Identification of SENP7 and UTF1/VENTX as new loci influencing clustered protocadherin methylation across blood and brain using a genome-wide association study

Identification of SENP7 and UTF1/VENTX as new loci influencing clustered protocadherin methylation across blood and brain using a genome-wide association study | bioRxiv /* */ /* */ <!-- <!-- /*! * 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-M677548'); Skip to main content Home About Submit ALERTS / RSS Search for this keyword Advanced Search New Results Identification of SENP7 and UTF1 / VENTX as new loci influencing clustered protocadherin methylation across blood and brain using a genome-wide association study Yunfeng Liu , Maja Vukic , View ORCID Profile Eilis Hannon , Hailiang Mei , BIOS Consortium , View ORCID Profile Jonathan Mill , Lucia Daxinger , View ORCID Profile Bastiaan T. Heijmans doi: https://doi.org/10.1101/2024.12.19.629385 Yunfeng Liu 1 Molecular Epidemiology, Department of Biomedical Data Sciences, Leiden University Medical Center , 2333 ZC, Leiden, The Netherlands Find this author on Google Scholar Find this author on PubMed Search for this author on this site Maja Vukic 2 Department of Human Genetics, Leiden University Medical Center , Leiden 2333 ZC, The Netherlands Find this author on Google Scholar Find this author on PubMed Search for this author on this site Eilis Hannon 3 University of Exeter Medical School, University of Exeter , Exeter, United Kingdom Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Eilis Hannon Hailiang Mei 4 Sequencing Analysis Support Core, Department of Biomedical Data Sciences , Leiden, the Netherlands Find this author on Google Scholar Find this author on PubMed Search for this author on this site Jonathan Mill 3 University of Exeter Medical School, University of Exeter , Exeter, United Kingdom Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Jonathan Mill Lucia Daxinger 2 Department of Human Genetics, Leiden University Medical Center , Leiden 2333 ZC, The Netherlands Find this author on Google Scholar Find this author on PubMed Search for this author on this site Bastiaan T. Heijmans 1 Molecular Epidemiology, Department of Biomedical Data Sciences, Leiden University Medical Center , 2333 ZC, Leiden, The Netherlands Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Bastiaan T. Heijmans For correspondence: b.t.heijmans{at}lumc.nl Abstract Full Text Info/History Metrics Supplementary material Preview PDF Summary The epigenetic regulation of clustered protocadherin (c PCDH ) genes is tightly linked to their function as specific cell surface barcodes for neural self-nonself discrimination. Differential c PCDH DNA methylation in both blood and brain has been implicated in diverse human traits and diseases ranging from BMI, aging, cancer and brain disorders. However, the unique regulation of c PCDH methylation remains poorly understood. Therefore, we performed a genome-wide association study to evaluate the association of >7 million genetic variants with DNA methylation at 607 c PCDH CpGs measured in whole blood of 3777 individuals and validated findings in prefrontal cortex samples obtained from 523 brain donors. We observed concordant c PCDH methylation patterns in blood and prefrontal cortex, which switched between hypo-, intermediate and hypermethylation over short distances with the former overlapping with the promoter regions of each c PCDH member. Through methylation quantitative trait locus (meQTL) analysis in trans , we first confirmed the broad effect of the candidate gene SMCHD1 on c PCDH methylation in blood which validated in prefrontal cortex. Through a genome-wide analysis, we next identified the SENP7 and UTF1 / VENTX loci to have widespread, subcluster-specific effects on c PCDH methylation in blood which was validated in prefrontal cortex. While SENP7 can indirectly affect DNA methylation through the deSUMOylation of the chromatin repressor KAP1 , UTF1 and VENTX are two genes involved in embryonic development not previously implicated in epigenetic regulation. Our findings shed new light on the processes involved in c PCDH methylation that may underlie associations with disease. Introduction A broad range of human diseases and traits have been linked to changes in epigenetic regulation of the clustered protocadherin genes (c PCDH , mapping to chromosome 5q31) 1 . Epigenome-wide association studies reported differential methylation for BMI 2 , brain disorders 3 – 6 and age 7 , 8 , while c PCDH also shows DNA methylation differences in multiple forms of cancer 9 – 11 . In addition, aberrant c PCDH methylation is characteristic for patients as affected by the immunodeficiency, centromeric region instability, facial anomalies (ICF) syndrome 12 and facioscapulohumeral muscular dystrophy (FSHD) 13 . These epigenetic associations resulted from the study of various cell types including blood and brain, although c PCDH expression is predominantly observed in brain. Contrasting these well-described disease associations is the still limited insight in the regulation of c PCDH methylation. In humans, the more than 50 clustered PCDHA , PCDHB and PCDHG genes together form a 1Mb locus, referred to as c PCDH genes. In the brain, the expression of the c PCDH genes is controlled by a unique combination of regulatory mechanisms. These include CCTC binding factor (CTCF)/cohesion mediated chromatin looping 14 , 15 , histone modifications 16 , 17 and DNA methylation 18 . In each neuronal cell, the exact tuning of these mechanisms results in the stochastic expression of a different subset of c PCDH gene members 19 . The resulting combination serves as specific cell surface barcode that help neurons distinguish between self and nonself 20 . DNA methylation of c PCDH gene promoters play a key role in the stochastic expression of c PCDH members 18 . Specifically, methylation of the CpG dinucleotide at c PCDH promoters precludes CTCF binding, thus disrupting the formation of long- range chromatin loops 14 . The regulation of c PCDH methylation is only partly understood in humans. Studies in mice, however, identified various genes involved. Two well-described examples are DNMT3B and SMCHD1 . DNMT3B regulates the stochastic expression of c PCDH members through mediating differential methylation of promoters in neurons 18 , while SMCHD1 is required for c PCDH methylation and its loss induces alterations in c PCDH expression 21 , 22 . Two more recently discovered include the WAPL gene 23 , which functions as a rheostat of c PCDH member diversity, and we reported the role of the CDCA7 gene 24 , which regulates c PCDH methylation and expression frequency. Human studies are necessary to shed light on the origin of differential c PCDH methylation implicated in human traits and diseases and may also indicate additional mechanisms underlying the generation of cell surface barcodes that is unique to c PCDH genes. To map loci involved in the epigenetic regulation of c PCDH genes in humans, we performed a genome-wide analysis to discover common genetic variants that are associated with c PCDH methylation in blood (n=3777) followed by validation of these associations in prefrontal cortex (n=523). We not only found that the candidate gene SMCHD1 locus has widespread effects on c PCDH methylation in blood and brain, but also report two new loci to be involved, namely SENP7 , a gene involved in deSUMOylation 25 , and the UTF1 / VENTX locus, two genes involved in embryonic development 26 , 27 . Methods Discovery Cohorts The discovery cohorts in this study was based on the Biobank-based Integrative Omics Studies (BIOS) Consortium, which comprises six Dutch biobanks: Cohort on Diabetes and Atherosclerosis Maastricht (CODAM) 28 , LifeLines (LL) 29 , Leiden Longevity Study (LLS) 30 , Netherlands Twin Register (NTR) 31 , Rotterdam Study (RS) 32 , and the Prospective ALS Study Netherlands (PAN) 33 . The data we analyzed consists of 3777 unrelated individuals for whom genotype data and DNA methylation data were available, and for 3013 individuals, RNA-seq data were available ( Supplementary Data 1, Table S1 ). Genotype data, DNA methylation data and gene expression data were all measured in whole blood. The Human Genotyping facility (HuGe-F, Erasmus MC, Rotterdam, The Netherlands, http://www.glimdna.org ) generated the methylation and RNA-sequencing data. Genotype data were measured per cohort individually. Details on the data generation can be found in the individual papers—CODAM 34 , LL 29 , LLS 35 , NTR 36 , RS 32 , and PAN 33 . The genotype data were harmonized towards the Genome of the Netherlands (GoNL) using Genotype Harmonizer 37 and subsequently imputed per cohort using MaCH 38 with the Haplotype Reference Consortium (HRCv1.1) panel 39 . For each cohort, SNPs with R 2 < 0.3 and call rate < 0.95 were removed, and then VCFtools 40 was used to remove SNPs with Hardy-Weinberg equilibrium P-value < 10 −4 . After merging the cohorts, SNPs with minor allele frequency < 0.01 were removed. These imputation and filtering steps resulted in 7,751,736 SNPs that passed quality control in each of the datasets. DNA methylation data of whole blood samples were obtained from bisulfite-converting 500 ng of genomic DNA using the Zymo EZ DNA Methylation kit (Zymo Research, Irvine, CA, USA). Next, 4 μl of bisulfite-converted DNA was hybridized on the Illumina HumanMethylation450 array according to the manufacturer’s protocol (Illumina, San Diego, CA, USA). Preprocessing and normalization of the data were done as described in DNAmArray workflow previously developed by our group ( https://molepi.github.io/DNAmArray_workflow/ ). Briefly, original IDAT files were imported into by R package minfi 41 , followed by sample-level quality control (QC) was performed using MethylAid 42 . Filtering of probes was based on detection P value ( P < 0.01), number of beads available (≤ 2), or zero values for signal intensity. Normalization was done using functional normalization as implemented in minfi 41 , using five principal components extracted using the control probes for normalization. All samples or probes with more than 5% missing were excluded. In addition, probes located on sex chromosomes, or that overlap with known common genetic variants or ambiguously mapping or cross-reactive recommended by Zhou et al were all removed for the reliability of analysis 43 . After these filtering steps, our final dataset consisted of 412,373 probes measured in 3777 samples. To exclude a negative impact of non-normal distributions and outliers on the validity of our results, DNA methylation data were transformed by rank-inverse normal (RIN) transformation for each cohort 44 – 46 . Detailed information on the generation and processing of the RNA-seq data can be found in previous work 47 . In short, globin transcripts were removed from whole blood RNA using the Ambion GLOBINclear kit and subsequently processed for RNA-sequencing using the Illumina TruSeq version 2 library preparation kit. RNA libraries were paired-end sequenced using Illumina’s HiSeq 2000 platform with a read length of 2 × 50 bp, pooling 10 samples per lane. Reads which passed the chastity filter were extracted with CASAVA. Quality control was done in three steps: initial QC was performed using FastQC (v0.10.1), adaptor sequences were removed using Cutadapt, and read ends with insufficient quality were removed with Sickle. Reads were aligned to the human genome (hg19) using STAR (v2.3.0e). To avoid reference mapping bias, all GoNL SNPs ( https://www.nlgenome.nl/ ) with MAF > 0.01 in the reference genome were masked with N. Read pairs with at most 8 mismatches, mapping to at most 5 positions, were used. Gene counts were calculated by summing the total number of reads aligning to a gene’s exons according to Ensembl, version 71. Samples for which less than 70% of all reads mapped to exons were removed. For data analysis, we used log counts per million (CPM), and only used protein coding genes with sufficient expression levels (median CPM > 1), resulting in 11,769 genes. Similar to DNA methylation data, RNA-seq data were transformed by rank inverse normal (RIN) transformation for each cohort 44 – 46 . Finally, correct data linkage of genotype, DNA methylation and RNA-seq data was verified using OmicsPrint 48 . Validation cohorts Data generated on tissue from the Brains for Dementia Research (BDR) cohort, which consists of a network of six dementia research centers across England and Wales (based at Bristol, Cardiff, King’s College London, Manchester, Oxford, and Newcastle Universities) and five brain banks (brain donations from Cardiff are banked at King’s College London) 49 , was used to validate our results. Briefly, participants >65 years of age were recruited using both national and local press, TV and radio coverage as well as at memory clinics and support groups. The cohort includes those with and without dementia and covers the full range of dementia diagnoses. Participants underwent a series of longitudinal cognitive and psychometric assessments and gave written informed consent for the use of tissue samples and clinical information for research purposes. We selected samples from the BDR cohort for which DNA methylation data and genotype data were all available and for which all of the data passed quality control (QC), totaling 523 prefrontal cortex samples for subsequent validation analysis ( Supplementary Data 1, Table S1 ). Details of DNA methylation and genetic data generation, processing, quality control and normalization from BDR cohort can be found in the original manuscript 50 , 51 . Genotype data from BDR cohort were measured on the NeuroChip array which is a custom Illumina genotyping array with an extensive genome-wide backbone (n=306,670 variants) and custom content covering 179,467 variants specific to neurological diseases 52 . Genotype calling was performed using GenomeStudio (v2.0, Illumina) and quality control was completed using PLINK1.9 53 . The genetic data were then imputed by the Michigan Imputation Server 54 ( https://imputationserver.sph.umich.edu/index.html#! ) which uses Eagle2 55 to phase haplotypes, and Minimac4 ( https://genome.sph.umich.edu/wiki/Minimac4 ) with the most recent 1000 Genomes reference panel (phase 3, version 5). Finally, imputed SNPs with minor allele frequency < 0.05, R 2 INFO score < 0.5, Hardy-Weinberg equilibrium P-value < 10 −4 and call rate < 0.95 were excluded. All samples with more than 5% missing were also excluded. The final quality controlled dataset of genotype consisted of 6,607,832 SNPs. In short, DNA methylation data was generated on the dorsolateral prefrontal cortex [DLPFC] from each BDR donor. DNA was isolated from ∼100mg of tissue using the Qiagen AllPrep DNA/RNA 96 Kit (Qiagen, cat no.80311) following tissue disruption using BeadBug 1.5mm Zirconium beads (Sigma Aldrich, cat no. Z763799) in a 96-well Deep Well Plate (Fisher Scientific, cat no. 12194162) shaking at 2500 rpm for 5min. Genome-wide DNA methylation was profiled using the Illumina EPIC DNA methylation array (Illumina Inc.), which interrogates >850,000 DNA methylation sites across the genome 56 . After stringent data quality control using the wateRmelon package 57 as previously described 50 , the BDR dataset consisted of DNA methylation estimates for 800,916 DNA methylation sites profiled. Genomic features annotation of c PCDH genes c PCDH genes were annotated according to 3 genomic features. First, the CpGs (hg19 genome coordinate- PCDHA :140165721-140391929, PCDHB :140430979-140627802, PCDHG : 140710252-140892546) mapping to c PCDH loci were divided into three categories based on mean DNA methylation level: hypomethylated (β < 0.25), intermediately methylated (0.25 < β 0.7). The hypomethylated and hypermethylated thresholds were chosen based on the location of the hypo- and hyper-methylated peaks in the density plots of chromosome 5 methylation in BIOS discovery data ( Figure 1A ). Second, we annotated CpGs involved according to promoters related features: promoters and non-promoters. Transcripts database (genome hg19) were first downloaded from UCSC using TxDb.Hsapiens.UCSC.hg19.knownGene package, and then promoters () function for extracting the promoters information of every c PCDH members. Promoters were annotated as 1500 bp upstream of transcription start site (TSS) to 500 bp downstream of TSS, and all remaining regions as non-promoters. Finally, unique genomic regions of c PCDH were visualized with Gviz package 58 . To test whether hypomethylated CpGs in the c PCDH loci were enriched for promoter regions, we calculated odds ratios (OR) of c PCDH hypomethylated CpGs being annotated with promoters compared to all c PCDH non-hypomethylated CpGs being annotated as promoters using a Chi-square test. Download figure Open in new tab Figure 1. Overview of c PCDH methylation patterns in blood and brain (prefrontal cortex). A Distribution of c PCDH methylation based on 607 CpGs in BIOS blood (n=3777, Illumina 450k array) and based on 747 CpGs in BDR prefrontal cortex samples (n=523, Illumina EPIC array). The thicker red line and thicker blue line represent the distribution of c PCDH methylation in blood and brain (prefrontal cortex), respectively in contrast to chromosome 5 methylation distribution (thinner blue and red lines). B Four different tracks plotted by Gviz package 58 to clearly display global methylation pattern in the c PCDH genes. First track shows methylation of 607 CpGs mapping to PCDHA (146 CpG), PCDHB (202 CpGs) and PCDHG (259 CpGs) in blood. Each red dot represents the mean methylation of one CpG in 3777 blood samples. Second track shows methylation of 747 CpGs mapping to PCDHA (199 CpG), PCDHB (240 CpGs) and PCDHG (308 CpGs) in brain (prefrontal cortex). Each blue dot represents the mean methylation of one CpG in 523 prefrontal cortex samples. Third track shows the location of promoter regions of each c PCDH member (1500 bp upstream of TSS to 500 bp downstream of TSS). Fourth track shows the genomic organization of the PCDHA , PCDHB and PCDHG gene clusters with exons. C Comparison of mean methylation level of overlapping c PCDH CpGs in blood and brain (prefrontal cortex). Pearson’s correlation coefficients are provided. Candidate gene analysis Of the 9 genes previously reported to be involved in cPCDH regulation according to mouse studies 16 , 18 , 21 – 24 , 59 , 60 and human cell lines 14 , 61 , 6 could be analyzed here. Three genes dropped out because no SNPs were available in blood ( MECP2 61 ) or brain ( WAPL 23 and SETDB1 16 ). For the remaining genes, namely SMCHD1 21 , 22 , CDCA7 24 , RAD21 14 , WIZ 59 , DNMT3B 18 and CTCF 14 , 60 , we fitted a linear regression model using R package Matrix-eQTL 62 to test association between the SNPs near the 50bp window of candidate gene and 607 CpGs mapping to the c PCDH genes measured in whole blood of 3777 unrelated individuals using the Illumina 450k array, correcting for known covariates M (age, sex, cohort, cell counts and technical batches, namely sentrix position and sample plate) and 2 unknown hidden confounders U, estimated using cate 63 . Blood cell composition was estimated by R package EpiDISH 64 and resulted in 12 broad immune cell type predictions including naïve CD4T cells, Basophils, memory CD4T cells, Memory B cells, Naive B cells, Regulatory T Cells, memory CD8 cells, naïve CD8T cells, Eosinophils, NK cells, Neutrophils and Monocytes. Neutrophils were excluded from the model to exclude collinearity so that the effect of this cell type becomes included in the intercept. For each genetic variant SNP i , this model yields 607 P-values P ij . Next, we combined all 607 P- values corresponding to one genetic variant SNP i into one overall P -value P i using the Simes procedure for multiple testing correction 65 . SNPs with an overall P -value < 1 × 10 −5 in candidate gene analysis were considered significantly associated with c PCDH methylation 66 . False discovery rate (FDR) was used to determine which of 607 CpGs were individually associated with the top SNP. Genome-wide of c PCDH methylation QTL analyses in blood For genome-wide association analyses of c PCDH methylation, the same linear regression model was fitted as for the evaluation of candidate genes but now testing the association of 7,751,736 SNPs across the genome with each of 607 CpGs mapping to the c PCDH genes measured in whole blood of 3777 unrelated individuals. Likewise, we applied Simes 65 procedure to perform multiple testing correction for 607 P-values corresponding to each genetic variant SNP i and finally resulted in 7,751,736 overall P-value. This overall P-value per SNP indicates if an SNP influences DNA methylation anywhere on c PCDH genes. SNPs at genome-wide significance level of overall P-value < 5 × 10 −8 were regarded to be associated with PCDH methylation. False discovery rate (FDR) was used to determine which of 607 individual CpGs were associated with the top SNP. Since we aimed to identify novel gene loci affecting c PCDH methylation in trans , SNPs in the c PCDH or mapping within 5MB of the cluster, defined as 5MB upstream of PCDHA transcription start sites (TSSs) to 5MB downstream of PCDHG transcription end sites (TESs), were removed from the analysis. Local ( cis ) expression QTL mapping in blood For cis -eQTL analysis in BIOS blood, we used a subset of 3031 individuals from the discovery cohort (N=3777, Supplementary Data 1, Table S1 ) for whom genetics, DNA methylation and also RNA-seq data were available. The association between the genotypes of a genetic variant SNP i with the expression levels of genes Expression j , was tested by a linear model. Similar to the trans -meQTL mapping for c PCDH genes, we corrected for known covariates M (age, sex, cohort, cell counts and technical batches, namely flowcell number), and 2 unknown hidden confounders U using cate 63 . For this study, we only focus on top SNP in four genetic loci ( SMCHD1 , OR2W3 , SENP7 and VENTX ) and tested its association with those genes that are identified as cis -eQTL according to eQTLGen consortium 67 . The Bonferroni correction was performed to the corresponding P-values P ij to identify genes associated with the genetic variant SNP i . Validation of trans -meQTL in brain To evaluate the effect of top SNP derived from blood in genetic loci on c PCDH methylation in brain, we repeated methylation QTL analysis with following statistical model using BDR cohort. where DNAm j represent 747 c PCDH methylation sites (EPIC array) matrix. M represent age, sex, experimental batch and derived brain cell proportions. Cell proportion estimates were derived from bulk cortex DNA methylation data using the Houseman method 68 , implemented with minfi functions and default parameters, incorporating the novel reference DNA methylation data generated on three Fluorescence-activated nuclei sorting (FANS)-purified nuclei populations (NeuN+, SOX10+, and NeuN–/SOX10–) from 12 DLPFC samples 50 . U represent PC1 which accounted for residual structure in the data. In brain, we tested top SNP from 6 candidate genetic loci and 3 additional genetic loci as detected in blood. For top SNP SNP top_i in each genetic locus (i = S MCHD1 , CDCA7 , RAD21 , WIZ , DNMT3B , CTCF , OR2W3 , SENP7 and VENTX ), this model yields 747 P-values P j . The validation in the brain of results in blood was assessed by two aspects: (1) The statistical consistency for detected significant CpGs in blood and brain. To test the probability of statistically significant CpGs in blood also being significant in brain, we calculated odds ratio (OR) of CpGs significant in blood to be also significant in brain. Statistical significance was evaluated using a Chi-square test or a Fisher’s exact test (if expected cell counts were < 5). (2) The consistency of effect direction for detected significant CpGs in blood or brain. Summarizing the number of CpGs significant in blood or brain with same effect direction (Positive + Negative), which included three categories of CpGs: Blood&Brain (statistically significant both in blood and brain), Blood only (only FDR significant in blood) and Brain only (only nominally significant in brain). Binomial test was used to determine whether direction of effects were concordant. Results c PCDH DNA methylation patterns are similar in blood and brain In whole blood, we evaluated methylation levels of 607 CpGs (Illumina 450k array) mapping to the c PCDH genes using a data set of 3777 samples ( Supplementary Data 1, Table S2 ). In contrast to the typical bimodal distribution of genomic DNA methylation with the majority of CpGs being either hypo- or hypermethylated, the majority of CpGs in c PCDH genes showed intermediate DNA methylation levels ( Figure 1A ). We found a similar result in brain ( Figure 1A ), where we evaluated the methylation levels of 747 CpGs (Illumina EPIC array) located in the c PCDH genes using a data set of 523 prefrontal cortex samples ( Supplementary Data 1, Table S3 ). To gain more insight in the pattern of c PCDH methylation, we first examined the mean methylation level for each CpG mapping to the PCDHA , PCDHB and PCDHG gene subclusters in blood and brain ( Figure 1B ). As shown in Figure 1B , the PCDHA and PCDHG subclusters have a similar genomic architecture where tandem arrays of alternative exons are followed by constant exons, while the PCDHB subcluster contains single exon genes. We observed that c PCDH methylation levels varied over short genomic distances between hypo-, intermediate and hypermethylation where hypomethylation coincided with promotor regions. In both blood and brain, promoter CpGs were more likely to be hypomethylated as compared with non-promoter CpGs (OR blood = 6.0, P=1.1×10 - 20 ; OR brain =4.4, P=7.9×10 - 18 ; Supplementary Data 1, Table S4 ). Finally, we tested the correlation between DNA methylation in blood and brain for the 562 overlapping CpGs. The correlation was high ranging between 0.88 for the PCDHG subcluster to 0.94 for the PCHDB subcluster ( Figure 1C ). The effect of candidate gene loci on c PCDH methylation in blood and brain The candidate genes SMCHD1 21 , 22 , CDCA7 24 , RAD21 14 , WIZ 59 , DNMT3B 18 and CTCF 14 , 60 were evaluated for an effect on c PCDH methylation in human blood and brain ( Figure 2A ). We found that top SNP rs10775431 at the SMCHD1 locus was significantly associated with c PCDH methylation in blood (P Simes =2.7×10 -6 , minimal nominal P= 4.4×10 -9 ) and affected 221 c PCDH CpGs methylation in blood (P FDR <0.05, 450k array, Supplementary Data 1, Table S5; Supplementary Data 2, Table S6 ). Of those, 205 were also measured in brain (EPIC array) and 66 (32%) were validated in brain (P<0.05; OR = 3.0, P=1.0×10 -7 ; Figure 2B , Supplementary Data 2, Table S6-S7, Table S18 ). In addition, among the 253 CpGs (available from both the 450k and EPIC array) found to be associated with the top SNP in either blood or brain, 230 (91%) had a consistent direction of effect (P=1.0x10 -8 , Supplementary Data 2, Table S6-S7 ). Interestingly, c PCDH CpGs affected by the SMCHD1 variant in blood or brain occurred across the whole cluster and were both hypo-, intermediate and hypermethylated ( Figure 2C ). Download figure Open in new tab Figure 2. Effect of 6 candidate gene loci on c PCDH methylation in blood and brain (prefrontal cortex). A We first performed trans -meQTL analysis to test the association between the SNPs near the 50bp window of candidate gene and 607 c PCDH CpGs in BIOS blood samples (n=3777). SNPs with an overall P-value < 1 × 10 −5 in candidate gene analysis were considered significantly associated with c PCDH methylation. Then the effect of top SNP in each candidate gene was validated in BDR prefrontal cortex samples (n=523). B Scatter plot of effect sizes for top SNP in 6 candidate genes on c PCDH methylation observed in blood and brain (prefrontal cortex). Green dots represent CpGs statistically significant in both blood and brain (prefrontal cortex). Red and blue dots represent CpGs statistically significant only in blood or brain (prefrontal cortex), respectively. Gray dots represent CpGs statistically significant in neither blood nor brain (prefrontal cortex). C Effect of SMCHD1 variant ( rs10775431 ) on c PCDH methylation in blood and brain (prefrontal cortex). The tracks display the P-values resulting from the statistical test, the direction of effect and mean methylation level of c PCDH CpGs affected by SMCHD1 variant ( rs10775431 ), respectively for blood and brain (prefrontal cortex). Red and blue dots represent CpGs that were statistically significant in blood (P FDR <0.05) and brain (nominal P -value<0.05, prefrontal cortex), respectively. The fifth track shows the location of promoter regions of each c PCDH member (1500 bp upstream of TSS to 500 bp downstream of TSS). Further indicating that the genetic associations were mediated by SMCHD1 , the top SNP rs10775431 was a blood expression QTL of the gene according to BIOS ( Supplementary Data 3, Table S19 ) and eQTLGen consortium 67 . Further, for DNMT3B and CTCF we only observed weak evidence for consistent associations with c PCDH methylation in blood and brain, while top SNP at the remaining candidate genes was not associated as none of CpGs that were statistically significant in blood validated in brain ( Supplementary Data 2, Table S8-S18 ). Overall, genetic variation at the SMCHD1 locus showed by far the most strongest and most consistent effect on c PCDH methylation in blood and brain of the 6 candidate loci evaluated. Genome-wide identification of genetic loci affecting c PCDH methylation in blood Next, we aimed to identify new loci in trans affecting c PCDH methylation. In view of the consistent DNA methylation patterns and effects of candidate genes in blood and brain, we set out to perform a genome-wide association analysis in blood, the data set with the largest sample size (N=3777) ( Figure 3A ). We detected 334 genetic variants representing 7 independent loci associated with c PCDH methylation in trans affecting at least 1 out of the 607 tested CpGs (P Simes <5×10 -8 , Figure 3B , Supplementary Data 1, Table S5 ) thus excluding cis -eQTL effects defined as within 5MB of c PCDH genes. Analysis of the top SNPs per locus showed that 4 out of 7 loci were associated with 1 c PCDH CpG only (P FDR <0.05; Table 1 ). We did not further examine these loci. The 3 remaining top SNPs were located on chromosomes 1, 3 and 10, and were associated with widespread c PCDH methylation in trans , each affecting at least 50 c PCDH CpGs (P FDR <0.05; Table 1 ). Further inspection of all suggestive genome-wide associations (P Simes <1×10 -5 ), excluded the possibility that we missed loci with widespread effects similar to SMCHD1 ( Supplementary Data 1, Table S5 ). Download figure Open in new tab Figure 3. Genome-wide of c PCDH methylation QTL analyses. A To identify additional novel genetic loci influencing c PCDH methylation, we performed trans -meQTL analysis to test the association between the SNPs across whole genome and 607 c PCDH CpGs in BIOS blood (n=3777). Then the effect of three novel genetic loci were validated in BDR prefrontal cortex samples (n=523). B Manhattan plot showing all tested trans -SNPs for an overall effect on c PCDH methylation in blood. Significant associations are depicted in red (P Simes <5×10 -8 ) and blue dots indicate SNPs with overall P-values between 1×10 -5 (suggestive threshold) and 5×10 -8 (genome-wide threshold). Additionally, italic text represents the location of 6 candidate gene loci (top SNP in candidate gene analysis) known to be involved in c PCDH regulation. View this table: View inline View popup Download powerpoint Table 1 Effect of seven top SNPs on PCDH methylation in blood. No validation of the OR2W3 locus effect in brain The top SNP rs3811444 is a missense variant (MAF=0.34) on chromosome 1, located in TRIM58 ( Figure 4A ). By looking up eQTLGen consortium 67 (n=26395), we found that rs3811444 in blood only regulates nearby OR2W3 , and its T allele was associated with increased expression. This was also the case in BIOS blood data (P=2.1×10 -10 ; Supplementary Data 3, Table S19 ). Download figure Open in new tab Figure 4. Effect of OR2W3 locus on c PCDH methylation in blood and brain (prefrontal cortex). A Locus Zoom plot of top SNP rs3811444 on chromosome 1. B Scatter plot of effect sizes for top SNP rs3811444 in the OR2W3 genetic locus on c PCDH methylation observed in blood and brain (prefrontal cortex). Red and blue dots represent CpGs statistically significant only in blood or brain (prefrontal cortex), respectively. Gray dots represent CpGs statistically significant in neither blood nor brain (prefrontal cortex). The effect of rs3811444 on c PCDH methylation observed in blood, however, was absent in brain samples. First, we found rs3811444 affected 63 PCDH CpGs methylation in blood (450k array, Table 1 ). Of those, 55 were also measured in brain (EPIC array) and none of the statistically significant CpGs in blood were validated in brain ( Supplementary Data 3, Table S20-21; Table S26 ). Second, among the 78 CpGs (available from both the 450k and EPIC array) found to be associated with the top SNP in either blood or brain, only 30 CpGs (38%) detected significant in blood or brain had a consistent direction of effect ( Figure 4B ; Supplementary Data 3, Table S20-21 ). Validating the SENP7 locus effect in brain The top SNP rs13062095 (MAF=0.35) in the second locus is located between SENP7 gene and TRMT10C gene on chromosome 3, which marked a region with SNPs in strong linkage disequilibrium (r 2 >0.9) overlapping with the SENP7 gene ( Figure 5A ). According to the eQTLGen consortium 67 (n=26,395), the C allele of rs13062095 was associated with the expression of several nearby genes including SENP7, IMPG2 , CEP97 , TFG and NXPE3 , but most strongly with the expression of the SENP7 gene. In BIOS blood, we found that all genes except for IMPG2 were also significantly associated with the C allele of rs13062095 ( Supplementary Data 3, Table S19 ). Interestingly, the three genes, SENP7 , IMPG2 and CEP97 , were also cis -eQTL gene of rs13062095 in cortex (MetaBrain consortium 69 , n=2757). In cortex, the SNP was associated with the expression of five genes in trans (MetaBrain consortium 69 , n=2757), four of which were protocadherin genes ( PCDHB5 , PCDHGA1 , PCDHGB1 and PCDHGB5 ) and one zinc finger coding gene ( ZNF274 ), which has recently been implicated in c PCDH gene regulation 70 . However, genetic variation at ZNF274 was not associated with c PCDH methylation in our study (P simes >10 -5 ) and this was also case in GoDMC 71 and Pan-mQTL 72 . Download figure Open in new tab Figure 5. Effect of SENP7 locus on c PCDH methylation in blood and brain (prefrontal cortex). A Locus Zoom plot of top SNP rs13062095 on chromosome 3. B Scatter plot of effect sizes for top SNP rs13062095 in SENP7 genetic locus on c PCDH methylation observed in blood and brain (prefrontal cortex). Green dots represent CpGs statistically significant in both blood and brain (prefrontal cortex). Red and blue dots represent CpGs statistically significant only in blood or brain (prefrontal cortex), respectively. Gray dots represent CpGs statistically significant in neither blood nor brain (prefrontal cortex). C Effect of SENP7 variant ( rs13062095 ) on c PCDH methylation in blood and brain (prefrontal cortex). The tracks display the P-values resulting from the statistical test, the direction of effect and mean methylation level of c PCDH CpGs affected by SENP7 variant ( rs13062095 ), respectively for blood and brain (prefrontal cortex). Red and blue dots represent CpGs that were statistically significant in blood (P FDR <0.05) and brain (nominal P-value<0.05, prefrontal cortex), respectively. The fifth track shows the location of promoter regions of each c PCDH member (1500 bp upstream of TSS to 500 bp downstream of TSS). Next, we tested the association of the top SNP rs13062095 on c PCDH methylation in blood, and then validated in brain. A high concordance was observed between the two tissues ( Figure 5B , Supplementary Data 3, Table S22-23; Table S26 ). First, top SNP rs13062095 affected methylation of 105 c PCDH CpGs in blood (P Simes =1.2×10 -9 , minimal nominal P= 1.9×10 - 12 , 450k array, Table 1 ). Of these, 97 were also measured in brain (EPIC array) and 26 (27%) were validated in brain (P<0.05; OR = 2.6, P=2.4×10 -4 ). Second, among the 154 CpGs (available from both the 450k and EPIC array) found to be associated with the top SNP in either blood or brain, 130 CpGs (84%) detected as significant in blood or brain had consistent direction of effect (P=10 -8 ). The high SENP7 expression associated C-allele of rs13062095 was associated with overall higher c PCDH methylation. Inspection of the three subclusters revealed this effect was mainly apparent for PCDHG in blood but had an effect on all three subclusters in brain and concerned hypo-, intermediate and hypermethylated CpGs ( Figure 5C ). To check concordance, we further looked up rs13062095 in large-scale blood meQTL consortia datasets including GoDMC 71 and Pan-mQTL 72 . In GoDMC 71 , rs62280667 , a SNP in high LD with rs13062095 (R 2 =0.97), was associated with one c PCDH CpG methylation ( Supplementary Data 3, Table S27 ). In Pan-mQTL 72 , we found that rs13062095 itself was associated with the methylation of three c PCDH CpGs in trans ( Supplementary Data 3, Table S28 ). Validating the VENTX locus effect in brain The top SNP rs11599284 (MAF=0.1) of the third identified locus is a missense variant on chromosome 10 (glycine to arginine substitution at amino acid 73), located in the UTF1 gene ( Figure 6A ). Moreover, we found that the A allele of rs11599284 was associated with the expression of several nearby genes including VENTX E, CHS1 , TUBGCP2 and ADAM8 , but most strongly with the expression of VENTX (eQTLGen consortium 67 , n=26,395). In BIOS blood data (n=3777), the strong cis - effect for VENTX was not observed, while the TUBGCP2 and ADAM8 were consistently found ( Supplementary Data 3, Table S19 ). The SNP was not evaluated in the MetaBrain Consortium 69 , precluding an assessment whether it was a cis -eQTL in brain. Download figure Open in new tab Figure 6. Effect of VENTX locus on c PCDH methylation in blood and brain (prefrontal cortex). A Locus Zoom plot of top SNP rs11599284 on chromosome 10. B Scatter plot of effect sizes for top SNP rs11599284 in VENTX genetic locus on c PCDH methylation observed in blood and brain (prefrontal cortex). Green dots represent CpGs statistically significant in both blood and brain (prefrontal cortex). Red and blue dots represent CpGs statistically significant in only blood or brain (prefrontal cortex), respectively. Gray dots represent CpGs statistically significant in neither blood nor brain (prefrontal cortex). C Effect of VENTX variant ( rs11599284 ) on c PCDH methylation in blood and brain (prefrontal cortex). The tracks display the P-values resulting from the statistical test, the direction of effect and mean methylation level of c PCDH CpGs affected by VENTX variant (rs11599284), respectively for blood and brain (prefrontal cortex). Red and blue dots represent CpGs that were statistically significant in blood (P FDR <0.05) and brain (nominal P-value<0.05, prefrontal cortex), respectively. The fifth track shows the location of promoter regions of each c PCDH member (1500 bp upstream of TSS to 500 bp downstream of TSS). Next, we tested the effect of the top SNP rs11599284 on c PCDH methylation in blood, and then validated in brain. A high concordance was observed between the two tissues ( Figure 6B , Supplementary Data 3, Table S24-26 ). First, top SNP rs11599284 affected methylation of 157 c PCDH CpGs in blood (P Simes =9.6×10 -28 , minimal nominal P= 1.6×10 -30 ,450k array, Table 1 ). Of those, 150 were also measured in brain (EPIC array) and 24 (16%) were validated in brain (P<0.05; OR = 5.4, P=1.4×10 -7 ). Second, among the 164 CpGs (available from both the 450k and EPIC array) found to be associated with the top SNP in either blood or brain, 130 CpGs (79%) detected as significant in blood or brain had a consistent direction of effect (P=10 -8 ). The A-allele of rs11599284 , leading to the amino-acid change in UTF1 and associated with low VENTX expression, was associated with overall lower c PCDH methylation. Inspection of the three subclusters revealed that this effect was most apparent for PCDHB and concerned hypo-, intermediate and hypermethylated CpGs ( Figure 6C ). To check concordance, we further looked up rs11599284 in large-scale blood meQTL consortium include GoDMC 71 and Pan-mQTL 72 . In GoDMC 71 , the SNP was not evaluated. In Pan-mQTL 72 , we found that this SNP was associated with the methylation of seven c PCDH CpGs in trans and all were mapping to the PCDHB subcluster ( Supplementary Data 3, Table S29 ). Discussion Our genetic study identified loci with a widespread effect on c PCDH methylation in human blood and brain. In contrast to many other genomic regions 73 , 74 , c PCDH methylation was highly correlated between blood and prefrontal cortex and the methylation patterns were concordant, which was characterized by a variation between hypomethylation near promoter regions to intermediate and hypermethylation in-between promoters. In a candidate gene analysis, we found that genetic variation at the SMCHD1 gene affected methylation at all three PCDH subclusters in blood and brain, while no or a much less pronounced effects were observed for other candidate genes evaluated. In a genome-wide analysis, we identified two novel genetic loci, SENP7 and UTF1 / VENTX . The SENP7 locus was primarily associated with PCDHG methylation in blood but had an effect on all three subclusters in brain. The UTF1 / VENTX locus mainly influenced methylation of the PCDHB subcluster in blood and brain, and had less pronounced effects on the other subclusters. Our systematic genome-wide analysis identified novel genetic loci for c PCDH methylation regulation, significantly expands upon genes that were previously implicated in association with c PCDH methylation using mouse models, and identifies the direction of the effect on c PCDH methylation. While previous work in mice established the critical role for multiple genes in c PCDH regulation 18 , 21 , 22 , 24 , 59 , 60 , their effects in c PCDH methylation in humans are only partly understood 12 , 13 . Here, we confirm the role of the SMCHD1 locus in c PCDH methylation in human blood and prefrontal cortex and highlight its broad impact on methylation of all three PCDH subclusters. We also observed that other candidate gene loci had no or a much less pronounced effects on c PCDH methylation. For example, the DNMT3B locus showed weak evidence for consistent associations with c PCDH methylation in blood and brain. Given the known role of DNMT3B in de novo methylation, this may be explained by the minor effect of common genetic variation on DNMT3B expression. Studies with a larger number of blood and brain samples will likely be able to detect more associations due to a higher statistical power. The CDCA7 locus is another candidate gene for which we did not detect consistent associations with c PCDH methylation in blood and brain. We previously reported that genetically controlled differential expression of CDCA7 induces genome- wide DNA methylation changes in particular at repeats in humans indicating that common genetic variation does affect DNA methylation 45 . In addition, CDCA7 plays a key role in c PCDH regulation in mouse neurons 24 . These apparent discrepancies may arise from either brain-specific effects which we could detect less well due to the lower number of brains samples in our analysis or from design differences between experimental study (tissues/cells from patients and knock-out/knock-in models for diseases) and our study (common genetic variation in general population). Our genome-wide association study implicates the SENP7 locus in c PCDH methylation regulation. SENP7 is a strong candidate to influence c PCDH methylation based on following evidence. First, it was reported to affect methylation levels of multiple CpG sites in trans 45 . Second, SENP7 has been shown to be involved in the deSUMOylation of the chromatin repressor KAP1 / TRIM28 25 , which functions in DNA repair and epigenetic regulation including DNA methylation regulation 75 , 76 . Therefore, we hypothesize that SENP7 affects c PCDH methylation through its interaction with KAP1 . Third, using external large-scale methylation or expression QTL atlas including GoDMC 71 , Pan-mQTL 72 and MetaBrain 69 , we observe that SENP7 variant does affect c PCDH methylation and regulate c PCDH expression. Of note, when comparing our results with other published large-scale blood meQTL results, it is important to be aware of the differences in study design. The number of CpGs evaluated in genome-wide trans-meQTL analyses is substantially higher than in our study (607 c PCDH CpGs only) and hence, significant threshold cutoff for SNP-CpG pairs is several order of magnitude lower than in our analysis focused on c PCDH . Interestingly, c PCDH differential methylation has been associated with many neurological diseases 3 – 6 and one GWAS study indicated that the SENP7 locus associated with late-onset Alzheimer’s disease 77 . Another study found that c PCDH methylation alterations related to a decline in regional brain volume and cognitive skills 78 . It will be interesting to establish in future studies whether SENP7 is involved in Alzheimer’s disease through its effect on c PCDH methylation. Similarly, our genome-wide analysis indicated a role for the UTF1 / VENTX locus in c PCDH methylation regulation. These genes have previously not been implicated in epigenetic regulation. UTF1 is required for the proper differentiation of embryonic stem cells 26 while VENTX regulates gene expression in stem cells and during embryonic development as a transcription factor 27 . The SNP we identified, rs11599284 , is associated with the expression of VENTX and a missense variant resulting in a glycine to arginine substitution in the UTF1 protein 79 . The missense mutation is predicted to be deleterious, while experimental evidence implicated the mutation in decrease in chromatin association, albeit only in combination with a second mutation 79 . Our study contributes to a better understanding of the epigenetic regulation of the c PCDH genes through identification of SENP7 and UTF1 / VENTX as new loci influencing c PCDH methylation across blood and brain. However, our study also has limitations. First, we first analyzed blood samples followed by validation in brain, which means that we missed brain-specific genetic loci influencing c PCDH methylation. Second, our brain sample size is relatively small (N=523) precluding a genome- wide analysis to capture loci influencing c PCDH methylation in brain. Third, our results does not provide insight into the exact underlying mechanisms of SENP7 and UTF1 / VENTX function in c PCDH regulation. In particular for the functionally poorly characterized UTF1 and VENTX genes it is currently unclear how they could influence epigenetic regulation. Functional experiments will be required to demonstrate causality for the genes we implicated in c PCDH methylation in blood and brain and uncover the mechanisms involved. In conclusion, we identified two new loci associated with c PCDH methylation across blood and brain on top of SMCHD1 , namely SENP7 and UTF1 / VENTX . These results can guide follow-up studies into the epigenetic regulation of c PCDH genes, the role of c PCDH in human traits and diseases, and may eventually lead to a better understanding of the generation of neuronal cell surface barcodes. Availability of data and materials The BIOS whole blood data are available from the European Genome-Phenome Archive (EGAC00001000277). The BDR brain data are available from the Dementias Platform UK (DPUK) ( https://portal.dementiasplatform.uk/CohortDirectory/Item?fingerPrintID=BDR ) upon application. Scripts for the main analyses in this manuscript are available at GitHub [ https://github.com/YunfengLUMC/cPCDH_methylation_regulation ] under an opensource MIT license. The summary blood meQTL results from the Europe population (GoDMC) are available at http://mqtldb.godmc.org.uk . The summary blood meQTL results from the Asian population are available at https://www.biosino.org/panmqtl/home . The summary blood eQTL results (eQTLGen consortium) are available at https://www.eqtlgen.org . The summary brain eQTL results (MetaBrain consortium) are available at https://www.metabrain.nl . Authors’ contributions Conceptualization: BTH, LD and JM. Methodology: YL, BTH. Formal analysis: YL, EH and MV. Resources: BIOS Consortium and BDR consortium. Writing – original draft: YL, BTH. Writing – review and editing: BTH, MV, EH, HM, JM and LD. Visualization: YL, BTH. Supervision: BTH and LD. All authors have read and approved the final manuscript. Declaration of interests The authors declare that they have no competing interests. Ethics declarations Ethics approval and consent to participate The study was approved by the institutional review boards of the participating centers (CODAM, Medical Ethical Committee of the Maastricht University; LL, Ethics Committee of the University Medical Centre Groningen; LLS, Ethical Committee of the Leiden University Medical Center; PAN, Institutional Review Board of the University Medical Centre Utrecht; NTR, Central Ethics Committee on Research Involving Human Subjects of the VU University Medical Centre; RS, Institutional Review Board (Medical Ethics Committee) of the Erasmus Medical Center; BDR, Ethical Committee of University of Exeter Medical School Research). All participants have given written informed consent, and the experimental methods comply with the Helsinki Declaration. Supplementary Information Supplementary Data 1 . Contains Table S1-S5 . Supplementary Data 2 . Contains Table S6-S18 . Supplementary Data 3 . Contains Table S19-29 . Acknowledgements BIOS Consortium samples and data were contributed by LifeLines, the Leiden Longevity Study, the Netherlands Twin Registry (NTR), the Rotterdam Study, the Genetic Research in Isolated Populations program, the Cohort on Diabetes and Atherosclerosis Maastricht (CODAM) study, and the Prospective ALS study Netherlands (PAN). The BIOS was funded by BBMRI-NL (a Research Infrastructure financed by the Dutch government (NWO, numbers 184.021.007 and 184.033.111)). Cortex DNA methylation data generation was funded by Medical Research Council (MRC) grants K013807 and W004984 (awarded to J.M.). Data analysis was undertaken using high-performance computing supported by a Medical Research Council (MRC) Clinical Infrastructure award (M008924 awarded to J.M.). The BDR is jointly funded by Alzheimer’s Research UK (ARUK) and the Alzheimer’s Society in association with the Medical Research Council (MRC). LD was supported by NWO-VIDI grant (ZonMW91718350). YL was supported by a PhD fellowship from the China Scholarship Council (CSC). We thank the participants of all aforementioned biobanks and acknowledge the contributions of the investigators to this study. This work was carried out on the Dutch national e-infrastructure with the support of SURF Cooperative. References 1. ↵ El Hajj , N. , Dittrich , M. , and Haaf , T. ( 2017 ). Epigenetic dysregulation of protocadherins in human disease . Semin Cell Dev Biol 69 , 172 – 182 . doi: 10.1016/j.semcdb.2017.07.007 . OpenUrl CrossRef PubMed 2. ↵ Vehmeijer , F.O.L. , Küpers , L.K. , Sharp , G.C. , Salas , L.A. , Lent , S. , Jima , D.D. , Tindula , G. , Reese , S. , Qi , C. , Gruzieva , O. , et al. ( 2020 ). DNA methylation and body mass index from birth to adolescence: meta-analyses of epigenome-wide association studies . Genome Med 12 , 105 . doi: 10.1186/s13073-020-00810-w . OpenUrl CrossRef 3. ↵ Zhang , L. , Silva , T.C. , Young , J.I. , Gomez , L. , Schmidt , M.A. , Hamilton-Nelson , K.L. , Kunkle , B.W. , Chen , X. , Martin , E.R. , and Wang , L . ( 2020 ). Epigenome-wide meta-analysis of DNA methylation differences in prefrontal cortex implicates the immune processes in Alzheimer’s disease . Nat Commun 11 , 6114 . doi: 10.1038/s41467-020-19791-w . OpenUrl CrossRef PubMed 4. Li , M. , Li , Y. , Qin , H. , Tubbs , J.D. , Li , M. , Qiao , C. , Lin , J. , Li , Q. , Fan , F. , Gou , M. , et al. ( 2021 ). Genome-wide DNA methylation analysis of peripheral blood cells derived from patients with first-episode schizophrenia in the Chinese Han population . Mol Psychiatry 26 , 4475 – 4485 . doi: 10.1038/s41380-020-00968-0 . OpenUrl CrossRef PubMed 5. Semick , S.A. , Bharadwaj , R.A. , Collado-Torres , L. , Tao , R. , Shin , J.H. , Deep-Soboslay , A. , Weiss , J.R. , Weinberger , D.R. , Hyde , T.M. , Kleinman , J.E. , et al. ( 2019 ). Integrated DNA methylation and gene expression profiling across multiple brain regions implicate novel genes in Alzheimer’s disease . Acta Neuropathol 137 , 557 – 569 . doi: 10.1007/s00401-019-01966-5 . OpenUrl CrossRef PubMed 6. ↵ Henderson-Smith , A. , Fisch , K.M. , Hua , J. , Liu , G. , Ricciardelli , E. , Jepsen , K. , Huentelman , M. , Stalberg , G. , Edland , S.D. , Scherzer , C.R. , et al. ( 2019 ). DNA methylation changes associated with Parkinson’s disease progression: outcomes from the first longitudinal genome-wide methylation analysis in blood . Epigenetics 14 , 365 – 382 . doi: 10.1080/15592294.2019.1588682 . OpenUrl CrossRef 7. ↵ Slieker , R.C. , van Iterson , M. , Luijk , R. , Beekman , M. , Zhernakova , D.V. , Moed , M.H. , Mei , H. , van Galen , M. , Deelen , P. , Bonder , M.J. , et al. ( 2016 ). Age-related accrual of methylomic variability is linked to fundamental ageing mechanisms . Genome Biol 17 , 191 . doi: 10.1186/s13059-016-1053-6 . OpenUrl CrossRef PubMed 8. ↵ Tan , Q. , Li , S. , Sørensen , M. , Nygaard , M. , Mengel-From , J. , and Christensen , K . ( 2021 ). Age patterns of intra-pair DNA methylation discordance in twins: Sex difference in epigenomic instability and implication on survival . Aging Cell 20 , e13460 . doi: 10.1111/acel.13460 . OpenUrl CrossRef PubMed 9. ↵ Dallosso , A.R. , Hancock , A.L. , Szemes , M. , Moorwood , K. , Chilukamarri , L. , Tsai , H.H. , Sarkar , A. , Barasch , J. , Vuononvirta , R. , Jones , C. , et al. ( 2009 ). Frequent long-range epigenetic silencing of protocadherin gene clusters on chromosome 5q31 in Wilms’ tumor . PLoS Genet 5 , e1000745 . doi: 10.1371/journal.pgen.1000745 . OpenUrl CrossRef PubMed 10. Dallosso , A.R. , Øster , B. , Greenhough , A. , Thorsen , K. , Curry , T.J. , Owen , C. , Hancock , A.L. , Szemes , M. , Paraskeva , C. , Frank , M. , et al. ( 2012 ). Long-range epigenetic silencing of chromosome 5q31 protocadherins is involved in early and late stages of colorectal tumorigenesis through modulation of oncogenic pathways . Oncogene 31 , 4409 – 4419 . doi: 10.1038/onc.2011.609 . OpenUrl CrossRef PubMed Web of Science 11. ↵ de Almeida , B.P. , Apolónio , J.D. , Binnie , A. , and Castelo-Branco , P. ( 2019 ). Roadmap of DNA methylation in breast cancer identifies novel prognostic biomarkers . BMC Cancer 19 , 219 . doi: 10.1186/s12885-019-5403-0 . OpenUrl CrossRef 12. ↵ Velasco , G. , Grillo , G. , Touleimat , N. , Ferry , L. , Ivkovic , I. , Ribierre , F. , Deleuze , J.F. , Chantalat , S. , Picard , C. , and Francastel , C . ( 2018 ). Comparative methylome analysis of ICF patients identifies heterochromatin loci that require ZBTB24 , CDCA 7 and HELLS for their methylated state. Hum Mol Genet 27 , 2409-2424. doi: 10.1093/hmg/ddy130 . OpenUrl CrossRef PubMed 13. ↵ Mason , A.G. , Slieker , R.C. , Balog , J. , Lemmers , R. , Wong , C.J. , Yao , Z. , Lim , J.W. , Filippova , G.N. , Ne , E. , Tawil , R. , et al. ( 2017 ). SMCHD1 regulates a limited set of gene clusters on autosomal chromosomes . Skelet Muscle 7 , 12 . doi: 10.1186/s13395-017-0129-7 . OpenUrl CrossRef PubMed 14. ↵ Guo , Y. , Monahan , K. , Wu , H. , Gertz , J. , Varley , K.E. , Li , W. , Myers , R.M. , Maniatis , T. , and Wu , Q . ( 2012 ). CTCF/cohesin-mediated DNA looping is required for protocadherin α promoter choice . Proc Natl Acad Sci U S A 109 , 21081 – 21086 . doi: 10.1073/pnas.1219280110 . OpenUrl Abstract / FREE Full Text 15. ↵ Monahan , K. , Rudnick , N.D. , Kehayova , P.D. , Pauli , F. , Newberry , K.M. , Myers , R.M. , and Maniatis , T . ( 2012 ). Role of CCCTC binding factor (CTCF) and cohesin in the generation of single-cell diversity of protocadherin-α gene expression . Proc Natl Acad Sci U S A 109 , 9125 – 9130 . doi: 10.1073/pnas.1205074109 . OpenUrl Abstract / FREE Full Text 16. ↵ Jiang , Y. , Loh , Y.E. , Rajarajan , P. , Hirayama , T. , Liao , W. , Kassim , B.S. , Javidfar , B. , Hartley , B.J. , Kleofas , L. , Park , R.B. , et al. ( 2017 ). The methyltransferase SETDB1 regulates a large neuron-specific topological chromatin domain . Nat Genet 49 , 1239 – 1250 . doi: 10.1038/ng.3906 . OpenUrl CrossRef PubMed 17. ↵ Lomvardas , S. , and Maniatis , T . ( 2016 ). Histone and DNA Modifications as Regulators of Neuronal Development and Function . Cold Spring Harb Perspect Biol 8 . doi: 10.1101/cshperspect.a024208 . OpenUrl Abstract / FREE Full Text 18. ↵ Toyoda , S. , Kawaguchi , M. , Kobayashi , T. , Tarusawa , E. , Toyama , T. , Okano , M. , Oda , M. , Nakauchi , H. , Yoshimura , Y. , Sanbo , M. , et al. ( 2014 ). Developmental epigenetic modification regulates stochastic expression of clustered protocadherin genes, generating single neuron diversity . Neuron 82 , 94 – 108 . doi: 10.1016/j.neuron.2014.02.005 . OpenUrl CrossRef PubMed 19. ↵ Hirayama , T. , and Yagi , T . ( 2017 ). Regulation of clustered protocadherin genes in individual neurons . Semin Cell Dev Biol 69 , 122 – 130 . doi: 10.1016/j.semcdb.2017.05.026 . OpenUrl CrossRef PubMed 20. ↵ Wu , Q. , and Jia , Z . ( 2021 ). Wiring the Brain by Clustered Protocadherin Neural Codes . Neurosci Bull 37 , 117 – 131 . doi: 10.1007/s12264-020-00578-4 . OpenUrl CrossRef PubMed 21. ↵ Chen , K. , Hu , J. , Moore , D.L. , Liu , R. , Kessans , S.A. , Breslin , K. , Lucet , I.S. , Keniry , A. , Leong , H.S. , Parish , C.L. , et al. ( 2015 ). Genome-wide binding and mechanistic analyses of Smchd1-mediated epigenetic regulation . Proc Natl Acad Sci U S A 112 , E3535 – 3544 . doi: 10.1073/pnas.1504232112 . OpenUrl Abstract / FREE Full Text 22. ↵ Gendrel , A.V. , Tang , Y.A. , Suzuki , M. , Godwin , J. , Nesterova , T.B. , Greally , J.M. , Heard , E. , and Brockdorff , N . ( 2013 ). Epigenetic functions of smchd1 repress gene clusters on the inactive X chromosome and on autosomes . Mol Cell Biol 33 , 3150 – 3165 . doi: 10.1128/mcb.00145-13 . OpenUrl Abstract / FREE Full Text 23. ↵ Kiefer , L. , Chiosso , A. , Langen , J. , Buckley , A. , Gaudin , S. , Rajkumar , S.M. , Servito , G.I.F. , Cha , E.S. , Vijay , A. , Yeung , A. , et al. ( 2023 ). WAPL functions as a rheostat of Protocadherin isoform diversity that controls neural wiring . Science 380 , eadf8440. doi: 10.1126/science.adf8440 . OpenUrl CrossRef PubMed 24. ↵ Vukic , M. , Chouaref , J. , Della Chiara , V. , Dogan , S. , Ratner , F. , Hogenboom , J.Z.M. , Epp , T.A. , Chawengsaksophak , K. , Vonk , K.K.D. , Breukel , C. , et al. ( 2024 ). CDCA7-associated global aberrant DNA hypomethylation translates to localized, tissue-specific transcriptional responses . Sci Adv 10 , eadk3384. doi: 10.1126/sciadv.adk3384 . OpenUrl CrossRef PubMed 25. ↵ Garvin , A.J. , Densham , R.M. , Blair-Reid , S.A. , Pratt , K.M. , Stone , H.R. , Weekes , D. , Lawrence , K.J. , and Morris , J.R . ( 2013 ). The deSUMOylase SENP7 promotes chromatin relaxation for homologous recombination DNA repair . EMBO Rep 14 , 975 – 983 . doi: 10.1038/embor.2013.141 . OpenUrl Abstract / FREE Full Text 26. ↵ van den Boom V. Kooistra , S.M. , Boesjes , M. , Geverts , B. , Houtsmuller , A.B. , Monzen , K. , Komuro , I. , Essers , J. , Drenth-Diephuis , L.J. , and Eggen , B.J. ( 2007 ). UTF1 is a chromatin- associated protein involved in ES cell differentiation . J Cell Biol 178 , 913 – 924 . doi: 10.1083/jcb.200702058 . OpenUrl Abstract / FREE Full Text 27. ↵ Kumar , S. , Kumar , V. , Li , W. , and Kim , J . ( 2022 ). Ventx Family and Its Functional Similarities with Nanog: Involvement in Embryonic Development and Cancer Progression . Int J Mol Sci 23 . doi: 10.3390/ijms23052741 . OpenUrl CrossRef 28. ↵ van Greevenbroek M.M. Jacobs , M. , van der Kallen , C.J. , Vermeulen , V.M. , Jansen , E.H. , Schalkwijk , C.G. , Ferreira , I. , Feskens , E.J. , and Stehouwer , C.D. ( 2011 ). The cross-sectional association between insulin resistance and circulating complement C3 is partly explained by plasma alanine aminotransferase, independent of central obesity and general inflammation (the CODAM study) . Eur J Clin Invest 41 , 372 – 379 . doi: 10.1111/j.1365-2362.2010.02418.x . OpenUrl CrossRef PubMed 29. ↵ Tigchelaar , E.F. , Zhernakova , A. , Dekens , J.A. , Hermes , G. , Baranska , A. , Mujagic , Z. , Swertz , M.A. , Muñoz , A.M. , Deelen , P. , Cénit , M.C. , et al. ( 2015 ). Cohort profile: LifeLines DEEP, a prospective, general population cohort study in the northern Netherlands: study design and baseline characteristics . BMJ Open 5 , e006772 . doi: 10.1136/bmjopen-2014-006772 . OpenUrl Abstract / FREE Full Text 30. ↵ Schoenmaker , M. , de Craen , A.J. , de Meijer , P.H. , Beekman , M. , Blauw , G.J. , Slagboom , P.E. , and Westendorp , R.G. ( 2006 ). Evidence of genetic enrichment for exceptional survival using a family approach: the Leiden Longevity Study . Eur J Hum Genet 14 , 79 – 84 . doi: 10.1038/sj.ejhg.5201508 . OpenUrl CrossRef PubMed Web of Science 31. ↵ Boomsma , D.I. , Vink , J.M. , van Beijsterveldt , T.C. , de Geus , E.J. , Beem , A.L. , Mulder , E.J. , Derks , E.M. , Riese , H. , Willemsen , G.A. , Bartels , M. et al. ( 2002 ). Netherlands Twin Register: a focus on longitudinal research . Twin Res 5 , 401 – 406 . doi: 10.1375/136905202320906174 . OpenUrl CrossRef PubMed Web of Science 32. ↵ Hofman , A. , Darwish Murad , S. , van Duijn , C.M. , Franco , O.H. , Goedegebure , A. , Ikram , M.A. , Klaver , C.C. , Nijsten , T.E. , Peeters , R.P. , Stricker , B.H. et al. ( 2013 ). The Rotterdam Study: 2014 objectives and design update . Eur J Epidemiol 28 , 889 – 926 . doi: 10.1007/s10654-013-9866-z . OpenUrl CrossRef PubMed 33. ↵ Huisman , M.H. , de Jong , S.W. , van Doormaal , P.T. , Weinreich , S.S. , Schelhaas , H.J. , van der Kooi , A.J. , de Visser , M. , Veldink , J.H. , and van den Berg , L.H. ( 2011 ). Population based epidemiology of amyotrophic lateral sclerosis using capture-recapture methodology . J Neurol Neurosurg Psychiatry 82 , 1165 – 1170 . doi: 10.1136/jnnp.2011.244939 . OpenUrl Abstract / FREE Full Text 34. ↵ Engelen , L. , Ferreira , I. , Brouwers , O. , Henry , R.M. , Dekker , J.M. , Nijpels , G. , Heine , R.J. , van Greevenbroek , M.M. , van der Kallen , C.J. , Blaak , E.E. et al. ( 2009 ). Polymorphisms in glyoxalase 1 gene are not associated with vascular complications: the Hoorn and CoDAM studies . J Hypertens 27 , 1399 – 1403 . doi: 10.1097/HJH.0b013e32832af6ba . OpenUrl CrossRef PubMed Web of Science 35. ↵ Deelen , J. , Beekman , M. , Uh , H.W. , Broer , L. , Ayers , K.L. , Tan , Q. , Kamatani , Y. , Bennet , A.M. , Tamm , R. , Trompet , S. , et al. ( 2014 ). Genome-wide association meta-analysis of human longevity identifies a novel locus conferring survival beyond 90 years of age . Hum Mol Genet 23 , 4420 – 4432 . doi: 10.1093/hmg/ddu139 . OpenUrl CrossRef PubMed Web of Science 36. ↵ Lin , B.D. , Willemsen , G. , Abdellaoui , A. , Bartels , M. , Ehli , E.A. , Davies , G.E. , Boomsma , D.I. , and Hottenga , J.J . ( 2016 ). The Genetic Overlap Between Hair and Eye Color . Twin Res Hum Genet 19 , 595 – 599 . doi: 10.1017/thg.2016.85 . OpenUrl CrossRef PubMed 37. ↵ Deelen , P. , Bonder , M.J. , van der Velde , K.J. , Westra , H.J. , Winder , E. , Hendriksen , D. , Franke , L. , and Swertz , M.A. ( 2014 ). Genotype harmonizer: automatic strand alignment and format conversion for genotype data integration . BMC Res Notes 7 , 901 . doi: 10.1186/1756-0500-7-901 . OpenUrl CrossRef PubMed 38. ↵ Li , Y. , Willer , C.J. , Ding , J. , Scheet , P. , and Abecasis , G.R . ( 2010 ). MaCH: using sequence and genotype data to estimate haplotypes and unobserved genotypes . Genet Epidemiol 34 , 816 – 834 . doi: 10.1002/gepi.20533 . OpenUrl CrossRef PubMed Web of Science 39. ↵ McCarthy , S. , Das , S. , Kretzschmar , W. , Delaneau , O. , Wood , A.R. , Teumer , A. , Kang , H.M. , Fuchsberger , C. , Danecek , P. , Sharp , K. , et al. ( 2016 ). A reference panel of 64,976 haplotypes for genotype imputation . Nat Genet 48 , 1279 – 1283 . doi: 10.1038/ng.3643 . OpenUrl CrossRef PubMed 40. ↵ Danecek , P. , Auton , A. , Abecasis , G. , Albers , C.A. , Banks , E. , DePristo , M.A. , Handsaker , R.E. , Lunter , G. , Marth , G.T. , Sherry , S.T. , et al. ( 2011 ). The variant call format and VCFtools . Bioinformatics 27 , 2156 – 2158 . doi: 10.1093/bioinformatics/btr330 . OpenUrl CrossRef PubMed Web of Science 41. ↵ Aryee , M.J. , Jaffe , A.E. , Corrada-Bravo , H. , Ladd-Acosta , C. , Feinberg , A.P. , Hansen , K.D. , and Irizarry , R.A . ( 2014 ). Minfi: a flexible and comprehensive Bioconductor package for the analysis of Infinium DNA methylation microarrays . Bioinformatics 30 , 1363 – 1369 . doi: 10.1093/bioinformatics/btu049 . OpenUrl CrossRef PubMed Web of Science 42. ↵ van Iterson , M. , Tobi , E.W. , Slieker , R.C. , den Hollander , W. , Luijk , R. , Slagboom , P.E. , and Heijmans , B.T. ( 2014 ). MethylAid: visual and interactive quality control of large Illumina 450k datasets . Bioinformatics 30 , 3435 – 3437 . doi: 10.1093/bioinformatics/btu566 . OpenUrl CrossRef PubMed 43. ↵ Zhou , W. , Laird , P.W. , and Shen , H . ( 2017 ). Comprehensive characterization, annotation and innovative use of Infinium DNA methylation BeadChip probes . Nucleic Acids Res 45 , e22 . doi: 10.1093/nar/gkw967 . OpenUrl CrossRef PubMed 44. ↵ Luijk , R. , Wu , H. , Ward-Caviness , C.K. , Hannon , E. , Carnero-Montoro , E. , Min , J.L. , Mandaviya , P. , Müller-Nurasyid , M. , Mei , H. , van der Maarel , S.M. et al. ( 2018 ). Autosomal genetic variation is associated with DNA methylation in regions variably escaping X-chromosome inactivation . Nat Commun 9 , 3738 . doi: 10.1038/s41467-018-05714-3 . OpenUrl CrossRef PubMed 45. ↵ Hop , P.J. , Luijk , R. , Daxinger , L. , van Iterson , M. , Dekkers , K.F. , Jansen , R. , van Meurs , J.B.J. , t Hoen , P.A.C. , Ikram , M.A. , van Greevenbroek , M.M.J. et al. ( 2020 ). Genome-wide identification of genes regulating DNA methylation using genetic anchors for causal inference . Genome Biol 21 , 220 . doi: 10.1186/s13059-020-02114-z . OpenUrl CrossRef PubMed 46. ↵ Liu , Y. , Sinke , L. , Jonkman , T.H. , Slieker , R.C. , van Zwet , E.W. , Daxinger , L. , and Heijmans , B.T. ( 2023 ). The inactive X chromosome accumulates widespread epigenetic variability with age . Clin Epigenetics 15 , 135 . doi: 10.1186/s13148-023-01549-y . OpenUrl CrossRef 47. ↵ Zhernakova , D.V. , Deelen , P. , Vermaat , M. , van Iterson , M. , van Galen , M. , Arindrarto , W. , van ’t Hof , P. , Mei , H. , van Dijk , F. , Westra , H.J. et al. ( 2017 ). Identification of context- dependent expression quantitative trait loci in whole blood . Nat Genet 49 , 139 – 145 . doi: 10.1038/ng.3737 . OpenUrl CrossRef PubMed 48. ↵ van Iterson , M. , Cats , D. , Hop , P. , and Heijmans , B.T. ( 2018 ). omicsPrint: detection of data linkage errors in multiple omics studies . Bioinformatics 34 , 2142 – 2143 . doi: 10.1093/bioinformatics/bty062 . OpenUrl CrossRef PubMed 49. ↵ Francis , P.T. , Costello , H. , and Hayes , G.M . ( 2018 ). Brains for Dementia Research: Evolution in a Longitudinal Brain Donation Cohort to Maximize Current and Future Value . J Alzheimers Dis 66 , 1635 – 1644 . doi: 10.3233/jad-180699 . OpenUrl CrossRef PubMed 50. ↵ Shireby , G. , Dempster , E.L. , Policicchio , S. , Smith , R.G. , Pishva , E. , Chioza , B. , Davies , J.P. , Burrage , J. , Lunnon , K. , Seiler Vellame , D. , et al. ( 2022 ). DNA methylation signatures of Alzheimer’s disease neuropathology in the cortex are primarily driven by variation in non- neuronal cell-types . Nat Commun 13 , 5620 . doi: 10.1038/s41467-022-33394-7 . OpenUrl CrossRef PubMed 51. ↵ Hannon , E. , Shireby , G.L. , Brookes , K. , Attems , J. , Sims , R. , Cairns , N.J. , Love , S. , Thomas , A.J. , Morgan , K. , Francis , P.T. , and Mill , J . ( 2020 ). Genetic risk for Alzheimer’s disease influences neuropathology via multiple biological pathways . Brain Commun 2 , fcaa167. doi: 10.1093/braincomms/fcaa167 . OpenUrl CrossRef 52. ↵ Blauwendraat , C. , Faghri , F. , Pihlstrom , L. , Geiger , J.T. , Elbaz , A. , Lesage , S. , Corvol , J.C. , May , P. , Nicolas , A. , Abramzon , Y. , et al. ( 2017 ). NeuroChip, an updated version of the NeuroX genotyping platform to rapidly screen for variants associated with neurological diseases . Neurobiol Aging 57 , 247 . e249 – 247 .e213. doi: 10.1016/j.neurobiolaging.2017.05.009 . OpenUrl CrossRef 53. ↵ Chang , C.C. , Chow , C.C. , Tellier , L.C. , Vattikuti , S. , Purcell , S.M. , and Lee , J.J . ( 2015 ). Second- generation PLINK: rising to the challenge of larger and richer datasets . Gigascience 4 , 7 . doi: 10.1186/s13742-015-0047-8 . OpenUrl CrossRef PubMed 54. ↵ Das , S. , Forer , L. , Schönherr , S. , Sidore , C. , Locke , A.E. , Kwong , A. , Vrieze , S.I. , Chew , E.Y. , Levy , S. , McGue , M. , et al. ( 2016 ). Next-generation genotype imputation service and methods . Nat Genet 48 , 1284 – 1287 . doi: 10.1038/ng.3656 . OpenUrl CrossRef PubMed 55. ↵ Loh , P.R. , Danecek , P. , Palamara , P.F. , Fuchsberger , C. , Y, A.R., H, K.F. , Schoenherr , S. , Forer , L. , McCarthy , S. , Abecasis , G.R. , et al. ( 2016 ). Reference-based phasing using the Haplotype Reference Consortium panel . Nat Genet 48 , 1443 – 1448 . doi: 10.1038/ng.3679 . OpenUrl CrossRef PubMed 56. ↵ Moran , S. , Arribas , C. , and Esteller , M . ( 2016 ). Validation of a DNA methylation microarray for 850,000 CpG sites of the human genome enriched in enhancer sequences . Epigenomics 8 , 389 – 399 . doi: 10.2217/epi.15.114 . OpenUrl CrossRef PubMed 57. ↵ Pidsley , R. , CC, Y.W. , Volta , M. , Lunnon , K. , Mill , J. , and Schalkwyk , L.C. ( 2013 ). A data-driven approach to preprocessing Illumina 450K methylation array data . BMC Genomics 14 , 293 . doi: 10.1186/1471-2164-14-293 . OpenUrl CrossRef PubMed 58. ↵ Hahne , F. , and Ivanek , R . ( 2016 ). Visualizing Genomic Data Using Gviz and Bioconductor . Methods Mol Biol 1418 , 335 – 351 . doi: 10.1007/978-1-4939-3578-9_16 . OpenUrl CrossRef PubMed 59. ↵ Isbel , L. , Prokopuk , L. , Wu , H. , Daxinger , L. , Oey , H. , Spurling , A. , Lawther , A.J. , Hale , M.W. , and Whitelaw , E . ( 2016 ). Wiz binds active promoters and CTCF-binding sites and is required for normal behaviour in the mouse . Elife 5 . doi: 10.7554/eLife.15082 . OpenUrl CrossRef 60. ↵ Hirayama , T. , Tarusawa , E. , Yoshimura , Y. , Galjart , N. , and Yagi , T . ( 2012 ). CTCF is required for neural development and stochastic expression of clustered Pcdh genes in neurons . Cell Rep 2 , 345 – 357 . doi: 10.1016/j.celrep.2012.06.014 . OpenUrl CrossRef PubMed Web of Science 61. ↵ Miyake , K. , Hirasawa , T. , Soutome , M. , Itoh , M. , Goto , Y. , Endoh , K. , Takahashi , K. , Kudo , S. , Nakagawa , T. , Yokoi , S. , et al. ( 2011 ). The protocadherins, PCDHB1 and PCDH7, are regulated by MeCP2 in neuronal cells and brain tissues: implication for pathogenesis of Rett syndrome . BMC Neurosci 12 , 81. doi: 10.1186/1471-2202-12-81 . OpenUrl CrossRef PubMed 62. ↵ Shabalin , A.A . ( 2012 ). Matrix eQTL: ultra fast eQTL analysis via large matrix operations . Bioinformatics 28 , 1353 – 1358 . doi: 10.1093/bioinformatics/bts163 . OpenUrl CrossRef PubMed Web of Science 63. ↵ Wang , J. , Zhao , Q. , Hastie , T. , and Owen , A.B . ( 2017 ). CONFOUNDER ADJUSTMENT IN MULTIPLE HYPOTHESIS TESTING . Ann Stat 45 , 1863 – 1894 . doi: 10.1214/16-aos1511 . OpenUrl CrossRef PubMed 64. ↵ Zheng , S.C. , Breeze , C.E. , Beck , S. , and Teschendorff , A.E . ( 2018 ). Identification of differentially methylated cell types in epigenome-wide association studies . Nat Methods 15 , 1059 – 1066 . doi: 10.1038/s41592-018-0213-x . OpenUrl CrossRef PubMed 65. ↵ SIMES R.J. ( 1986 ). An improved Bonferroni procedure for multiple tests of significance . Biometrika 73 , 751 – 754 . doi: 10.1093/biomet/73.3.751 . OpenUrl CrossRef Web of Science 66. ↵ Chernus , J.M. , Allen , E.G. , Zeng , Z. , Hoffman , E.R. , Hassold , T.J. , Feingold , E. , and Sherman , S.L . ( 2019 ). A candidate gene analysis and GWAS for genes associated with maternal nondisjunction of chromosome 21 . PLoS Genet 15 , e1008414 . doi: 10.1371/journal.pgen.1008414 . OpenUrl CrossRef PubMed 67. ↵ Võsa , U. , Claringbould , A. , Westra , H.J. , Bonder , M.J. , Deelen , P. , Zeng , B. , Kirsten , H. , Saha , A. , Kreuzhuber , R. , Yazar , S. , et al. ( 2021 ). Large-scale cis- and trans-eQTL analyses identify thousands of genetic loci and polygenic scores that regulate blood gene expression . Nat Genet 53 , 1300 – 1310 . doi: 10.1038/s41588-021-00913-z . OpenUrl CrossRef PubMed 68. ↵ Houseman , E.A. , Accomando , W.P. , Koestler , D.C. , Christensen , B.C. , Marsit , C.J. , Nelson , H.H. , Wiencke , J.K. , and Kelsey , K.T . ( 2012 ). DNA methylation arrays as surrogate measures of cell mixture distribution . BMC Bioinformatics 13 , 86 . doi: 10.1186/1471-2105-13-86 . OpenUrl CrossRef PubMed 69. ↵ de Klein N. Tsai , E.A. , Vochteloo , M. , Baird , D. , Huang , Y. , Chen , C.Y. , van Dam , S. , Oelen , R. , Deelen , P. , Bakker , O.B. et al. ( 2023 ). Brain expression quantitative trait locus and network analyses reveal downstream effects and putative drivers for brain-related diseases . Nat Genet 55 , 377 – 388 . doi: 10.1038/s41588-023-01300-6 . OpenUrl CrossRef 70. ↵ Begnis , M. , Duc , J. , Offner , S. , Grun , D. , Sheppard , S. , Rosspopoff , O. , and Trono , D . ( 2024 ). Clusters of lineage-specific genes are anchored by ZNF274 in repressive perinucleolar compartments . Sci Adv 10 , eado1662. doi: 10.1126/sciadv.ado1662 . OpenUrl CrossRef 71. ↵ Min , J.L. , Hemani , G. , Hannon , E. , Dekkers , K.F. , Castillo-Fernandez , J. , Luijk , R. , Carnero-Montoro , E. , Lawson , D.J. , Burrows , K. , Suderman , M. , et al. ( 2021 ). Genomic and phenotypic insights from an atlas of genetic effects on DNA methylation . Nat Genet 53 , 1311 – 1321 . doi: 10.1038/s41588-021-00923-x . OpenUrl CrossRef PubMed 72. ↵ Peng , Q. , Liu , X. , Li , W. , Jing , H. , Li , J. , Gao , X. , Luo , Q. , Breeze , C.E. , Pan , S. , Zheng , Q. , et al. ( 2024 ). Analysis of blood methylation quantitative trait loci in East Asians reveals ancestry-specific impacts on complex traits . Nat Genet 56 , 846 – 860 . doi: 10.1038/s41588-023-01494-9 . OpenUrl CrossRef PubMed 73. ↵ Slieker , R.C. , Bos , S.D. , Goeman , J.J. , Bovée , J.V. , Talens , R.P. , van der Breggen , R. , Suchiman , H.E. , Lameijer , E.W. , Putter , H. , van den Akker , E.B. et al. ( 2013 ). Identification and systematic annotation of tissue-specific differentially methylated regions using the Illumina 450k array . Epigenetics Chromatin 6 , 26 . doi: 10.1186/1756-8935-6-26 . OpenUrl CrossRef PubMed 74. ↵ Hannon , E. , Mansell , G. , Walker , E. , Nabais , M.F. , Burrage , J. , Kepa , A. , Best-Lane , J. , Rose , A. , Heck , S. , Moffitt , T.E. , et al. ( 2021 ). Assessing the co-variability of DNA methylation across peripheral cells and tissues: Implications for the interpretation of findings in epigenetic epidemiology . PLoS Genet 17 , e1009443 . doi: 10.1371/journal.pgen.1009443 . OpenUrl CrossRef PubMed 75. ↵ Quenneville , S. , Verde , G. , Corsinotti , A. , Kapopoulou , A. , Jakobsson , J. , Offner , S. , Baglivo , I. , Pedone , P.V. , Grimaldi , G. , Riccio , A. , and Trono , D . ( 2011 ). In embryonic stem cells, ZFP57/KAP1 recognize a methylated hexanucleotide to affect chromatin and DNA methylation of imprinting control regions . Mol Cell 44 , 361-372. doi: 10.1016/j.molcel.2011.08.032 . OpenUrl CrossRef PubMed Web of Science 76. ↵ Zuo , X. , Sheng , J. , Lau , H.T. , McDonald , C.M. , Andrade , M. , Cullen , D.E. , Bell , F.T. , Iacovino , M. , Kyba , M. , Xu , G. , and Li , X . ( 2012 ). Zinc finger protein ZFP57 requires its co-factor to recruit DNA methyltransferases and maintains DNA methylation imprint in embryonic stem cells via its transcriptional repression domain . J Biol Chem 287 , 2107 – 2118 . doi: 10.1074/jbc.M111.322644 . OpenUrl Abstract / FREE Full Text 77. ↵ Kunkle , B.W. , Grenier-Boley , B. , Sims , R. , Bis , J.C. , Damotte , V. , Naj , A.C. , Boland , A. , Vronskaya , M. , van der Lee , S.J. , Amlie-Wolf , A. et al. ( 2019 ). Genetic meta-analysis of diagnosed Alzheimer’s disease identifies new risk loci and implicates Aβ, tau, immunity and lipid processing . Nat Genet 51 , 414 – 430 . doi: 10.1038/s41588-019-0358-2 . OpenUrl CrossRef PubMed 78. ↵ Schmithorst , V. , Bais , A. , Badaly , D. , Williams , K. , Gabriel , G. , Ceschin , R. , Wallace , J. , Lee , V. , Lopez , O. , Cohen , A. et al. ( 2024 ). Complex Regulation of Protocadherin Epigenetics on Aging-Related Brain Health . medRxiv . doi: 10.1101/2024.04.21.24306143 . OpenUrl Abstract / FREE Full Text 79. ↵ Thummer , R.P. , Drenth-Diephuis , L.J. , Carney , K.E. , and Eggen , B.J . ( 2010 ). Functional characterization of single-nucleotide polymorphisms in the human undifferentiated embryonic-cell transcription factor 1 gene . DNA Cell Biol 29 , 241 – 248 . doi: 10.1089/dna.2009.0981 . OpenUrl CrossRef PubMed View the discussion thread. Back to top Previous Next Posted December 21, 2024. Download PDF Supplementary Material Email Thank you for your interest in spreading the word about bioRxiv. 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 Identification of SENP7 and UTF1/VENTX as new loci influencing clustered protocadherin methylation across blood and brain using a genome-wide association study Message Subject (Your Name) has forwarded a page to you from bioRxiv Message Body (Your Name) thought you would like to see this page from the bioRxiv 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 Identification of SENP7 and UTF1 / VENTX as new loci influencing clustered protocadherin methylation across blood and brain using a genome-wide association study Yunfeng Liu , Maja Vukic , Eilis Hannon , Hailiang Mei , BIOS Consortium , Jonathan Mill , Lucia Daxinger , Bastiaan T. Heijmans bioRxiv 2024.12.19.629385; doi: https://doi.org/10.1101/2024.12.19.629385 Share This Article: Copy Citation Tools Identification of SENP7 and UTF1 / VENTX as new loci influencing clustered protocadherin methylation across blood and brain using a genome-wide association study Yunfeng Liu , Maja Vukic , Eilis Hannon , Hailiang Mei , BIOS Consortium , Jonathan Mill , Lucia Daxinger , Bastiaan T. Heijmans bioRxiv 2024.12.19.629385; doi: https://doi.org/10.1101/2024.12.19.629385 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 Genetics Subject Areas All Articles Animal Behavior and Cognition (7653) Biochemistry (17763) Bioengineering (13944) Bioinformatics (42101) Biophysics (21509) Cancer Biology (18667) Cell Biology (25592) Clinical Trials (138) Developmental Biology (13413) Ecology (19969) Epidemiology (2067) Evolutionary Biology (24393) Genetics (15647) Genomics (22582) Immunology (17791) Microbiology (40524) Molecular Biology (17222) Neuroscience (88860) Paleontology (667) Pathology (2848) Pharmacology and Toxicology (4841) Physiology (7670) Plant Biology (15182) Scientific Communication and Education (2048) Synthetic Biology (4312) Systems Biology (9843) Zoology (2274)