[{"quality_controlled":"1","date_created":"2026-03-23T15:10:03Z","OA_type":"gold","oa":1,"article_processing_charge":"Yes","publisher":"Elsevier","article_type":"original","article_number":"101162","ddc":["000","570"],"month":"02","status":"public","abstract":[{"text":"Human height is a model for the genetic analysis of complex traits, and recent studies suggest the presence of thousands of common genetic variant associations and hundreds of low-frequency/rare variants. Here, we develop a new algorithmic paradigm based on approximate message passing (genomic vector approximate message passing [gVAMP]) for identifying DNA sequence variants associated with complex traits and common diseases in large-scale whole-genome sequencing (WGS) data. We show that gVAMP accurately localizes associations to variants with the correct frequency and position in the DNA, outperforming existing fine-mapping methods in selecting the appropriate genetic variants within WGS data. We then apply gVAMP to jointly model the relationship of tens of millions of WGS variants with human height in hundreds of thousands of UK Biobank individuals. We identify 59 rare variants and gene burden scores alongside many hundreds of DNA regions containing common variant associations and show that understanding the genetic basis of complex traits will require the joint analysis of hundreds of millions of variables measured on millions of people. The polygenic risk scores obtained from gVAMP have high accuracy (including a prediction accuracy of ∼46% for human height) and outperform current methods for downstream tasks such as mixed linear model association testing across 13 UK Biobank traits. In conclusion, gVAMP offers a scalable foundation for a wider range of analyses in WGS data.","lang":"eng"}],"DOAJ_listed":"1","publication_identifier":{"eissn":["2666-979X"]},"publication":"Cell Genomics","related_material":{"record":[{"relation":"dissertation_contains","id":"22258","status":"public"}],"link":[{"description":"News on ISTA website","url":"https://ista.ac.at/en/news/big-data-and-human-height/","relation":"press_release"}]},"user_id":"ba8df636-2132-11f1-aed0-ed93e2281fdd","has_accepted_license":"1","acknowledgement":"We thank Malgorzata Borczyk for creating the gene burden scores. We thank Robin Beaumont, Amedeo Roberto Esposito, Gareth Hawkes, Philip Schniter, Matthew Stephens, Pragya Sur, Peter Visscher, Michael Weedon, and Harry Wright for providing valuable suggestions and comments on earlier versions of the work. This project was funded by a Lopez-Loreta Prize to M.M., an SNSF Eccellenza Grant to M.R.R. (PCEGP3-181181), an ERC Starting Grant to M.M. (INF2, project number 101161364), and core funding from ISTA. High-performance computing was supported by the Scientific Service Units (SSU) of ISTA through resources provided by Scientific Computing (SciComp). We would like to acknowledge the participants and investigators of the UK Biobank study. We gratefully acknowledge the All of Us participants for their contributions, without whom this research would not have been possible. We also thank the National Institutes of Health All of Us Research Program for making available the participant data (and/or samples and/or cohort) examined in this study.","language":[{"iso":"eng"}],"main_file_link":[{"url":"https://doi.org/10.1016/j.xgen.2026.101162","open_access":"1"}],"date_published":"2026-02-18T00:00:00Z","date_updated":"2026-07-23T05:33:49Z","tmp":{"name":"Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)","legal_code_url":"https://creativecommons.org/licenses/by-nc-nd/4.0/legalcode","image":"/images/cc_by_nc_nd.png","short":"CC BY-NC-ND (4.0)"},"day":"18","year":"2026","doi":"10.1016/j.xgen.2026.101162","title":"Joint modeling of whole-genome sequencing data for human height via approximate message passing","corr_author":"1","OA_place":"publisher","project":[{"name":"Prix Lopez-Loretta 2019 - Marco Mondelli","_id":"059876FA-7A3F-11EA-A408-12923DDC885E"},{"grant_number":"101161364","_id":"911e6d1f-16d5-11f0-9cad-c5c68c6a1cdf","name":"Inference in High Dimensions: Light-speed Algorithms and Information Limits"},{"grant_number":"PCEGP3_181181","_id":"9B8D11D6-BA93-11EA-9121-9846C619BF3A","name":"Improving estimation and prediction of common complex disease risk"}],"publication_status":"epub_ahead","citation":{"mla":"Depope, Al, et al. “Joint Modeling of Whole-Genome Sequencing Data for Human Height via Approximate Message Passing.” <i>Cell Genomics</i>, 101162, Elsevier, 2026, doi:<a href=\"https://doi.org/10.1016/j.xgen.2026.101162\">10.1016/j.xgen.2026.101162</a>.","chicago":"Depope, Al, Jakub Bajzik, Marco Mondelli, and Matthew Richard Robinson. “Joint Modeling of Whole-Genome Sequencing Data for Human Height via Approximate Message Passing.” <i>Cell Genomics</i>. Elsevier, 2026. <a href=\"https://doi.org/10.1016/j.xgen.2026.101162\">https://doi.org/10.1016/j.xgen.2026.101162</a>.","short":"A. Depope, J. Bajzik, M. Mondelli, M.R. Robinson, Cell Genomics (2026).","ista":"Depope A, Bajzik J, Mondelli M, Robinson MR. 2026. Joint modeling of whole-genome sequencing data for human height via approximate message passing. Cell Genomics., 101162.","ama":"Depope A, Bajzik J, Mondelli M, Robinson MR. Joint modeling of whole-genome sequencing data for human height via approximate message passing. <i>Cell Genomics</i>. 2026. doi:<a href=\"https://doi.org/10.1016/j.xgen.2026.101162\">10.1016/j.xgen.2026.101162</a>","ieee":"A. Depope, J. Bajzik, M. Mondelli, and M. R. Robinson, “Joint modeling of whole-genome sequencing data for human height via approximate message passing,” <i>Cell Genomics</i>. Elsevier, 2026.","apa":"Depope, A., Bajzik, J., Mondelli, M., &#38; Robinson, M. R. (2026). Joint modeling of whole-genome sequencing data for human height via approximate message passing. <i>Cell Genomics</i>. Elsevier. <a href=\"https://doi.org/10.1016/j.xgen.2026.101162\">https://doi.org/10.1016/j.xgen.2026.101162</a>"},"author":[{"full_name":"Depope, Al","last_name":"Depope","id":"0b77531d-dbcd-11ea-9d1d-a8eee0bf3830","first_name":"Al"},{"first_name":"Jakub","id":"b995e25b-8c4b-11ed-a6d8-f71b7bcd6122","last_name":"Bajzik","full_name":"Bajzik, Jakub"},{"full_name":"Mondelli, Marco","orcid":"0000-0002-3242-7020","first_name":"Marco","last_name":"Mondelli","id":"27EB676C-8706-11E9-9510-7717E6697425"},{"first_name":"Matthew Richard","id":"E5D42276-F5DA-11E9-8E24-6303E6697425","last_name":"Robinson","orcid":"0000-0001-8982-8813","full_name":"Robinson, Matthew Richard"}],"department":[{"_id":"MaMo"},{"_id":"MaRo"}],"_id":"21488","oa_version":"Published Version","type":"journal_article"},{"publication_identifier":{"issn":["1474-7596"],"eissn":["1474-760X"]},"DOAJ_listed":"1","publication":"Genome Biology","status":"public","abstract":[{"text":"Background: DNA methylation (DNAm) can regulate gene expression, and its genome-wide patterns (epigenetic scores or EpiScores) can act as biomarkers for complex traits. The relative stability of methylation profiles may enable better assessment of chronic exposures compared to single time-point protein measures. We present the first large-scale epigenetic study of the highly-abundant serum proteome measured via ultra-high throughput mass spectrometry in 14,671 samples from the Generation Scotland cohort. We further demonstrate the first large-scale comparison of protein EpiScores and their respective proteins as predictors of incident cardiovascular disease.\r\n\r\nResults: Marginal epigenome-wide association models, adjusting for age, sex, measurement batch, estimated white cell proportions, BMI, smoking and methylation principal components, reveal 15,855 significant CpG – protein associations across 125 of 133 proteins PBonferroni < 2.71 × 10-10. Bayesian epigenome-wide association studies of the same 133 proteins reveal 697 CpG-Protein associations (posterior inclusion probability > 0.95). 112 protein EpiScores correlate significantly with their respective protein in a holdout test-set. Of these, sixteen associate significantly with incident all-cause cardiovascular disease (Nevents=191) compared to one measured protein.\r\n\r\nConclusions: We highlight a complex interplay between the blood-based methylome and proteome. Importantly, we show that protein EpiScores correlate with measured proteins and demonstrate that the, as-yet understudied, high-abundance proteome may yield clinically relevant biomarkers. The protein EpiScores demonstrate more significant associations with cardiovascular disease than directly measured proteins, suggesting their potential as clinical biomarkers for monitoring or predicting disease risk. We suggest that biomarker development could be enhanced by the consideration of protein EpiScores alongside measured proteins.","lang":"eng"}],"month":"12","volume":26,"article_processing_charge":"Yes","quality_controlled":"1","oa":1,"date_created":"2025-12-14T23:02:04Z","OA_type":"gold","ddc":["570"],"article_number":"417","publisher":"Springer Nature","file_date_updated":"2025-12-15T13:18:07Z","article_type":"original","_id":"20816","department":[{"_id":"MaRo"}],"intvolume":"        26","type":"journal_article","oa_version":"Published Version","OA_place":"publisher","publication_status":"published","author":[{"full_name":"Robertson, Josephine A.","last_name":"Robertson","first_name":"Josephine A."},{"full_name":"Bajzik, Jakub","last_name":"Bajzik","id":"b995e25b-8c4b-11ed-a6d8-f71b7bcd6122","first_name":"Jakub"},{"full_name":"Vernardis, Spyros","first_name":"Spyros","last_name":"Vernardis"},{"full_name":"Chybowska, Aleksandra D.","last_name":"Chybowska","first_name":"Aleksandra D."},{"last_name":"Mccartney","first_name":"Daniel L.","full_name":"Mccartney, Daniel L."},{"full_name":"Grauslys, Arturas","first_name":"Arturas","last_name":"Grauslys"},{"full_name":"Mur, Jure","first_name":"Jure","last_name":"Mur"},{"full_name":"Smith, Hannah M.","first_name":"Hannah M.","last_name":"Smith"},{"full_name":"Campbell, Archie","first_name":"Archie","last_name":"Campbell"},{"full_name":"Drake, Camilla","last_name":"Drake","first_name":"Camilla"},{"full_name":"Grant, Hannah","first_name":"Hannah","last_name":"Grant"},{"full_name":"Pearce, Jamie","first_name":"Jamie","last_name":"Pearce"},{"full_name":"Russ, Tom C.","first_name":"Tom C.","last_name":"Russ"},{"last_name":"Adkin","first_name":"Poppy","full_name":"Adkin, Poppy"},{"first_name":"Matthew","last_name":"White","full_name":"White, Matthew"},{"last_name":"Brigden","first_name":"Charles","full_name":"Brigden, Charles"},{"last_name":"Messner","first_name":"Christoph B.","full_name":"Messner, Christoph B."},{"full_name":"Porteous, David J.","last_name":"Porteous","first_name":"David J."},{"last_name":"Hayward","first_name":"Caroline","full_name":"Hayward, Caroline"},{"full_name":"Cox, Simon R.","last_name":"Cox","first_name":"Simon R."},{"full_name":"Zelezniak, Aleksej","last_name":"Zelezniak","first_name":"Aleksej"},{"first_name":"Markus","last_name":"Ralser","full_name":"Ralser, Markus"},{"orcid":"0000-0001-8982-8813","full_name":"Robinson, Matthew Richard","last_name":"Robinson","id":"E5D42276-F5DA-11E9-8E24-6303E6697425","first_name":"Matthew Richard"},{"first_name":"Riccardo E.","last_name":"Marioni","full_name":"Marioni, Riccardo E."}],"citation":{"ama":"Robertson JA, Bajzik J, Vernardis S, et al. Methylome-wide association studies and epigenetic biomarker development for 133 mass spectrometry-assessed circulating proteins in 14,671 Generation Scotland participants. <i>Genome Biology</i>. 2025;26. doi:<a href=\"https://doi.org/10.1186/s13059-025-03892-0\">10.1186/s13059-025-03892-0</a>","ieee":"J. A. Robertson <i>et al.</i>, “Methylome-wide association studies and epigenetic biomarker development for 133 mass spectrometry-assessed circulating proteins in 14,671 Generation Scotland participants,” <i>Genome Biology</i>, vol. 26. Springer Nature, 2025.","apa":"Robertson, J. A., Bajzik, J., Vernardis, S., Chybowska, A. D., Mccartney, D. L., Grauslys, A., … Marioni, R. E. (2025). Methylome-wide association studies and epigenetic biomarker development for 133 mass spectrometry-assessed circulating proteins in 14,671 Generation Scotland participants. <i>Genome Biology</i>. Springer Nature. <a href=\"https://doi.org/10.1186/s13059-025-03892-0\">https://doi.org/10.1186/s13059-025-03892-0</a>","chicago":"Robertson, Josephine A., Jakub Bajzik, Spyros Vernardis, Aleksandra D. Chybowska, Daniel L. Mccartney, Arturas Grauslys, Jure Mur, et al. “Methylome-Wide Association Studies and Epigenetic Biomarker Development for 133 Mass Spectrometry-Assessed Circulating Proteins in 14,671 Generation Scotland Participants.” <i>Genome Biology</i>. Springer Nature, 2025. <a href=\"https://doi.org/10.1186/s13059-025-03892-0\">https://doi.org/10.1186/s13059-025-03892-0</a>.","short":"J.A. Robertson, J. Bajzik, S. Vernardis, A.D. Chybowska, D.L. Mccartney, A. Grauslys, J. Mur, H.M. Smith, A. Campbell, C. Drake, H. Grant, J. Pearce, T.C. Russ, P. Adkin, M. White, C. Brigden, C.B. Messner, D.J. Porteous, C. Hayward, S.R. Cox, A. Zelezniak, M. Ralser, M.R. Robinson, R.E. Marioni, Genome Biology 26 (2025).","ista":"Robertson JA, Bajzik J, Vernardis S, Chybowska AD, Mccartney DL, Grauslys A, Mur J, Smith HM, Campbell A, Drake C, Grant H, Pearce J, Russ TC, Adkin P, White M, Brigden C, Messner CB, Porteous DJ, Hayward C, Cox SR, Zelezniak A, Ralser M, Robinson MR, Marioni RE. 2025. Methylome-wide association studies and epigenetic biomarker development for 133 mass spectrometry-assessed circulating proteins in 14,671 Generation Scotland participants. Genome Biology. 26, 417.","mla":"Robertson, Josephine A., et al. “Methylome-Wide Association Studies and Epigenetic Biomarker Development for 133 Mass Spectrometry-Assessed Circulating Proteins in 14,671 Generation Scotland Participants.” <i>Genome Biology</i>, vol. 26, 417, Springer Nature, 2025, doi:<a href=\"https://doi.org/10.1186/s13059-025-03892-0\">10.1186/s13059-025-03892-0</a>."},"title":"Methylome-wide association studies and epigenetic biomarker development for 133 mass spectrometry-assessed circulating proteins in 14,671 Generation Scotland participants","tmp":{"name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)","image":"/images/cc_by.png","short":"CC BY (4.0)","legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode"},"file":[{"relation":"main_file","date_updated":"2025-12-15T13:18:07Z","file_name":"2025_GenomeBiology_Robertson.pdf","checksum":"7c92919af1b5820d01e91e08906a411f","content_type":"application/pdf","file_size":2206991,"access_level":"open_access","creator":"dernst","date_created":"2025-12-15T13:18:07Z","success":1,"file_id":"20825"}],"external_id":{"pmid":["41361833"]},"date_updated":"2025-12-15T13:19:41Z","date_published":"2025-12-08T00:00:00Z","doi":"10.1186/s13059-025-03892-0","pmid":1,"year":"2025","day":"08","scopus_import":"1","has_accepted_license":"1","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","acknowledgement":"Generation Scotland received core support from the Chief Scientist Office of the Scottish Government Health Directorates [CZD/16/6] and the Scottish Funding Council [HR03006] and is currently supported by the Wellcome Trust [216767/Z/19/Z]. Genotyping of the Generation Scotland samples was carried out by the Genetics Core Laboratory at the Edinburgh Clinical Research Facility, University of Edinburgh, Scotland and was funded by the Medical Research Council UK and the Wellcome Trust (Wellcome Trust Strategic Award “STratifying Resilience and Depression Longitudinally” (STRADL) Reference 104036/Z/14/Z). The DNA methylation profiling and analysis was supported by Wellcome Investigator Award 220857/Z/20/Z and Grant 104036/Z/14/Z (PI: Prof AM McIntosh) and through funding from NARSAD (Ref: 27404; awardee: Dr DM Howard) and the Royal College of Physicians of Edinburgh (Sim Fellowship; Awardee: Prof HC Whalley).\r\nJAR is a University of Edinburgh Clinical Academic Track PhD student, supported by the Wellcome Trust (319878/Z/24/Z). ADC was supported by a Medical Research Council PhD Studentship in Precision Medicine with funding from the Medical Research Council Doctoral Training Program and the University of Edinburgh College of Medicine and Veterinary Medicine. HMS is a student on the University of Edinburgh Translational Neuroscience PhD programme funded by the Wellcome Trust (218493/Z/19/Z). CH was funded by MRC Human Genetics Unit program (QTL in Health and Disease) (grant U.MC_UU_00007/10). S.R.C. is supported by a Sir Henry Dale Fellowship jointly funded by the Wellcome Trust and the Royal Society (221890/Z/20/Z). JM and REM were supported by Alzheimer’s Society project grant AS-PG-19b-010.","language":[{"iso":"eng"}]}]