.2 . PubMed PMID: 26925227 ; PubMed Central PMCID: PMCPMC4712774 . OpenUrl CrossRef PubMed 17. ↵ Li YI , Knowles DA , Humphrey J , Barbeira AN , Dickinson SP , Im HK , et al. Annotation- free quantification of RNA splicing using LeafCutter . Nat Genet . 2018 ; 50 ( 1 ): 151 – 8 . Epub 2017/12/13. doi: 10.1038/s41588-017-0004-9 . PubMed PMID: 29229983 ; PubMed Central PMCID: PMCPMC5742080 . OpenUrl CrossRef PubMed 18. ↵ Risso D , Ngai J , Speed TP , Dudoit S . Normalization of RNA-seq data using factor analysis of control genes or samples . Nat Biotechnol . 2014 ; 32 ( 9 ): 896 – 902 . Epub 2014/08/26. doi: 10.1038/nbt.2931 . PubMed PMID: 25150836 ; PubMed Central PMCID: PMCPMC4404308 . OpenUrl CrossRef PubMed 19. ↵ Taylor-Weiner A , Aguet F , Haradhvala NJ , Gosai S , Anand S , Kim J , et al. Scaling computational genomics to millions of individuals with GPUs . Genome Biol . 2019 ; 20 ( 1 ): 228 . Epub 2019/11/05. doi: 10.1186/s13059-019-1836-7 . PubMed PMID: 31675989 ; PubMed Central PMCID: PMCPMC6823959 GG have filed a patent application related to the methods described in this work. GG receives research funds from IBM and Pharmacyclics. GG is an inventor on multiple bioinformatics-related patent applications. EMV is a consultant for Tango Therapeutics, Genome Medical, Invitae, Foresite Capital, and Illumina. EMV received research support from Novartis and BMS, as well as travel support from Roche/Genentech. EMV is an equity holder of Syapse, Tango Therapeutics, and Genome Medical. EMV holds stock in Microsoft. Broad permits non-profit institutions and government agencies to operate under Broad patents to conduct internal research, including sponsored research to the extent such research does not include the production or manufacture of products for sale or offer for sale or performance of commercial services for a fee. OpenUrl CrossRef PubMed 20. ↵ Cho MH , Castaldi PJ , Wan ES , Siedlinski M , Hersh CP , Demeo DL , et al. A genome- wide association study of COPD identifies a susceptibility locus on chromosome 19q13 . Hum Mol Genet . 2012 ; 21 ( 4 ): 947 – 57 . Epub 2011/11/15. doi: 10.1093/hmg/ddr524 . PubMed PMID: 22080838 ; PubMed Central PMCID: PMCPMC3298111 . OpenUrl CrossRef PubMed Web of Science 21. ↵ Wang K , Li M , Hakonarson H . ANNOVAR: functional annotation of genetic variants from high-throughput sequencing data . Nucleic Acids Res . 2010 ; 38 ( 16 ): e164 . Epub 2010/07/06. doi: 10.1093/nar/gkq603 . PubMed PMID: 20601685 ; PubMed Central PMCID: PMCPMC2938201 . OpenUrl CrossRef PubMed 22. ↵ Giambartolomei C , Zhenli Liu J , Zhang W , Hauberg M , Shi H , Boocock J , et al. A Bayesian framework for multiple trait colocalization from summary association statistics . Bioinformatics . 2018 ; 34 ( 15 ): 2538 – 45 . Epub 2018/03/27. doi: 10.1093/bioinformatics/bty147 . PubMed PMID: 29579179 ; PubMed Central PMCID: PMCPMC6061859 . OpenUrl CrossRef PubMed 23. ↵ Zou Y , Carbonetto P , Xie D , Wang G , Stephens M . Fast and flexible joint fine-mapping of multiple traits via the Sum of Single Effects model . bioRxiv . 2023 . Epub 2023/07/10. doi: 10.1101/2023.04.14.536893 . PubMed PMID: 37425935 ; PubMed Central PMCID: PMCPMC10327118 . OpenUrl Abstract / FREE Full Text 24. ↵ Li YI , Knowles DA , Humphrey J , Barbeira AN , Dickinson SP , Im HK , et al. Annotation- free quantification of RNA splicing using LeafCutter . Nature Genetics . 2018 ; 50 ( 1 ): 151 ,Äì8-,Äì8. OpenUrl CrossRef PubMed 25. ↵ Saferali A , Kim W , Xu Z , Chase RP , Cho MH , Laederach A , et al. Colocalization analysis of 3’ UTR alternative polyadenylation quantitative trait loci reveals novel mechanisms underlying associations with lung function . Hum Mol Genet . 2024 . Epub 2024/04/04. doi: 10.1093/hmg/ddae055 . PubMed PMID: 38569558 . OpenUrl CrossRef PubMed 26. ↵ Saferali A , Xu Z , Sheynkman GM , Hersh CP , Cho MH , Silverman EK , et al. Characterization of a COPD-Associated NPNT Functional Splicing Genetic Variant in Human Lung Tissue via Long-Read Sequencing . medRxiv . 2020 . Epub 2020/11/12. doi: 10.1101/2020.10.20.20203927 . PubMed PMID: 33173926 ; PubMed Central PMCID: PMCPMC7654922 . OpenUrl Abstract / FREE Full Text 27. ↵ Morrow JD , Zhou X , Lao T , Jiang Z , Demeo DL , Cho M , et al. Functional interactors of three genome-wide association study genes are differentially expressed in severe chronic obstructive pulmonary disease lung tissue . Scientific reports . 2017 ; 7 ( 1 ): 44232 -. OpenUrl 28. ↵ Hormozdiari F , van de Bunt M , Segre AV , Li X , Joo JWJ , Bilow M , et al. Colocalization of GWAS and eQTL Signals Detects Target Genes . American Journal of Human Genetics . 2016 ; 99 ( 6 ): 1245 ,Äì60-,Äì60. OpenUrl CrossRef PubMed 29. ↵ Jaganathan K , Kyriazopoulou Panagiotopoulou S , McRae JF , Darbandi SF , Knowles D , Li YI , et al. Predicting Splicing from Primary Sequence with Deep Learning . Cell . 2019 ; 176 ( 3 ): 535 – 48 e24. Epub 2019/01/22. doi: 10.1016/j.cell.2018.12.015 . PubMed PMID: OpenUrl CrossRef PubMed 30. ↵ pmid: 30661751 . OpenUrl CrossRef PubMed 30. ↵ Zhang Z , Xin D , Wang P , Zhou L , Hu L , Kong X , et al. Noisy splicing, more than expression regulation, explains why some exons are subject to nonsense-mediated mRNA decay . BMC Biol . 2009 ; 7 : 23 . Epub 2009/05/16. doi: 10.1186/1741-7007-7-23 . PubMed PMID: 19442261 ; PubMed Central PMCID: PMCPMC2697156 . OpenUrl CrossRef PubMed 31. ↵ Kipreos ET , Pagano M . The F-box protein family . Genome Biol . 2000 ; 1 (5):REVIEWS3002. Epub 2001/02/24. doi: 10.1186/gb-2000-1-5-reviews3002 . PubMed PMID: 11178263 ; PubMed Central PMCID: PMCPMC138887 . OpenUrl CrossRef PubMed 32. ↵ Smaldone S , Laub F , Else C , Dragomir C , Ramirez F . Identification of MoKA, a novel F- box protein that modulates Kruppel-like transcription factor 7 activity . Mol Cell Biol . 2004 ; 24 ( 3 ): 1058 – 69 . Epub 2004/01/20. doi: 10.1128/MCB.24.3.1058-1069.2004 . PubMed PMID: 14729953 ; PubMed Central PMCID: PMCPMC321422 . OpenUrl Abstract / FREE Full Text 33. ↵ Smaldone S , Ramirez F . Multiple pathways regulate intracellular shuttling of MoKA, a co-activator of transcription factor KLF7 . Nucleic Acids Res . 2006 ; 34 ( 18 ): 5060 – 8 . Epub 2006/09/23. doi: 10.1093/nar/gkl659 . PubMed PMID: 16990251 ; PubMed Central PMCID: PMCPMC1636432 . OpenUrl CrossRef PubMed 34. ↵ Dunbar AJ , Goddard C . Structure-function and biological role of betacellulin . Int J Biochem Cell Biol . 2000 ; 32 ( 8 ): 805 – 15 . Epub 2000/08/15. doi: 10.1016/s1357-2725(00)00028-5 . PubMed PMID: 10940639 . OpenUrl CrossRef PubMed Web of Science 35. ↵ Serban KA , Pratte KA , Strange C , Sandhaus RA , Turner AM , Beiko T , et al. Unique and shared systemic biomarkers for emphysema in Alpha-1 Antitrypsin deficiency and chronic obstructive pulmonary disease . EBioMedicine . 2022 ; 84 : 104262 . Epub 2022/09/27. doi: 10.1016/j.ebiom.2022.104262 . PubMed PMID: 36155958 ; PubMed Central PMCID: PMCPMC9507992 . OpenUrl CrossRef PubMed 36. Chen H , Song Z , Qian M , Bai C , Wang X . Selection of disease-specific biomarkers by integrating inflammatory mediators with clinical informatics in AECOPD patients: a preliminary study . J Cell Mol Med . 2012 ; 16 ( 6 ): 1286 – 97 . Epub 2011/09/03. doi: 10.1111/j.1582-4934.2011.01416.x . PubMed PMID: 21883889 ; PubMed Central PMCID: PMCPMC3823081 . OpenUrl CrossRef PubMed View the discussion thread. Back to top Previous Next Posted July 08, 2024. 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 Overlap between COPD genetic association results and transcriptional quantitative trait loci 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 Overlap between COPD genetic association results and transcriptional quantitative trait loci Aabida Saferali , Wonji Kim , Robert P. Chase , NHLBI TransOmics in Precision Medicine (TOPMed) , Chris Vollmers , Edwin K. Silverman , Michael H. Cho , Peter J. Castaldi , Craig P. Hersh medRxiv 2024.07.08.24310079; doi: https://doi.org/10.1101/2024.07.08.24310079 Share This Article: Copy Citation Tools Overlap between COPD genetic association results and transcriptional quantitative trait loci Aabida Saferali , Wonji Kim , Robert P. Chase , NHLBI TransOmics in Precision Medicine (TOPMed) , Chris Vollmers , Edwin K. Silverman , Michael H. Cho , Peter J. Castaldi , Craig P. Hersh medRxiv 2024.07.08.24310079; doi: https://doi.org/10.1101/2024.07.08.24310079 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 (573) Allergy and Immunology (865) Anesthesia (302) Cardiovascular Medicine (4453) Dentistry and Oral Medicine (444) Dermatology (383) Emergency Medicine (609) Endocrinology (including Diabetes Mellitus and Metabolic Disease) (1515) Epidemiology (15242) Forensic Medicine (30) Gastroenterology (1131) Genetic and Genomic Medicine (6615) Geriatric Medicine (669) Health Economics (1001) Health Informatics (4552) Health Policy (1372) Health Systems and Quality Improvement (1614) Hematology (543) HIV/AIDS (1270) Infectious Diseases (except HIV/AIDS) (15929) Intensive Care and Critical Care Medicine (1106) Medical Education (624) Medical Ethics (147) Nephrology (670) Neurology (6625) Nursing (346) Nutrition (999) Obstetrics and Gynecology (1148) Occupational and Environmental Health (957) Oncology (3344) Ophthalmology (979) Orthopedics (369) Otolaryngology (421) Pain Medicine (436) Palliative Medicine (130) Pathology (665) Pediatrics (1696) Pharmacology and Therapeutics (693) Primary Care Research (714) Psychiatry and Clinical Psychology (5461) Public and Global Health (9252) Radiology and Imaging (2207) Rehabilitation Medicine and Physical Therapy (1371) Respiratory Medicine (1197) Rheumatology (597) Sexual and Reproductive Health (715) Sports Medicine (530) Surgery (714) 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:'a02e7a1dbf65f48a',t:'MTc3OTk4NDA3Ng=='};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())}}}})();