[{"doi":"10.1038/s41397-026-00399-0","intvolume":"        26","oa_version":"Published Version","file":[{"checksum":"2fd3d7e48b779ac24245f6c35449b89a","file_name":"2026_PharmacogenomicsJour_Hajto.pdf","date_created":"2026-03-30T07:04:08Z","content_type":"application/pdf","date_updated":"2026-03-30T07:04:08Z","file_size":2618963,"success":1,"file_id":"21506","access_level":"open_access","relation":"main_file","creator":"dernst"}],"scopus_import":"1","type":"journal_article","author":[{"last_name":"Hajto","first_name":"Jacek","full_name":"Hajto, Jacek"},{"full_name":"Piechota, Marcin","first_name":"Marcin","last_name":"Piechota"},{"id":"30d4014e-7753-11eb-b44b-db6d61112e73","full_name":"Krätschmer, Ilse","first_name":"Ilse","last_name":"Krätschmer","orcid":"0000-0002-5636-9259"},{"last_name":"Konowalska","first_name":"Paula","full_name":"Konowalska, Paula"},{"last_name":"Boyle","first_name":"Gabriel E.","full_name":"Boyle, Gabriel E."},{"last_name":"Fowler","first_name":"Douglas M.","full_name":"Fowler, Douglas M."},{"last_name":"Borczyk","full_name":"Borczyk, Malgorzata","first_name":"Malgorzata"},{"last_name":"Korostynski","first_name":"Michal","full_name":"Korostynski, Michal"}],"external_id":{"pmid":["41803106"]},"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","issue":"2","publication_status":"published","ddc":["570"],"citation":{"apa":"Hajto, J., Piechota, M., Krätschmer, I., Konowalska, P., Boyle, G. E., Fowler, D. M., … Korostynski, M. (2026). Computational variant predictors for pharmacogenomics: From evaluation of single alleles to assessment of adverse drug reactions to antidepressants. <i>Pharmacogenomics Journal</i>. Springer Nature. <a href=\"https://doi.org/10.1038/s41397-026-00399-0\">https://doi.org/10.1038/s41397-026-00399-0</a>","ama":"Hajto J, Piechota M, Krätschmer I, et al. Computational variant predictors for pharmacogenomics: From evaluation of single alleles to assessment of adverse drug reactions to antidepressants. <i>Pharmacogenomics Journal</i>. 2026;26(2). doi:<a href=\"https://doi.org/10.1038/s41397-026-00399-0\">10.1038/s41397-026-00399-0</a>","ieee":"J. Hajto <i>et al.</i>, “Computational variant predictors for pharmacogenomics: From evaluation of single alleles to assessment of adverse drug reactions to antidepressants,” <i>Pharmacogenomics Journal</i>, vol. 26, no. 2. Springer Nature, 2026.","short":"J. Hajto, M. Piechota, I. Krätschmer, P. Konowalska, G.E. Boyle, D.M. Fowler, M. Borczyk, M. Korostynski, Pharmacogenomics Journal 26 (2026).","chicago":"Hajto, Jacek, Marcin Piechota, Ilse Krätschmer, Paula Konowalska, Gabriel E. Boyle, Douglas M. Fowler, Malgorzata Borczyk, and Michal Korostynski. “Computational Variant Predictors for Pharmacogenomics: From Evaluation of Single Alleles to Assessment of Adverse Drug Reactions to Antidepressants.” <i>Pharmacogenomics Journal</i>. Springer Nature, 2026. <a href=\"https://doi.org/10.1038/s41397-026-00399-0\">https://doi.org/10.1038/s41397-026-00399-0</a>.","ista":"Hajto J, Piechota M, Krätschmer I, Konowalska P, Boyle GE, Fowler DM, Borczyk M, Korostynski M. 2026. Computational variant predictors for pharmacogenomics: From evaluation of single alleles to assessment of adverse drug reactions to antidepressants. Pharmacogenomics Journal. 26(2), 8.","mla":"Hajto, Jacek, et al. “Computational Variant Predictors for Pharmacogenomics: From Evaluation of Single Alleles to Assessment of Adverse Drug Reactions to Antidepressants.” <i>Pharmacogenomics Journal</i>, vol. 26, no. 2, 8, Springer Nature, 2026, doi:<a href=\"https://doi.org/10.1038/s41397-026-00399-0\">10.1038/s41397-026-00399-0</a>."},"article_processing_charge":"Yes (in subscription journal)","volume":26,"OA_place":"publisher","date_published":"2026-03-09T00:00:00Z","file_date_updated":"2026-03-30T07:04:08Z","tmp":{"image":"/images/cc_by_nc_nd.png","short":"CC BY-NC-ND (4.0)","legal_code_url":"https://creativecommons.org/licenses/by-nc-nd/4.0/legalcode","name":"Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)"},"day":"09","date_created":"2026-03-29T22:07:08Z","status":"public","language":[{"iso":"eng"}],"acknowledgement":"This research has been conducted using the UK Biobank Resource under Application Number 62979. We are grateful to the UK Biobank and all its voluntary participants. This work used data provided by patients and collected by the NHS as part of their care and support.\r\n\r\nThis study was funded by the National Science Center, Poland: PRELUDIUM BIS-3 grant no. 2021/43/O/NZ7/01187 (development and benchmarking of variant scores) and SONATINA 5 grant 2021/40/C/NZ2/00218 (UKB analyses). Additional support came from the statutory funds of the Maj Institute of Pharmacology PAS. We gratefully acknowledge Poland’s high-performance Infrastructure PLGrid ACK Cyfronet AGH, for providing computer facilities and support within computational grant no PLG/2022/015861. DMF and GEB were funded by NIH grants NIH R35GM152106 and UM1HG011969.","publication":"Pharmacogenomics Journal","abstract":[{"text":"Currently, pharmacogenetics relies on partially annotated star alleles, leaving novel variants and complex haplotypes uninterpretable. Computational scoring frameworks could overcome these limitations. Here, we comprehensively evaluated the ability of existing (CADD, FATHMM-XF, PROVEAN, MutationAssessor, SIFT, PhyloP100, APF, APF2) and novel (PharmGScore and PharmMLScore) variant effect predictors to assess pharmacogenetic alleles in multiple scenarios. Altogether we analyzed 541 PharmVar alleles, high‑throughput CYP2C9 and CYP2C19 mutational maps, and 200 642 UK Biobank exomes linked with health records containing antidepressant treatment outcomes. Many evaluated tools, especially ensemble frameworks, matched or exceeded star allele classifications (ROC‑AUC up to 0.85 for allele definitions, 0.95 in vitro; TPR up to 0.99 for exomes) and accurately predicted severe antidepressant adverse events for carriers of deleterious variants in CYP2C19 (OR 1.20–1.35). Our findings show that computational predictors deliver star allele accuracy while overcoming their limitations. With additional validation, computational tools could enhance clinical decision frameworks by enabling continuous scoring, incorporating previously unknown variants, and providing genome-wide applicability.","lang":"eng"}],"fulldoi":"https://doi.org/10.1038/s41397-026-00399-0","year":"2026","publication_identifier":{"eissn":["1473-1150"],"issn":[" 1470-269X"]},"publisher":"Springer Nature","quality_controlled":"1","department":[{"_id":"MaRo"}],"pmid":1,"has_accepted_license":"1","oa":1,"OA_type":"hybrid","month":"03","article_type":"original","title":"Computational variant predictors for pharmacogenomics: From evaluation of single alleles to assessment of adverse drug reactions to antidepressants","_id":"21503","date_updated":"2026-03-30T07:10:50Z","article_number":"8"},{"article_number":"iyag042","date_updated":"2026-07-27T11:56:04Z","_id":"21484","title":"A quantitative genetic model for indirect genetic effects and genomic imprinting under random and assortative mating","oa":1,"pmid":1,"has_accepted_license":"1","PlanS_conform":"1","article_type":"original","month":"04","OA_type":"hybrid","department":[{"_id":"MaRo"}],"quality_controlled":"1","fulldoi":"https://doi.org/10.1093/genetics/iyag042","publisher":"Oxford University Press","year":"2026","publication_identifier":{"issn":["1943-2631"]},"acknowledgement":"We thank members of the Medical Genomics group at ISTA for their comments, which improved this manuscript. This work was funded by an SNSF Eccellenza Grant to MRR (PCEGP3-181181), and by core funding from the Institute of Science and Technology Austria.","language":[{"iso":"eng"}],"status":"public","abstract":[{"lang":"eng","text":"An individual's phenotype reflects a complex interplay of the direct effects of their DNA, epigenetic modifications of their DNA induced by their parents, and indirect effects of their parents' DNA. Here, we derive how the genetic variance within a population is changed under the influence of indirect maternal, paternal and parent-of-origin effects under random mating. We also consider indirect effects of a sibling, in particular how the genetic variance is altered when looking at the phenotypic difference between two siblings. The calculations are then extended to include assortative mating (AM), which alters the variance by inducing increased homozygosity and correlations within and across loci. AM likely leads to covariance of parental genetic effects, a measure of the similarity of parents in the indirect effects they have on their children. We propose that this assortment for parental characteristics, where biological parents create similar environments for their children, can create shared parental effects across traits and the appearance of cross-trait AM. Our theory shows how the resemblance among relatives increases under both AM, indirect and parent-of-origin effects. When our model is used to predict correlations among relatives in human height, we find that explaining the patterns observed in real data requires both indirect genetic effects and assortative mating. The degree to which direct, indirect and epigenetic effects shape the phenotypic variance of complex traits remains an open question that requires large-scale family data to be resolved."}],"publication":"Genetics","date_created":"2026-03-23T15:02:54Z","related_material":{"link":[{"relation":"software","url":"https://github.com/medical-genomics-group/familyMC"}]},"tmp":{"legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","short":"CC BY (4.0)","image":"/images/cc_by.png","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)"},"corr_author":"1","day":"01","das_tickbox":"1","dataavailabilitystatement":"The code used to simulate data can be found at https://github.\r\ncom/medical-genomics-group/familyMC. Simulations are based\r\non genotype data from 1000 Genomes Project downloaded from\r\nhttps://ftp.1000genomes.ebi. ac.uk/vol1/ftp/release/20130502/.\r\nSupplemental material available at GENETICS online.","date_published":"2026-04-01T00:00:00Z","file_date_updated":"2026-07-27T11:54:00Z","article_processing_charge":"Yes (via OA deal)","citation":{"mla":"Krätschmer, Ilse, and Matthew Richard Robinson. “A Quantitative Genetic Model for Indirect Genetic Effects and Genomic Imprinting under Random and Assortative Mating.” <i>Genetics</i>, vol. 232, no. 4, iyag042, Oxford University Press, 2026, doi:<a href=\"https://doi.org/10.1093/genetics/iyag042\">10.1093/genetics/iyag042</a>.","ista":"Krätschmer I, Robinson MR. 2026. A quantitative genetic model for indirect genetic effects and genomic imprinting under random and assortative mating. Genetics. 232(4), iyag042.","chicago":"Krätschmer, Ilse, and Matthew Richard Robinson. “A Quantitative Genetic Model for Indirect Genetic Effects and Genomic Imprinting under Random and Assortative Mating.” <i>Genetics</i>. Oxford University Press, 2026. <a href=\"https://doi.org/10.1093/genetics/iyag042\">https://doi.org/10.1093/genetics/iyag042</a>.","short":"I. Krätschmer, M.R. Robinson, Genetics 232 (2026).","ieee":"I. Krätschmer and M. R. Robinson, “A quantitative genetic model for indirect genetic effects and genomic imprinting under random and assortative mating,” <i>Genetics</i>, vol. 232, no. 4. Oxford University Press, 2026.","apa":"Krätschmer, I., &#38; Robinson, M. R. (2026). A quantitative genetic model for indirect genetic effects and genomic imprinting under random and assortative mating. <i>Genetics</i>. Oxford University Press. <a href=\"https://doi.org/10.1093/genetics/iyag042\">https://doi.org/10.1093/genetics/iyag042</a>","ama":"Krätschmer I, Robinson MR. A quantitative genetic model for indirect genetic effects and genomic imprinting under random and assortative mating. <i>Genetics</i>. 2026;232(4). doi:<a href=\"https://doi.org/10.1093/genetics/iyag042\">10.1093/genetics/iyag042</a>"},"ddc":["570"],"supplementarymaterial":"no","OA_place":"publisher","volume":232,"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","publication_status":"published","issue":"4","type":"journal_article","file":[{"date_updated":"2026-07-27T11:54:00Z","content_type":"application/pdf","file_size":734475,"success":1,"checksum":"926322c83b02522e96ab7a86e4011eec","file_name":"2026_Genetics_Kraetschmer.pdf","date_created":"2026-07-27T11:54:00Z","creator":"dernst","relation":"main_file","file_id":"22425","access_level":"open_access"}],"scopus_import":"1","external_id":{"pmid":["41677404"]},"author":[{"first_name":"Ilse","full_name":"Krätschmer, Ilse","orcid":"0000-0002-5636-9259","last_name":"Krätschmer","id":"30d4014e-7753-11eb-b44b-db6d61112e73"},{"id":"E5D42276-F5DA-11E9-8E24-6303E6697425","first_name":"Matthew Richard","full_name":"Robinson, Matthew Richard","orcid":"0000-0001-8982-8813","last_name":"Robinson"}],"intvolume":"       232","researchdata_availability":"no","doi":"10.1093/genetics/iyag042","oa_version":"Published Version"},{"article_number":"115736","date_updated":"2026-08-03T06:35:45Z","_id":"22614","title":"DES formulation for recycling synthetic fibre textile waste containing elastane","month":"07","article_type":"original","OA_type":"hybrid","oa":1,"has_accepted_license":"1","pmid":1,"PlanS_conform":"1","main_file_link":[{"open_access":"1","url":"https://doi.org/10.1016/j.wasman.2026.115736"}],"quality_controlled":"1","department":[{"_id":"MaRo"}],"publisher":"Elsevier","year":"2026","publication_identifier":{"issn":["0956-053X"],"eissn":["1879-2456"]},"fulldoi":"https://doi.org/10.1016/j.wasman.2026.115736","abstract":[{"text":"This study presents a sustainable and non-destructive recycling strategy for synthetic fibres, specifically polyethylene terephthalate (PET), polyamide 6 (PA6), polyamide 66 (PA66), and elastane (EL). Two deep eutectic solvents (DESs) were synthesised, enabling selective dissolution of EL without degrading the surrounding polymer matrices. The dissolved EL phase was subsequently recovered by centrifugation, demonstrating its potential for material reuse. Comprehensive characterisation confirmed that the process preserves fibre integrity. SEM imaging revealed no detectable changes in fibre morphology, while DSC and TGA analyses indicated that the thermal properties of both EL and synthetic polymers were preserved. ATR-FTIR spectroscopy verified the absence of measurable chemical modifications. Mechanical testing showed that solvent treatment did not compromise the tensile performance of PET, PA6, or PA66 fibres, confirming their suitability for fibre-to-fibre recycling.\r\nThe recovered fibres were successfully re-extruded into continuous filaments, confirming their melt processability and enabling potential applications in textile yarns, technical fibres, nonwovens, and polymer components via melt-spinning or moulding. These results demonstrate that the proposed DES-based method offers a promising approach for the circular recycling of complex fibre blends and provides a viable pathway towards industrial implementation.","lang":"eng"}],"publication":"Waste Management","status":"public","acknowledgement":"The financial support by the Austrian Federal Ministry of Economy, Energy and Tourism, the National Foundation for Research, Technology and Development and the Christian Doppler Research Association is gratefully acknowledged. The authors acknowledge “Open Access Funding by TU Wien” for financial support through its Open Access Funding Program.\r\nSpecial thanks are extended to EREMA Group GmbH, SALESIANER MIETTEX GmbH and Starlinger & Co GmbH for their material support and valuable input throughout the development of this study.","language":[{"iso":"eng"}],"date_created":"2026-08-02T22:01:51Z","day":"15","tmp":{"legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","short":"CC BY (4.0)","image":"/images/cc_by.png","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)"},"date_published":"2026-07-15T00:00:00Z","dataavailabilitystatement":"Data will be made available on request.","das_tickbox":"1","volume":224,"OA_place":"publisher","article_processing_charge":"Yes (via OA deal)","citation":{"ama":"Depope N, Depope A, Archodoulaki VM, et al. DES formulation for recycling synthetic fibre textile waste containing elastane. <i>Waste Management</i>. 2026;224. doi:<a href=\"https://doi.org/10.1016/j.wasman.2026.115736\">10.1016/j.wasman.2026.115736</a>","apa":"Depope, N., Depope, A., Archodoulaki, V. M., Dabrowska, A., Lendl, B., Mautner, A., … Bartl, A. (2026). DES formulation for recycling synthetic fibre textile waste containing elastane. <i>Waste Management</i>. Elsevier. <a href=\"https://doi.org/10.1016/j.wasman.2026.115736\">https://doi.org/10.1016/j.wasman.2026.115736</a>","ieee":"N. Depope <i>et al.</i>, “DES formulation for recycling synthetic fibre textile waste containing elastane,” <i>Waste Management</i>, vol. 224. Elsevier, 2026.","chicago":"Depope, Nika, Al Depope, Vasiliki Maria Archodoulaki, Alicja Dabrowska, Bernhard Lendl, Andreas Mautner, Wolfgang Ipsmiller, and Andreas Bartl. “DES Formulation for Recycling Synthetic Fibre Textile Waste Containing Elastane.” <i>Waste Management</i>. Elsevier, 2026. <a href=\"https://doi.org/10.1016/j.wasman.2026.115736\">https://doi.org/10.1016/j.wasman.2026.115736</a>.","short":"N. Depope, A. Depope, V.M. Archodoulaki, A. Dabrowska, B. Lendl, A. Mautner, W. Ipsmiller, A. Bartl, Waste Management 224 (2026).","ista":"Depope N, Depope A, Archodoulaki VM, Dabrowska A, Lendl B, Mautner A, Ipsmiller W, Bartl A. 2026. DES formulation for recycling synthetic fibre textile waste containing elastane. Waste Management. 224, 115736.","mla":"Depope, Nika, et al. “DES Formulation for Recycling Synthetic Fibre Textile Waste Containing Elastane.” <i>Waste Management</i>, vol. 224, 115736, Elsevier, 2026, doi:<a href=\"https://doi.org/10.1016/j.wasman.2026.115736\">10.1016/j.wasman.2026.115736</a>."},"ddc":["540"],"supplementarymaterial":"yes","publication_status":"epub_ahead","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","external_id":{"pmid":["42456595"]},"author":[{"last_name":"Depope","full_name":"Depope, Nika","first_name":"Nika"},{"id":"0b77531d-dbcd-11ea-9d1d-a8eee0bf3830","last_name":"Depope","first_name":"Al","full_name":"Depope, Al"},{"full_name":"Archodoulaki, Vasiliki Maria","first_name":"Vasiliki Maria","last_name":"Archodoulaki"},{"last_name":"Dabrowska","full_name":"Dabrowska, Alicja","first_name":"Alicja"},{"last_name":"Lendl","first_name":"Bernhard","full_name":"Lendl, Bernhard"},{"last_name":"Mautner","first_name":"Andreas","full_name":"Mautner, Andreas"},{"full_name":"Ipsmiller, Wolfgang","first_name":"Wolfgang","last_name":"Ipsmiller"},{"full_name":"Bartl, Andreas","first_name":"Andreas","last_name":"Bartl"}],"type":"journal_article","scopus_import":"1","oa_version":"Published Version","researchdata_availability":"upon request","intvolume":"       224","doi":"10.1016/j.wasman.2026.115736"},{"language":[{"iso":"eng"}],"acknowledgement":"We thank members of the Medical Genomics group at ISTA for their comments, which improved this manuscript. This work was funded by an SNSF Eccellenza Grant to MRR [PCEGP3-181181], and by core funding from the Institute of Science and Technology Austria. We would like to acknowledge the participants and investigators of the Generation Scotland and Lothian Birth Cohort studies. 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]. Genotyping and methylation typing of the GS: SFHS samples was carried out by the Genetics Core Laboratory at the Wellcome Trust Clinical Research Facility, 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]. DNA methylation data for Generation Scotland was also funded by a 2018 NARSAD Young Investigator Grant from the Brain and Behavior Research Foundation [Ref: 27404; awardee: Dr David M Howard] and by a John, Margaret, Alfred and Stewart Sim Fellowship from the Royal College of Physicians of Edinburgh (Awardee: Dr Heather C Whalley). The LBC1936 is supported by the Biotechnology and Biological Sciences Research Council, and the Economic and Social Research Council [BB/W008793/1] (which supports SEH, and JC), Age UK (Disconnected Mind project), the Milton Damerel Trust, the Medical Research Council [G0701120, G1001245, MR/M013111/1, MR/R024065/1] and the University of Edinburgh. Methylation typing of LBC1936 was supported by the Centre for Cognitive Ageing and Cognitive Epidemiology (Pilot Fund award), Age UK, The Wellcome Trust Institutional Strategic Support Fund, The University of Edinburgh, and The University of Queensland. HS is supported by funding from the Wellcome Trust 4-year PhD in Translational Neuroscience [218493/Z/19/Z]. SRC is also supported by a Sir Henry Dale Fellowship jointly funded by Wellcome and the Royal Society [221890/Z/20/Z]. High-performance computing was supported by the Scientific Service Units (SSU) of IST Austria through resources provided by Scientific Computing (SciComp).","status":"public","publication":"Bioinformatics Advances","abstract":[{"text":"Genomic measurements of DNA methylation, gene expression or protein levels are becoming more prevalent and are increasingly used to study health outcomes. However, most proposed association testing methods consider only marginal effects of each feature on a single outcome variable and are not set up to handle highly correlated, continuous data. Here, we introduce MAJA, a method to learn shared and outcome-specific effects for multiple traits in multi-omics data. MAJA determines the unique contribution of individual loci, genes, or molecular pathways to variation in one or more traits, conditional on all other measured “omics” data genome-wide. Simulations show MAJA accurately finds shared and distinct associations between omics-data and multiple traits and estimates omics-specific (co)variances, allowing for sparsity and correlations within the data. Applying MAJA to 12 outcome traits in Generation Scotland methylation data (n = 18 264), we find novel shared epigenetic probes among cholesterol metabolism, osteoarthritis, blood pressure and asthma. In contrast to marginal testing, we find only 10 CpG probes with significant effects above the genome-wide background. This highlights the need for joint association testing in highly correlated methylation data from whole blood and for studies of increased sample size in order to refine epigenomic associations in observational data.","lang":"eng"}],"date_created":"2026-09-22T05:41:01Z","tmp":{"legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","short":"CC BY (4.0)","image":"/images/cc_by.png","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)"},"day":"01","corr_author":"1","das_tickbox":"1","dataavailabilitystatement":"Access to the data is available with appropriate permission from the Generation Scotland Access Committee. Applications should be made to access@generationscotland.org. https://www.ed.ac.uk/lothian-birth-cohorts/data-access-collaboration gives information on the Lothian Birth Cohort data, which are available on request from the Lothian Birth Cohort Study, University of Edinburgh. Data from both cohorts are not publicly available as they contain information that could compromise participant consent and confidentiality.\r\n\r\nSource code is available at https://github.com/medical-genomics-group/MAJA.","date_published":"2026-09-01T00:00:00Z","file_date_updated":"2026-10-06T12:49:18Z","supplementarymaterial":"yes","citation":{"chicago":"Krätschmer, Ilse, Hannah M Smith, Daniel L McCartney, Elena Bernabeu, Mahdi Mahmoudi, Archie Campbell, Janie Corley, et al. “MAJA: Multivariate Bayesian Model for Discovery of Shared Epigenetic Pathways across Human Phenotypes.” <i>Bioinformatics Advances</i>. Oxford University Press, 2026. <a href=\"https://doi.org/10.1093/bioadv/vbag231\">https://doi.org/10.1093/bioadv/vbag231</a>.","short":"I. Krätschmer, H.M. Smith, D.L. McCartney, E. Bernabeu, M. Mahmoudi, A. Campbell, J. Corley, S.E. Harris, S.R. Cox, R.E. Marioni, M.R. Robinson, Bioinformatics Advances 6 (2026).","apa":"Krätschmer, I., Smith, H. M., McCartney, D. L., Bernabeu, E., Mahmoudi, M., Campbell, A., … Robinson, M. R. (2026). MAJA: Multivariate Bayesian model for discovery of shared epigenetic pathways across human phenotypes. <i>Bioinformatics Advances</i>. Oxford University Press. <a href=\"https://doi.org/10.1093/bioadv/vbag231\">https://doi.org/10.1093/bioadv/vbag231</a>","ama":"Krätschmer I, Smith HM, McCartney DL, et al. MAJA: Multivariate Bayesian model for discovery of shared epigenetic pathways across human phenotypes. <i>Bioinformatics Advances</i>. 2026;6(1). doi:<a href=\"https://doi.org/10.1093/bioadv/vbag231\">10.1093/bioadv/vbag231</a>","ieee":"I. Krätschmer <i>et al.</i>, “MAJA: Multivariate Bayesian model for discovery of shared epigenetic pathways across human phenotypes,” <i>Bioinformatics Advances</i>, vol. 6, no. 1. Oxford University Press, 2026.","mla":"Krätschmer, Ilse, et al. “MAJA: Multivariate Bayesian Model for Discovery of Shared Epigenetic Pathways across Human Phenotypes.” <i>Bioinformatics Advances</i>, vol. 6, no. 1, vbag231, Oxford University Press, 2026, doi:<a href=\"https://doi.org/10.1093/bioadv/vbag231\">10.1093/bioadv/vbag231</a>.","ista":"Krätschmer I, Smith HM, McCartney DL, Bernabeu E, Mahmoudi M, Campbell A, Corley J, Harris SE, Cox SR, Marioni RE, Robinson MR. 2026. MAJA: Multivariate Bayesian model for discovery of shared epigenetic pathways across human phenotypes. Bioinformatics Advances. 6(1), vbag231."},"ddc":["570"],"article_processing_charge":"Yes","OA_place":"publisher","volume":6,"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","issue":"1","publication_status":"published","scopus_import":"1","file":[{"creator":"dernst","relation":"main_file","file_id":"23064","access_level":"open_access","content_type":"application/pdf","date_updated":"2026-10-06T12:49:18Z","success":1,"file_size":1370368,"checksum":"86849f1b88c47d050be4aa0a40105a97","date_created":"2026-10-06T12:49:18Z","file_name":"2026_BioinformaticsAdvances_Kraetschmer.pdf"}],"type":"journal_article","author":[{"id":"30d4014e-7753-11eb-b44b-db6d61112e73","first_name":"Ilse","full_name":"Krätschmer, Ilse","orcid":"0000-0002-5636-9259","last_name":"Krätschmer"},{"last_name":"Smith","first_name":"Hannah M","full_name":"Smith, Hannah M"},{"last_name":"McCartney","first_name":"Daniel L","full_name":"McCartney, Daniel L"},{"last_name":"Bernabeu","full_name":"Bernabeu, Elena","first_name":"Elena"},{"last_name":"Mahmoudi","full_name":"Mahmoudi, Mahdi","first_name":"Mahdi"},{"first_name":"Archie","full_name":"Campbell, Archie","last_name":"Campbell"},{"last_name":"Corley","full_name":"Corley, Janie","first_name":"Janie"},{"last_name":"Harris","first_name":"Sarah E","full_name":"Harris, Sarah E"},{"first_name":"Simon R","full_name":"Cox, Simon R","last_name":"Cox"},{"last_name":"Marioni","full_name":"Marioni, Riccardo E","first_name":"Riccardo E"},{"full_name":"Robinson, Matthew Richard","first_name":"Matthew Richard","last_name":"Robinson","orcid":"0000-0001-8982-8813","id":"E5D42276-F5DA-11E9-8E24-6303E6697425"}],"external_id":{"pmid":["42761413"]},"doi":"10.1093/bioadv/vbag231","researchdata_availability":"no","intvolume":"         6","oa_version":"Published Version","date_updated":"2026-10-06T12:50:50Z","article_number":"vbag231","_id":"22972","title":"MAJA: Multivariate Bayesian model for discovery of shared epigenetic pathways across human phenotypes","DOAJ_listed":"1","has_accepted_license":"1","PlanS_conform":"1","pmid":1,"oa":1,"OA_type":"gold","article_type":"original","acknowledged_ssus":[{"_id":"ScienComp"}],"month":"09","quality_controlled":"1","department":[{"_id":"MaRo"}],"fulldoi":"https://doi.org/10.1093/bioadv/vbag231","year":"2026","publication_identifier":{"eissn":["2635-0041"]},"publisher":"Oxford University Press"},{"publisher":"Springer Nature","publication_identifier":{"eissn":["2041-1723"]},"year":"2026","fulldoi":"https://doi.org/10.1038/s41467-026-76877-7","department":[{"_id":"MaRo"}],"quality_controlled":"1","acknowledged_ssus":[{"_id":"ScienComp"}],"month":"08","article_type":"original","OA_type":"gold","oa":1,"has_accepted_license":"1","DOAJ_listed":"1","title":"Causal inference for multiple risk factors and diseases from genomics data","_id":"23043","article_number":"10153 ","date_updated":"2026-10-16T11:01:16Z","oa_version":"Published Version","intvolume":"        17","researchdata_availability":"yes","doi":"10.1038/s41467-026-76877-7","author":[{"id":"3591A0AA-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0001-6617-9742","last_name":"Machnik","first_name":"Nick N","full_name":"Machnik, Nick N"},{"id":"b9f6d5ef-7774-11eb-a47f-df2c75c02ee7","last_name":"Mahmoudi","full_name":"Mahmoudi, Seyed Mahdi","first_name":"Seyed Mahdi"},{"full_name":"Borczyk, Malgorzata","first_name":"Malgorzata","last_name":"Borczyk"},{"id":"30d4014e-7753-11eb-b44b-db6d61112e73","orcid":"0000-0002-5636-9259","last_name":"Krätschmer","first_name":"Ilse","full_name":"Krätschmer, Ilse"},{"last_name":"Bauer","full_name":"Bauer, Markus J.","first_name":"Markus J."},{"id":"E5D42276-F5DA-11E9-8E24-6303E6697425","orcid":"0000-0001-8982-8813","last_name":"Robinson","first_name":"Matthew Richard","full_name":"Robinson, Matthew Richard"}],"type":"journal_article","file":[{"file_id":"23070","access_level":"open_access","relation":"main_file","creator":"dernst","checksum":"05517674168a275c70f18e964ce33d8b","date_created":"2026-10-07T09:50:18Z","file_name":"2026_NatureComm_Machnik.pdf","date_updated":"2026-10-07T09:50:18Z","content_type":"application/pdf","success":1,"file_size":2345578}],"scopus_import":"1","publication_status":"published","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","volume":17,"OA_place":"publisher","article_processing_charge":"Yes","citation":{"ieee":"N. N. Machnik, S. M. Mahmoudi, M. Borczyk, I. Krätschmer, M. J. Bauer, and M. R. Robinson, “Causal inference for multiple risk factors and diseases from genomics data,” <i>Nature Communications</i>, vol. 17. Springer Nature, 2026.","ama":"Machnik NN, Mahmoudi SM, Borczyk M, Krätschmer I, Bauer MJ, Robinson MR. Causal inference for multiple risk factors and diseases from genomics data. <i>Nature Communications</i>. 2026;17. doi:<a href=\"https://doi.org/10.1038/s41467-026-76877-7\">10.1038/s41467-026-76877-7</a>","apa":"Machnik, N. N., Mahmoudi, S. M., Borczyk, M., Krätschmer, I., Bauer, M. J., &#38; Robinson, M. R. (2026). Causal inference for multiple risk factors and diseases from genomics data. <i>Nature Communications</i>. Springer Nature. <a href=\"https://doi.org/10.1038/s41467-026-76877-7\">https://doi.org/10.1038/s41467-026-76877-7</a>","short":"N.N. Machnik, S.M. Mahmoudi, M. Borczyk, I. Krätschmer, M.J. Bauer, M.R. Robinson, Nature Communications 17 (2026).","chicago":"Machnik, Nick N, Seyed Mahdi Mahmoudi, Malgorzata Borczyk, Ilse Krätschmer, Markus J. Bauer, and Matthew Richard Robinson. “Causal Inference for Multiple Risk Factors and Diseases from Genomics Data.” <i>Nature Communications</i>. Springer Nature, 2026. <a href=\"https://doi.org/10.1038/s41467-026-76877-7\">https://doi.org/10.1038/s41467-026-76877-7</a>.","ista":"Machnik NN, Mahmoudi SM, Borczyk M, Krätschmer I, Bauer MJ, Robinson MR. 2026. Causal inference for multiple risk factors and diseases from genomics data. Nature Communications. 17, 10153.","mla":"Machnik, Nick N., et al. “Causal Inference for Multiple Risk Factors and Diseases from Genomics Data.” <i>Nature Communications</i>, vol. 17, 10153, Springer Nature, 2026, doi:<a href=\"https://doi.org/10.1038/s41467-026-76877-7\">10.1038/s41467-026-76877-7</a>."},"ddc":["570"],"supplementarymaterial":"no","file_date_updated":"2026-10-07T09:50:18Z","date_published":"2026-08-25T00:00:00Z","das_tickbox":"1","dataavailabilitystatement":"This project uses the UK Biobank data under project number 35520.\r\nUK Biobank genotypic and phenotypic data is available through a\r\nformal request at (http://www.ukbiobank.ac.uk). All of the data generated\r\nin this study are provided in the Source Data file. Source data\r\nare provided with this paper. The CI-GWAS code is fully open source and available at https://github.\r\ncom/medical-genomics-group/ci-gwasand has been archived on\r\nZenodo52. The scripts used to execute the model are available at\r\nhttps://github.com/medical-genomics-group/ci-gwas. R version 4.2.1 is\r\navailable at https://www.r-project.org/. Plink version 1.9 is available at\r\nhttps://www.cog-genomics.org/plink/1.9/.","corr_author":"1","day":"25","tmp":{"image":"/images/cc_by_nc_nd.png","short":"CC BY-NC-ND (4.0)","legal_code_url":"https://creativecommons.org/licenses/by-nc-nd/4.0/legalcode","name":"Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)"},"related_material":{"record":[{"status":"public","relation":"earlier_version","id":"18648"}]},"date_created":"2026-10-04T22:01:53Z","abstract":[{"text":"Mendelian randomization, the standard instrument variable causal-inference approach for genomics, can be severely biased by inadequate selection of appropriate instrument variables and horizontal pleiotropy. We introduce Causal Inference GWAS, a graphical approach that selects genetic instruments from summary statistics controlling for linkage and pleiotropy, accommodates rare variants and binary outcomes, distinguishes direct from indirect risk factors in high dimensions, and flags latent confounding. Applied to 9 risk factors, 4 metabolic disease outcomes, and 8.4M variants across 458,747 UK Biobank individuals, our method runs in 20 minutes, identifying only 696 genome-wide valid instruments. We replicate nearly all previously reported risk factor-outcome paths, but find that most are indistinguishable from unmeasured confounding. This suggests robust biobank causal inference will require longitudinal and family data to resolve temporal precedence from reverse causation. Our approach offers a principled first step toward screening genuine causal signal from phenotypic correlation in biobank data.","lang":"eng"}],"publication":"Nature Communications","acknowledgement":"We thank Zoltan Kutalik andmembers of the Robinson group at ISTA for\r\ntheir comments, which improved this manuscript. We would like to\r\nacknowledge the participants and investigators of the UK Biobank study.\r\nHigh-performance computing was supported by the Scientific Service\r\nUnits (SSU) of IST Austria through resources provided by Scientific\r\nComputing (SciComp). This work was funded by a research collaboration agreement between\r\nBoehringer Ingelheim and the research group of MRR at the Institute of\r\nScience and Technology Austria. Additional funding was also provided\r\nby an SNSF Eccellenza Grant to MRR (PCEGP3-181181), and by core\r\nfunding from the Institute of Science and Technology Austria. MB was\r\nfunded by the National Science Center Poland grant SONATINA UMO-\r\n2021/40/C/NZ2/00218.","status":"public","language":[{"iso":"eng"}]},{"publisher":"Cell Press","publication_identifier":{"eissn":["2666-979X"]},"year":"2026","fulldoi":"https://doi.org/10.1016/j.xgen.2026.101277","quality_controlled":"1","department":[{"_id":"MaRo"}],"acknowledged_ssus":[{"_id":"ScienComp"}],"month":"07","article_type":"original","OA_type":"gold","oa":1,"has_accepted_license":"1","pmid":1,"DOAJ_listed":"1","title":"Separating direct, indirect, and parent-of-origin genetic effects in the human population","_id":"21987","keyword":["direct genetic effects","DGE","indirect genetic effects","IGE","parent-of-origin effects","phenotypic variation","assortative mating","within-family GWAS","MoBa","EstBB"],"article_number":"101277","date_updated":"2026-10-20T09:03:50Z","oa_version":"Published Version","intvolume":"         6","researchdata_availability":"yes","doi":"10.1016/j.xgen.2026.101277","external_id":{"pmid":["40909755"]},"author":[{"first_name":"Ilse","full_name":"Krätschmer, Ilse","orcid":"0000-0002-5636-9259","last_name":"Krätschmer","id":"30d4014e-7753-11eb-b44b-db6d61112e73"},{"first_name":"Laura","full_name":"Hegemann, Laura","last_name":"Hegemann"},{"first_name":"Robin J.","full_name":"Hofmeister, Robin J.","last_name":"Hofmeister"},{"full_name":"Corfield, Elizabeth C.","first_name":"Elizabeth C.","last_name":"Corfield"},{"last_name":"Mahmoudi","first_name":"Mahdi","full_name":"Mahmoudi, Mahdi"},{"last_name":"Delaneau","first_name":"Olivier","full_name":"Delaneau, Olivier"},{"full_name":"Andreassen, Ole A.","first_name":"Ole A.","last_name":"Andreassen"},{"last_name":"Campbell","first_name":"Archie","full_name":"Campbell, Archie"},{"last_name":"Hayward","first_name":"Caroline","full_name":"Hayward, Caroline"},{"last_name":"Marioni","first_name":"Riccardo E.","full_name":"Marioni, Riccardo E."},{"first_name":"Eivind","full_name":"Ystrom, Eivind","last_name":"Ystrom"},{"first_name":"Alexandra","full_name":"Havdahl, Alexandra","last_name":"Havdahl"},{"last_name":"Robinson","orcid":"0000-0001-8982-8813","full_name":"Robinson, Matthew Richard","first_name":"Matthew Richard","id":"E5D42276-F5DA-11E9-8E24-6303E6697425"}],"type":"journal_article","file":[{"date_updated":"2026-07-28T07:24:50Z","content_type":"application/pdf","file_size":3679297,"success":1,"checksum":"f896b510480d2d4e4a7fd46c2e2761f4","file_name":"2026_CellGenomics_Kraetschmer.pdf","date_created":"2026-07-28T07:24:50Z","relation":"main_file","creator":"dernst","file_id":"22597","access_level":"open_access"}],"scopus_import":"1","publication_status":"published","issue":"7","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","project":[{"_id":"9B8D11D6-BA93-11EA-9121-9846C619BF3A","grant_number":"PCEGP3_181181","name":"Improving estimation and prediction of common complex disease risk"}],"OA_place":"publisher","volume":6,"article_processing_charge":"Yes","supplementarymaterial":"yes","citation":{"ista":"Krätschmer I, Hegemann L, Hofmeister RJ, Corfield EC, Mahmoudi M, Delaneau O, Andreassen OA, Campbell A, Hayward C, Marioni RE, Ystrom E, Havdahl A, Robinson MR. 2026. Separating direct, indirect, and parent-of-origin genetic effects in the human population. Cell Genomics. 6(7), 101277.","mla":"Krätschmer, Ilse, et al. “Separating Direct, Indirect, and Parent-of-Origin Genetic Effects in the Human Population.” <i>Cell Genomics</i>, vol. 6, no. 7, 101277, Cell Press, 2026, doi:<a href=\"https://doi.org/10.1016/j.xgen.2026.101277\">10.1016/j.xgen.2026.101277</a>.","apa":"Krätschmer, I., Hegemann, L., Hofmeister, R. J., Corfield, E. C., Mahmoudi, M., Delaneau, O., … Robinson, M. R. (2026). Separating direct, indirect, and parent-of-origin genetic effects in the human population. <i>Cell Genomics</i>. Cell Press. <a href=\"https://doi.org/10.1016/j.xgen.2026.101277\">https://doi.org/10.1016/j.xgen.2026.101277</a>","ama":"Krätschmer I, Hegemann L, Hofmeister RJ, et al. Separating direct, indirect, and parent-of-origin genetic effects in the human population. <i>Cell Genomics</i>. 2026;6(7). doi:<a href=\"https://doi.org/10.1016/j.xgen.2026.101277\">10.1016/j.xgen.2026.101277</a>","ieee":"I. Krätschmer <i>et al.</i>, “Separating direct, indirect, and parent-of-origin genetic effects in the human population,” <i>Cell Genomics</i>, vol. 6, no. 7. Cell Press, 2026.","chicago":"Krätschmer, Ilse, Laura Hegemann, Robin J. Hofmeister, Elizabeth C. Corfield, Mahdi Mahmoudi, Olivier Delaneau, Ole A. Andreassen, et al. “Separating Direct, Indirect, and Parent-of-Origin Genetic Effects in the Human Population.” <i>Cell Genomics</i>. Cell Press, 2026. <a href=\"https://doi.org/10.1016/j.xgen.2026.101277\">https://doi.org/10.1016/j.xgen.2026.101277</a>.","short":"I. Krätschmer, L. Hegemann, R.J. Hofmeister, E.C. Corfield, M. Mahmoudi, O. Delaneau, O.A. Andreassen, A. Campbell, C. Hayward, R.E. Marioni, E. Ystrom, A. Havdahl, M.R. Robinson, Cell Genomics 6 (2026)."},"ddc":["570"],"file_date_updated":"2026-07-28T07:24:50Z","das_tickbox":"1","dataavailabilitystatement":"Information on how to access the MoBaPsychGen post-imputation QC data are available here: https://www.fhi.no/en/me/the-psychgen-centre-for-genetic-epidemiology-and-mental-health/access-to-genetic-data-after-quality-control-by-the-mobapsychgen-pipeline-v/.\r\nEstonian Biobank data (https://genomics.ut.ee/en/content/estonian-biobank) were used in this project. For access to be granted to the Estonian Biobank genotypic and corresponding phenotypic data, a preliminary application must be presented to the oversight committee, who must first approve the project. Ethics permission must then be obtained from the Estonian Committee on Bioethics and Human Research. Finally, a full project must be submitted and approved by the Estonian Biobank.\r\nAccess to the Generation Scotland data is available with appropriate permission from the Generation Scotland Access Committee. Applications should be made to access@generationscotland.org (https://genscot.ed.ac.uk/).\r\nThe code for JODIE developed in this work is open source and is publicly available on zenodo (https://doi.org/10.5281/zenodo.19593928) and GitHub (https://github.com/medical-genomics-group/JODIE).\r\nHaplotype Reference Consortium Release 1.1 data (https://ega-archive.org/datasets/EGAD00001002729) are available by application to a Data Access Committee (DAC) of the Wellcome Trust Sanger Institute.\r\nThe Common Metabolic Diseases Atlas can be accessed here: https://cmdga.org.","date_published":"2026-07-08T00:00:00Z","corr_author":"1","day":"08","tmp":{"image":"/images/cc_by_nc_nd.png","short":"CC BY-NC-ND (4.0)","legal_code_url":"https://creativecommons.org/licenses/by-nc-nd/4.0/legalcode","name":"Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)"},"related_material":{"link":[{"url":"https://ista.ac.at/en/news/human-traits-beyond-inherited-genes/","relation":"press_release","description":"News on ISTA website"}]},"date_created":"2026-06-10T07:39:08Z","abstract":[{"lang":"eng","text":"We introduce JODIE, a genetic joint modeling approach that estimates how DNA loci influence human traits by partitioning genetic effects into four components: direct effects (from a child’s alleles), indirect maternal and paternal effects (from parents’ alleles), and parent-of-origin (PofO) effects (dependent on parental transmission of alleles), while uniquely accounting for assortative mating. We analyze 30,000 child-mother-father trios from the Estonian Biobank and the Norwegian Mother, Father, and Child Cohort, focusing on height, body mass index, and childhood educational test scores. We find direct effects to be the largest contributor to trait variation, but combined, indirect parental and PofO effects are similarly substantial. We support our results by within-family genome-wide association testing and identify 276 independently associated DNA regions with a complex interplay between direct, indirect, and PofO effects. By joint modeling, we show that direct, indirect, and PofO effects collectively shape human phenotypic variation across loci genome-wide."}],"publication":"Cell Genomics","language":[{"iso":"eng"}],"status":"public","acknowledgement":"We thank Zoltan Kutalik, Peter Visscher, and members of the Robinson group at ISTA for their comments, which improved this manuscript. This work was funded by an SNSF Eccellenza Grant to M.R.R. (PCEGP3-181181) and by core funding from the Institute of Science and Technology Austria.\r\nThe Norwegian Mother, Father, and Child Cohort Study is supported by the Norwegian Ministry of Health and Care Services and the Ministry of Education and Research. We are grateful to all the participating families in Norway who take part in this on-going cohort study. We thank the Norwegian Institute of Public Health (NIPH) for generating high-quality genomic data. The research is part of the HARVEST collaboration, supported by the Research Council of Norway (#229624). We also thank the NORMENT Center for providing genotype data, funded by the Research Council of Norway (#223273), South East Norway Health Authorities, and Stiftelsen Kristian Gerhard Jebsen, and in collaboration with deCODE Genetics. We further thank the Center for Diabetes Research, the University of Bergen for providing genotype data funded by the ERC AdG project SELECTionPREDISPOSED, Stiftelsen Kristian Gerhard Jebsen, Trond Mohn Foundation, the Research Council of Norway, the Novo Nordisk Foundation, the University of Bergen, and the Western Norway Health Authorities. The MoBa work was performed on the TSD (Tjeneste for Sensitive Data) facilities, owned by the University of Oslo, operated and developed by the TSD service group at the University of Oslo, IT Department (USIT, tsd-drift@usit.uio.no). E.Y. is supported by the European Union (grant numbers 101045526 and 101073237) and the Research Council of Norway (grant numbers 336078, 288083, and 331640).\r\nWe would like to acknowledge the participants and investigators of the Generation Scotland Cohort study. 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). Genotyping and methylation typing of the GS:SFHS samples was carried out by the Genetics Core Laboratory at the Wellcome Trust Clinical Research Facility, 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] ref. 104036/Z/14/Z).\r\nWe would like to thank and acknowledge the participants and investigators of the Estonian Biobank (EstBB) study. The research was conducted using the Estonian Center of Genomics/Roadmap II funded by the Estonian Research Council (project number TT17).\r\nNorwegian analyses were performed on resources provided by Sigma2 - the National Infrastructure for High-Performance Computing and Data Storage in Norway. Estonian Data analysis was carried out in the High-Performance Computing Center cloud provided by University of Tartu. Analysis of the Generation Scotland data and the summary statistics obtained from the other analyses was conducted at IST Austria and is supported by the Scientific Service Units (SSU) of IST Austria through resources provided by Scientific Computing (SciComp)."},{"supervisor":[{"last_name":"Robinson","orcid":"0000-0001-8982-8813","full_name":"Robinson, Matthew Richard","first_name":"Matthew Richard","id":"E5D42276-F5DA-11E9-8E24-6303E6697425"},{"id":"27EB676C-8706-11E9-9510-7717E6697425","full_name":"Mondelli, Marco","first_name":"Marco","last_name":"Mondelli","orcid":"0000-0002-3242-7020"}],"language":[{"iso":"eng"}],"acknowledgement":"This work was supported in part by the Swiss National Science Foundation through the\r\nEccellenza Grant \"Improving estimation and prediction of common complex disease risk\"\r\n(grant number PCEGP3_181181); the European Research Council through the grant\r\n\"Inference in High Dimensions: Light-speed Algorithms and Information Limits\" (grant\r\nnumber 101161364); and the Fondation Jean-Jacques et Felicia Lopez-Loreta through the\r\nPrix Lopez-Loretta 2019.\r\n","status":"public","abstract":[{"text":"Uncovering the genetic architecture of complex traits and pinpointing causal molecular drivers require the ability to distinguish true signals from noise within massive, high-dimensional omics datasets. To extract meaningful biological insights from these datasets, such as identifying causal genetic variants and proteins, scalable and accurate inference methods are essential. To this end, this thesis develops novel Bayesian inference frameworks based on Vector Approximate Message Passing and demonstrates their effectiveness in the modeling of disease onset times and quantitative physical and clinical measures.\r\n\r\nFirst, we introduce gVAMP, a Bayesian framework tailored for Genome-Wide Association Studies that enables the joint modeling of quantitative complex traits across millions of genetic variants. gVAMP demonstrates superior accuracy in variable selection and out-of-sample polygenic risk prediction compared to state-of-the-art approaches. We model human height using 17 million whole-genome sequence variants from the UK Biobank, incorporating a vast number of rare variants and revealing novel associations. gVAMP achieves a prediction accuracy of approximately 46% for human height, representing the highest reported performance for this trait to date. \r\n\r\nSecond, we present vampW, a Bayesian framework for survival analysis applied to proteomic data. By effectively handling right-censoring and complex protein dependencies within the UK Biobank Pharma Proteomics Project dataset, vampW identifies 219 protein associations across 24 disease outcomes, the majority of which are not among the top marginal discoveries. We further adjust protein levels for exponential age effects, yielding 1,308 associations and highlighting the sensitivity of the analysis to the chosen age-correction methodology. Finally, vampW improves upon the variable selection capabilities of the commonly used (penalized) variants of the Cox proportional hazards model and delivers state-of-the-art out-of-sample prediction of disease onset times.\r\n\r\nCollectively, these methods provide powerful tools for dissecting the genetic architecture of complex traits and the proteomic drivers of disease onset. Furthermore, by delivering accurate polygenic risk scores and precise predictions of onset times, this work advances the capabilities of personalized medicine and clinical risk stratification.","lang":"eng"}],"date_created":"2026-07-10T13:27:20Z","related_material":{"record":[{"relation":"part_of_dissertation","status":"public","id":"21488"}]},"corr_author":"1","day":"11","das_tickbox":"1","date_published":"2026-07-11T00:00:00Z","page":"169","file_date_updated":"2026-07-13T14:56:41Z","article_processing_charge":"No","citation":{"ieee":"A. Depope, “From sparse selection to risk prediction: Approximate message passing for proteomic survival models and large-scale genomics,” Institute of Science and Technology Austria, 2026.","ama":"Depope A. From sparse selection to risk prediction: Approximate message passing for proteomic survival models and large-scale genomics. 2026. doi:<a href=\"https://doi.org/10.15479/AT-ISTA-22258\">10.15479/AT-ISTA-22258</a>","apa":"Depope, A. (2026). <i>From sparse selection to risk prediction: Approximate message passing for proteomic survival models and large-scale genomics</i>. Institute of Science and Technology Austria. <a href=\"https://doi.org/10.15479/AT-ISTA-22258\">https://doi.org/10.15479/AT-ISTA-22258</a>","chicago":"Depope, Al. “From Sparse Selection to Risk Prediction: Approximate Message Passing for Proteomic Survival Models and Large-Scale Genomics.” Institute of Science and Technology Austria, 2026. <a href=\"https://doi.org/10.15479/AT-ISTA-22258\">https://doi.org/10.15479/AT-ISTA-22258</a>.","short":"A. Depope, From Sparse Selection to Risk Prediction: Approximate Message Passing for Proteomic Survival Models and Large-Scale Genomics, Institute of Science and Technology Austria, 2026.","ista":"Depope A. 2026. From sparse selection to risk prediction: Approximate message passing for proteomic survival models and large-scale genomics. Institute of Science and Technology Austria.","mla":"Depope, Al. <i>From Sparse Selection to Risk Prediction: Approximate Message Passing for Proteomic Survival Models and Large-Scale Genomics</i>. Institute of Science and Technology Austria, 2026, doi:<a href=\"https://doi.org/10.15479/AT-ISTA-22258\">10.15479/AT-ISTA-22258</a>."},"ddc":["576","610","006"],"degree_awarded":"PhD","OA_place":"publisher","user_id":"8b945eb4-e2f2-11eb-945a-df72226e66a9","project":[{"name":"Prix Lopez-Loretta 2019 - Marco Mondelli","_id":"059876FA-7A3F-11EA-A408-12923DDC885E"},{"_id":"911e6d1f-16d5-11f0-9cad-c5c68c6a1cdf","name":"Inference in High Dimensions: Light-speed Algorithms and Information Limits","grant_number":"101161364"},{"grant_number":"PCEGP3_181181","name":"Improving estimation and prediction of common complex disease risk","_id":"9B8D11D6-BA93-11EA-9121-9846C619BF3A"}],"publication_status":"published","type":"dissertation","file":[{"access_level":"open_access","file_id":"22316","relation":"main_file","creator":"adepope","file_name":"2026_Depope_Al_Thesis.pdf","date_created":"2026-07-13T14:52:19Z","checksum":"9ab386790515628d957a194f30a7ccb4","file_size":25109878,"date_updated":"2026-07-13T14:52:19Z","content_type":"application/pdf"},{"file_size":1203199939,"date_updated":"2026-07-13T14:56:41Z","content_type":"application/zip","date_created":"2026-07-13T14:56:41Z","file_name":"2026_Depope_Al_Thesis.zip","checksum":"8ed8fb63f76a695d5b6fec35343f4b90","relation":"source_file","creator":"adepope","access_level":"closed","file_id":"22317"}],"author":[{"full_name":"Depope, Al","first_name":"Al","last_name":"Depope","id":"0b77531d-dbcd-11ea-9d1d-a8eee0bf3830"}],"doi_confirm":"1","doi":"10.15479/AT-ISTA-22258","oa_version":"Published Version","date_updated":"2026-10-20T09:03:21Z","_id":"22258","keyword":["Approximate Message Passing","GWAS","Genomics","Proteomics","Survival modeling"],"title":"From sparse selection to risk prediction: Approximate message passing for proteomic survival models and large-scale genomics","oa":1,"has_accepted_license":"1","acknowledged_ssus":[{"_id":"ScienComp"}],"month":"07","alternative_title":["ISTA Thesis"],"department":[{"_id":"GradSch"},{"_id":"MaRo"},{"_id":"MaMo"}],"fulldoi":"https://doi.org/10.15479/AT-ISTA-22258","publisher":"Institute of Science and Technology Austria","year":"2026","publication_identifier":{"issn":["2663-337X"]}},{"citation":{"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. 6(5), 101162.","mla":"Depope, Al, et al. “Joint Modeling of Whole-Genome Sequencing Data for Human Height via Approximate Message Passing.” <i>Cell Genomics</i>, vol. 6, no. 5, 101162, Cell Press, 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>, vol. 6, no. 5. Cell Press, 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>. Cell Press. <a href=\"https://doi.org/10.1016/j.xgen.2026.101162\">https://doi.org/10.1016/j.xgen.2026.101162</a>","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;6(5). doi:<a href=\"https://doi.org/10.1016/j.xgen.2026.101162\">10.1016/j.xgen.2026.101162</a>","short":"A. Depope, J. Bajzik, M. Mondelli, M.R. Robinson, Cell Genomics 6 (2026).","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>. Cell Press, 2026. <a href=\"https://doi.org/10.1016/j.xgen.2026.101162\">https://doi.org/10.1016/j.xgen.2026.101162</a>."},"supplementarymaterial":"yes","ddc":["000","570"],"article_processing_charge":"Yes","OA_place":"publisher","volume":6,"project":[{"_id":"059876FA-7A3F-11EA-A408-12923DDC885E","name":"Prix Lopez-Loretta 2019 - Marco Mondelli"},{"grant_number":"101161364","name":"Inference in High Dimensions: Light-speed Algorithms and Information Limits","_id":"911e6d1f-16d5-11f0-9cad-c5c68c6a1cdf"},{"_id":"9B8D11D6-BA93-11EA-9121-9846C619BF3A","name":"Improving estimation and prediction of common complex disease risk","grant_number":"PCEGP3_181181"}],"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","issue":"5","publication_status":"published","scopus_import":"1","file":[{"checksum":"6b59686f8d9733add4f23d23f3dd9df0","date_created":"2026-07-28T07:06:26Z","file_name":"2026_CellGenomics_Depope.pdf","date_updated":"2026-07-28T07:06:26Z","content_type":"application/pdf","file_size":3736705,"success":1,"file_id":"22596","access_level":"open_access","relation":"main_file","creator":"dernst"}],"type":"journal_article","author":[{"id":"0b77531d-dbcd-11ea-9d1d-a8eee0bf3830","last_name":"Depope","first_name":"Al","full_name":"Depope, Al"},{"first_name":"Jakub","full_name":"Bajzik, Jakub","last_name":"Bajzik","id":"b995e25b-8c4b-11ed-a6d8-f71b7bcd6122"},{"orcid":"0000-0002-3242-7020","last_name":"Mondelli","first_name":"Marco","full_name":"Mondelli, Marco","id":"27EB676C-8706-11E9-9510-7717E6697425"},{"id":"E5D42276-F5DA-11E9-8E24-6303E6697425","full_name":"Robinson, Matthew Richard","first_name":"Matthew Richard","last_name":"Robinson","orcid":"0000-0001-8982-8813"}],"external_id":{"pmid":["41713425"]},"doi":"10.1016/j.xgen.2026.101162","researchdata_availability":"yes","intvolume":"         6","oa_version":"Published Version","status":"public","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"}],"publication":"Cell Genomics","abstract":[{"lang":"eng","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."}],"date_created":"2026-03-23T15:10:03Z","tmp":{"image":"/images/cc_by_nc_nd.png","short":"CC BY-NC-ND (4.0)","legal_code_url":"https://creativecommons.org/licenses/by-nc-nd/4.0/legalcode","name":"Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)"},"related_material":{"record":[{"status":"public","relation":"dissertation_contains","id":"22258"}],"link":[{"url":"https://ista.ac.at/en/news/big-data-and-human-height/","relation":"press_release","description":"News on ISTA website"}]},"day":"13","corr_author":"1","date_published":"2026-05-13T00:00:00Z","das_tickbox":"1","dataavailabilitystatement":"This project uses the UK Biobank data under project number 35520. UK Biobank genotypic and phenotypic data are available through a formal request at http://www.ukbiobank.ac.uk. It also uses genotypic and phenotypic data from the All of Us study, which are also available through a formal request at https://www.researchallofus.org/data-tools/data-access/. All summary statistic estimates are released publicly on Dryad: https://doi.org/10.5061/dryad.cz8w9gjjc.\r\n•\r\nThe gVAMP code developed in this work is open source and has been deposited on GitHub, where it is publicly available at https://github.com/medical-genomics-group/gVAMP, and the code used to generate the data in the manuscript are available from Zenodo https://doi.org/10.5281/zenodo.17935521. The URLs of other software used are listed in the key resources table.","file_date_updated":"2026-07-28T07:06:26Z","department":[{"_id":"MaMo"},{"_id":"MaRo"}],"quality_controlled":"1","fulldoi":"https://doi.org/10.1016/j.xgen.2026.101162","publication_identifier":{"eissn":["2666-979X"]},"year":"2026","publisher":"Cell Press","date_updated":"2026-10-20T09:03:22Z","article_number":"101162","_id":"21488","title":"Joint modeling of whole-genome sequencing data for human height via approximate message passing","DOAJ_listed":"1","pmid":1,"has_accepted_license":"1","oa":1,"OA_type":"gold","month":"05","article_type":"original"},{"quality_controlled":"1","department":[{"_id":"MaRo"}],"publisher":"Springer Nature","year":"2025","publication_identifier":{"eissn":["1868-7083"],"issn":["1868-7075"]},"fulldoi":"https://doi.org/10.1186/s13148-025-01818-y","article_number":"14","date_updated":"2025-09-30T10:31:08Z","_id":"19023","DOAJ_listed":"1","title":"Blood-based epigenome-wide association study and prediction of alcohol consumption","isi":1,"month":"01","article_type":"original","OA_type":"gold","oa":1,"has_accepted_license":"1","pmid":1,"volume":17,"OA_place":"publisher","article_processing_charge":"Yes","citation":{"short":"E. Bernabeu, A.D. Chybowska, J.K. Kresovich, M. Suderman, D.L. Mccartney, R.F. Hillary, J. Corley, M.D.C. Valdés-Hernández, S.M. Maniega, M.E. Bastin, J.M. Wardlaw, Z. Xu, D.P. Sandler, A. Campbell, S.E. Harris, A.M. Mcintosh, J.A. Taylor, P. Yousefi, S.R. Cox, K.L. Evans, M.R. Robinson, C.A. Vallejos, R.E. Marioni, Clinical Epigenetics 17 (2025).","chicago":"Bernabeu, Elena, Aleksandra D. Chybowska, Jacob K. Kresovich, Matthew Suderman, Daniel L. Mccartney, Robert F. Hillary, Janie Corley, et al. “Blood-Based Epigenome-Wide Association Study and Prediction of Alcohol Consumption.” <i>Clinical Epigenetics</i>. Springer Nature, 2025. <a href=\"https://doi.org/10.1186/s13148-025-01818-y\">https://doi.org/10.1186/s13148-025-01818-y</a>.","ieee":"E. Bernabeu <i>et al.</i>, “Blood-based epigenome-wide association study and prediction of alcohol consumption,” <i>Clinical Epigenetics</i>, vol. 17. Springer Nature, 2025.","apa":"Bernabeu, E., Chybowska, A. D., Kresovich, J. K., Suderman, M., Mccartney, D. L., Hillary, R. F., … Marioni, R. E. (2025). Blood-based epigenome-wide association study and prediction of alcohol consumption. <i>Clinical Epigenetics</i>. Springer Nature. <a href=\"https://doi.org/10.1186/s13148-025-01818-y\">https://doi.org/10.1186/s13148-025-01818-y</a>","ama":"Bernabeu E, Chybowska AD, Kresovich JK, et al. Blood-based epigenome-wide association study and prediction of alcohol consumption. <i>Clinical Epigenetics</i>. 2025;17. doi:<a href=\"https://doi.org/10.1186/s13148-025-01818-y\">10.1186/s13148-025-01818-y</a>","mla":"Bernabeu, Elena, et al. “Blood-Based Epigenome-Wide Association Study and Prediction of Alcohol Consumption.” <i>Clinical Epigenetics</i>, vol. 17, 14, Springer Nature, 2025, doi:<a href=\"https://doi.org/10.1186/s13148-025-01818-y\">10.1186/s13148-025-01818-y</a>.","ista":"Bernabeu E, Chybowska AD, Kresovich JK, Suderman M, Mccartney DL, Hillary RF, Corley J, Valdés-Hernández MDC, Maniega SM, Bastin ME, Wardlaw JM, Xu Z, Sandler DP, Campbell A, Harris SE, Mcintosh AM, Taylor JA, Yousefi P, Cox SR, Evans KL, Robinson MR, Vallejos CA, Marioni RE. 2025. Blood-based epigenome-wide association study and prediction of alcohol consumption. Clinical Epigenetics. 17, 14."},"ddc":["570"],"publication_status":"published","user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","project":[{"grant_number":"PCEGP3_181181","name":"Improving estimation and prediction of common complex disease risk","_id":"9B8D11D6-BA93-11EA-9121-9846C619BF3A"}],"external_id":{"isi":["001406495600001"],"pmid":["39863868"]},"author":[{"full_name":"Bernabeu, Elena","first_name":"Elena","last_name":"Bernabeu"},{"last_name":"Chybowska","first_name":"Aleksandra D.","full_name":"Chybowska, Aleksandra D."},{"first_name":"Jacob K.","full_name":"Kresovich, Jacob K.","last_name":"Kresovich"},{"last_name":"Suderman","first_name":"Matthew","full_name":"Suderman, Matthew"},{"last_name":"Mccartney","first_name":"Daniel L.","full_name":"Mccartney, Daniel L."},{"first_name":"Robert F.","full_name":"Hillary, Robert F.","last_name":"Hillary"},{"full_name":"Corley, Janie","first_name":"Janie","last_name":"Corley"},{"last_name":"Valdés-Hernández","full_name":"Valdés-Hernández, Maria Del C.","first_name":"Maria Del C."},{"last_name":"Maniega","full_name":"Maniega, Susana Muñoz","first_name":"Susana Muñoz"},{"first_name":"Mark E.","full_name":"Bastin, Mark E.","last_name":"Bastin"},{"last_name":"Wardlaw","first_name":"Joanna M.","full_name":"Wardlaw, Joanna M."},{"full_name":"Xu, Zongli","first_name":"Zongli","last_name":"Xu"},{"last_name":"Sandler","first_name":"Dale P.","full_name":"Sandler, Dale P."},{"full_name":"Campbell, Archie","first_name":"Archie","last_name":"Campbell"},{"last_name":"Harris","first_name":"Sarah E.","full_name":"Harris, Sarah E."},{"last_name":"Mcintosh","first_name":"Andrew M.","full_name":"Mcintosh, Andrew M."},{"last_name":"Taylor","first_name":"Jack A.","full_name":"Taylor, Jack A."},{"full_name":"Yousefi, Paul","first_name":"Paul","last_name":"Yousefi"},{"full_name":"Cox, Simon R.","first_name":"Simon R.","last_name":"Cox"},{"first_name":"Kathryn L.","full_name":"Evans, Kathryn L.","last_name":"Evans"},{"id":"E5D42276-F5DA-11E9-8E24-6303E6697425","last_name":"Robinson","orcid":"0000-0001-8982-8813","full_name":"Robinson, Matthew Richard","first_name":"Matthew Richard"},{"last_name":"Vallejos","full_name":"Vallejos, Catalina A.","first_name":"Catalina A."},{"last_name":"Marioni","full_name":"Marioni, Riccardo E.","first_name":"Riccardo E."}],"type":"journal_article","scopus_import":"1","file":[{"file_size":1170930,"success":1,"date_updated":"2025-02-17T08:44:23Z","content_type":"application/pdf","file_name":"2025_ClinicalEpigenetics_Bernabeu.pdf","date_created":"2025-02-17T08:44:23Z","checksum":"c32511f2d09e6c164116793e784944b8","creator":"dernst","relation":"main_file","access_level":"open_access","file_id":"19030"}],"oa_version":"Published Version","intvolume":"        17","doi":"10.1186/s13148-025-01818-y","abstract":[{"text":"Alcohol consumption is an important risk factor for multiple diseases. It is typically assessed via self-report, which is open to measurement error through recall bias. Instead, molecular data such as blood-based DNA methylation (DNAm) could be used to derive a more objective measure of alcohol consumption by incorporating information from cytosine-phosphate-guanine (CpG) sites known to be linked to the trait. Here, we explore the epigenetic architecture of self-reported weekly units of alcohol consumption in the Generation Scotland study. We first create a blood-based epigenetic score (EpiScore) of alcohol consumption using elastic net penalized linear regression. We explore the effect of pre-filtering for CpG features ahead of elastic net, as well as differential patterns by sex and by units consumed in the last week relative to an average week. The final EpiScore was trained on 16,717 individuals and tested in four external cohorts: the Lothian Birth Cohorts (LBC) of 1921 and 1936, the Sister Study, and the Avon Longitudinal Study of Parents and Children (total N across studies > 10,000). The maximum Pearson correlation between the EpiScore and self-reported alcohol consumption within cohort ranged from 0.41 to 0.53. In LBC1936, higher EpiScore levels had significant associations with poorer global brain imaging metrics, whereas self-reported alcohol consumption did not. Finally, we identified two novel CpG loci via a Bayesian penalized regression epigenome-wide association study of alcohol consumption. Together, these findings show how DNAm can objectively characterize patterns of alcohol consumption that associate with brain health, unlike self-reported estimates.","lang":"eng"}],"publication":"Clinical Epigenetics","language":[{"iso":"eng"}],"status":"public","acknowledgement":"Generation Scotland: 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). Genotyping and DNA methylation profiling of the Generation Scotland samples were carried out by the Genetics Core Laboratory at the Edinburgh Clinical Research Facility, Edinburgh, Scotland, and were 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) and 220857/Z/20/Z. The DNA methylation data assayed for Generation Scotland were partially funded by a 2018 NARSAD Young Investigator Grant from the Brain & Behavior Research Foundation (Ref: 27404; awardee: Dr David M Howard) and by a JMAS SIM fellowship from the Royal College of Physicians of Edinburgh (Awardee: Dr Heather C Whalley). Lothian Birth Cohorts: We thank the LBC1921 and LBC1936 participants and team members who contributed to these studies. The LBC1921 was supported by the UK’s Biotechnology and Biological Sciences Research Council (BBSRC), The Royal Society, and The Chief Scientist Office of the Scottish Government. The LBC1936 is supported by the BBSRC, and the Economic and Social Research Council [BB/W008793/1] (which supports S.E.H.), Age UK (Disconnected Mind project), the Milton Damerel Trust, the Medical Research Council (MR/M01311/1), and the University of Edinburgh. Methylation typing of LBC1936 was supported by the Centre for Cognitive Ageing and Cognitive Epidemiology (Pilot Fund award), Age UK, The Wellcome Trust Institutional Strategic Support Fund, The University of Edinburgh, and The University of Queensland. Genotyping was funded by the BBSRC (BB/F019394/1). S.R.C. is supported by a Sir Henry Dale Fellowship jointly funded by the Wellcome Trust and the Royal Society (Grant Number 221890/Z/20/Z). ALSPAC: The UK Medical Research Council and Wellcome (Grant ref: 217065/Z/19/Z) and the University of Bristol provide core support for ALSPAC. This publication is the work of the authors and Matthew Suderman will serve as guarantors for the contents of this paper. A comprehensive list of grants funding is available on the ALSPAC website (http://www.bristol.ac.uk/alspac/external/documents/grant-acknowledgements.pdf). Funding for ALSPAC DNAm measurements was supported by the Wellcome (102215/2/13/2); the University of Bristol; the UK Economic and Social Research Council (ES/N000498/1); the UK Medical Research Council (MC_UU_12013/1, MC_UU_12013/2); and the John Templeton Foundation (60828). MS and PY work within the MRC Integrative Epidemiology Unit at the University of Bristol, which is supported by the Medical Research Council (MC_UU_00011/5). Sister Study: This research was supported by the Intramural Research Program of the National Institutes of Health (Z01-ES049033, Z01-ES049032, Z01-ES044005). A.D.C. 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. R.F.H is supported by an MRC IEU Fellowship. M.R.R. was funded by Swiss National Science Foundation Eccellenza Grant PCEGP3-181181 and by core funding from the Institute of Science and Technology Austria. E.B. and R.E.M. are supported by Alzheimer’s Society major project grant AS-PG-19b-010. This research was funded in whole, or in part, by the Wellcome Trust (104036/Z/14/Z, 220857/Z/20/Z, and 221890/Z/20/Z). For the purpose of open access, the author has applied a CC BY public copyright licence to any Author Accepted Manuscript version arising from this submission.","date_created":"2025-02-16T23:02:33Z","day":"25","tmp":{"legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","short":"CC BY (4.0)","image":"/images/cc_by.png","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)"},"file_date_updated":"2025-02-17T08:44:23Z","date_published":"2025-01-25T00:00:00Z"},{"acknowledgement":"We thank P. Baduel and V. Colot for sharing SV data, A. Muyle for gbM conservation data and X. Feng, C. Dean, E. Coen and Zilberman lab members for constructive comments on the paper. This work was supported by a European Research Council grant (725746) to D.Z., LUMS Startup grant (STG-188) to Z.S. and US National Science Foundation grant (MCB-2334561) to H.R. This study would not have been possible without Arabidopsis 1001 genome, methylome and transcriptome resources. Open access funding provided by Institute of Science and Technology (IST Austria).","language":[{"iso":"eng"}],"status":"public","abstract":[{"lang":"eng","text":"Genetic variation is generally regarded as a prerequisite for evolution. In principle, epigenetic information inherited independently of DNA sequence can also enable evolution, but whether this occurs in natural populations is unknown. Here we show that single-nucleotide and epigenetic gene body DNA methylation (gbM) polymorphisms explain comparable amounts of expression variance in <jats:italic>Arabidopsis thaliana</jats:italic> populations. We genetically demonstrate that gbM regulates transcription, and we identify and genetically validate many associations between gbM polymorphism and the variation of complex traits: fitness under heat and drought, flowering time and accumulation of diverse minerals. Epigenome-wide association studies pinpoint trait-relevant genes with greater precision than genetic association analyses, probably due to reduced linkage disequilibrium between gbM variants. Finally, we identify numerous associations between gbM epialleles and diverse environmental conditions in native habitats, suggesting that gbM facilitates adaptation. Overall, our results indicate that epigenetic methylation variation fundamentally shapes phenotypic diversity in a natural population."}],"publication":"Nature Plants","date_created":"2025-10-16T13:11:21Z","tmp":{"legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","short":"CC BY (4.0)","image":"/images/cc_by.png","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)"},"corr_author":"1","day":"12","date_published":"2025-09-12T00:00:00Z","file_date_updated":"2025-10-23T11:13:58Z","page":"2084-2099","article_processing_charge":"Yes (via OA deal)","citation":{"ista":"Shahzad Z, Hollwey E, Moore JD, Choi J, Cassin-Ross G, Rouached H, Robinson MR, Zilberman D. 2025. Gene body methylation regulates gene expression and mediates phenotypic diversity in natural Arabidopsis populations. Nature Plants. 11, 2084–2099.","mla":"Shahzad, Zaigham, et al. “Gene Body Methylation Regulates Gene Expression and Mediates Phenotypic Diversity in Natural Arabidopsis Populations.” <i>Nature Plants</i>, vol. 11, Springer Nature, 2025, pp. 2084–99, doi:<a href=\"https://doi.org/10.1038/s41477-025-02108-4\">10.1038/s41477-025-02108-4</a>.","ama":"Shahzad Z, Hollwey E, Moore JD, et al. Gene body methylation regulates gene expression and mediates phenotypic diversity in natural Arabidopsis populations. <i>Nature Plants</i>. 2025;11:2084-2099. doi:<a href=\"https://doi.org/10.1038/s41477-025-02108-4\">10.1038/s41477-025-02108-4</a>","apa":"Shahzad, Z., Hollwey, E., Moore, J. D., Choi, J., Cassin-Ross, G., Rouached, H., … Zilberman, D. (2025). Gene body methylation regulates gene expression and mediates phenotypic diversity in natural Arabidopsis populations. <i>Nature Plants</i>. Springer Nature. <a href=\"https://doi.org/10.1038/s41477-025-02108-4\">https://doi.org/10.1038/s41477-025-02108-4</a>","ieee":"Z. Shahzad <i>et al.</i>, “Gene body methylation regulates gene expression and mediates phenotypic diversity in natural Arabidopsis populations,” <i>Nature Plants</i>, vol. 11. Springer Nature, pp. 2084–2099, 2025.","chicago":"Shahzad, Zaigham, Elizabeth Hollwey, Jonathan D. Moore, Jaemyung Choi, Gaëlle Cassin-Ross, Hatem Rouached, Matthew Richard Robinson, and Daniel Zilberman. “Gene Body Methylation Regulates Gene Expression and Mediates Phenotypic Diversity in Natural Arabidopsis Populations.” <i>Nature Plants</i>. Springer Nature, 2025. <a href=\"https://doi.org/10.1038/s41477-025-02108-4\">https://doi.org/10.1038/s41477-025-02108-4</a>.","short":"Z. Shahzad, E. Hollwey, J.D. Moore, J. Choi, G. Cassin-Ross, H. Rouached, M.R. Robinson, D. Zilberman, Nature Plants 11 (2025) 2084–2099."},"ddc":["580"],"OA_place":"publisher","volume":11,"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","project":[{"name":"Quantitative analysis of DNA methylation maintenance with chromatin","grant_number":"725746","call_identifier":"H2020","_id":"62935a00-2b32-11ec-9570-eff30fa39068"}],"publication_status":"published","type":"journal_article","scopus_import":"1","file":[{"success":1,"file_size":7746662,"content_type":"application/pdf","date_updated":"2025-10-23T11:13:58Z","date_created":"2025-10-23T11:13:58Z","file_name":"2025_NaturePlants_Shahzad.pdf","checksum":"6a3f6cffdc934b8a2015c3c247f5a92a","relation":"main_file","creator":"dernst","access_level":"open_access","file_id":"20524"}],"external_id":{"pmid":["40940427"],"isi":["001570197600001"]},"author":[{"full_name":"Shahzad, Zaigham","first_name":"Zaigham","last_name":"Shahzad"},{"last_name":"Hollwey","first_name":"Elizabeth","full_name":"Hollwey, Elizabeth","id":"b8c4f54b-e484-11eb-8fdc-a54df64ef6dd"},{"last_name":"Moore","full_name":"Moore, Jonathan D.","first_name":"Jonathan D."},{"first_name":"Jaemyung","full_name":"Choi, Jaemyung","last_name":"Choi"},{"full_name":"Cassin-Ross, Gaëlle","first_name":"Gaëlle","last_name":"Cassin-Ross"},{"first_name":"Hatem","full_name":"Rouached, Hatem","last_name":"Rouached"},{"first_name":"Matthew Richard","full_name":"Robinson, Matthew Richard","orcid":"0000-0001-8982-8813","last_name":"Robinson","id":"E5D42276-F5DA-11E9-8E24-6303E6697425"},{"id":"6973db13-dd5f-11ea-814e-b3e5455e9ed1","orcid":"0000-0002-0123-8649","last_name":"Zilberman","first_name":"Daniel","full_name":"Zilberman, Daniel"}],"intvolume":"        11","doi":"10.1038/s41477-025-02108-4","oa_version":"Published Version","date_updated":"2025-12-01T14:59:10Z","_id":"20479","isi":1,"title":"Gene body methylation regulates gene expression and mediates phenotypic diversity in natural Arabidopsis populations","oa":1,"PlanS_conform":"1","has_accepted_license":"1","pmid":1,"article_type":"original","month":"09","OA_type":"hybrid","department":[{"_id":"MaRo"},{"_id":"DaZi"}],"quality_controlled":"1","fulldoi":"https://doi.org/10.1038/s41477-025-02108-4","publisher":"Springer Nature","year":"2025","ec_funded":1,"publication_identifier":{"issn":["2055-0278"]}},{"fulldoi":"https://doi.org/10.1016/j.wasman.2025.115177","publisher":"Elsevier","year":"2025","publication_identifier":{"eissn":["1879-2456"],"issn":["0956-053X"]},"department":[{"_id":"MaRo"}],"quality_controlled":"1","_id":"20491","article_number":"115177","date_updated":"2025-12-01T12:58:17Z","oa":1,"has_accepted_license":"1","PlanS_conform":"1","pmid":1,"month":"11","article_type":"original","OA_type":"hybrid","title":"Deep eutectic solvent as a solution for polyester/cotton textile recycling","isi":1,"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","publication_status":"published","article_processing_charge":"Yes (via OA deal)","citation":{"short":"N. Depope, A. Depope, V.M. Archodoulaki, W. Ipsmiller, A. Bartl, Waste Management 208 (2025).","chicago":"Depope, Nika, Al Depope, Vasiliki Maria Archodoulaki, Wolfgang Ipsmiller, and Andreas Bartl. “Deep Eutectic Solvent as a Solution for Polyester/Cotton Textile Recycling.” <i>Waste Management</i>. Elsevier, 2025. <a href=\"https://doi.org/10.1016/j.wasman.2025.115177\">https://doi.org/10.1016/j.wasman.2025.115177</a>.","ieee":"N. Depope, A. Depope, V. M. Archodoulaki, W. Ipsmiller, and A. Bartl, “Deep eutectic solvent as a solution for polyester/cotton textile recycling,” <i>Waste Management</i>, vol. 208. Elsevier, 2025.","apa":"Depope, N., Depope, A., Archodoulaki, V. M., Ipsmiller, W., &#38; Bartl, A. (2025). Deep eutectic solvent as a solution for polyester/cotton textile recycling. <i>Waste Management</i>. Elsevier. <a href=\"https://doi.org/10.1016/j.wasman.2025.115177\">https://doi.org/10.1016/j.wasman.2025.115177</a>","ama":"Depope N, Depope A, Archodoulaki VM, Ipsmiller W, Bartl A. Deep eutectic solvent as a solution for polyester/cotton textile recycling. <i>Waste Management</i>. 2025;208. doi:<a href=\"https://doi.org/10.1016/j.wasman.2025.115177\">10.1016/j.wasman.2025.115177</a>","mla":"Depope, Nika, et al. “Deep Eutectic Solvent as a Solution for Polyester/Cotton Textile Recycling.” <i>Waste Management</i>, vol. 208, 115177, Elsevier, 2025, doi:<a href=\"https://doi.org/10.1016/j.wasman.2025.115177\">10.1016/j.wasman.2025.115177</a>.","ista":"Depope N, Depope A, Archodoulaki VM, Ipsmiller W, Bartl A. 2025. Deep eutectic solvent as a solution for polyester/cotton textile recycling. Waste Management. 208, 115177."},"ddc":["572"],"volume":208,"OA_place":"publisher","intvolume":"       208","doi":"10.1016/j.wasman.2025.115177","oa_version":"Published Version","type":"journal_article","scopus_import":"1","file":[{"success":1,"file_size":4511527,"date_updated":"2025-10-20T10:57:36Z","content_type":"application/pdf","file_name":"2025_WasteMgmt_Depope.pdf","date_created":"2025-10-20T10:57:36Z","checksum":"c232aae0ef7ed653813a835013f25bae","creator":"dernst","relation":"main_file","access_level":"open_access","file_id":"20501"}],"external_id":{"pmid":["41066876"],"isi":["001594629200003"]},"author":[{"last_name":"Depope","first_name":"Nika","full_name":"Depope, Nika"},{"full_name":"Depope, Al","first_name":"Al","last_name":"Depope","id":"0b77531d-dbcd-11ea-9d1d-a8eee0bf3830"},{"last_name":"Archodoulaki","first_name":"Vasiliki Maria","full_name":"Archodoulaki, Vasiliki Maria"},{"first_name":"Wolfgang","full_name":"Ipsmiller, Wolfgang","last_name":"Ipsmiller"},{"last_name":"Bartl","full_name":"Bartl, Andreas","first_name":"Andreas"}],"date_created":"2025-10-19T22:01:31Z","status":"public","language":[{"iso":"eng"}],"acknowledgement":"This study was conducted at the Josef Ressel Centre for Recovery Strategies of Textiles which is funded by the Christian Doppler Research Society on behalf of the Austrian Federal Ministry of Labor and Economic Affairs and the National Foundation for Research, Technology. The authors acknowledge “Open Access Funding by TU Wien” for financial support through its Open Access Funding Program.\r\nSpecial thanks are extended to EREMA Group GmbH, SALESIANER MIETTEX GmbH and Starlinger & Co GmbH for their material support and valuable input throughout the development of this study.","abstract":[{"lang":"eng","text":"Global fibre production has expanded rapidly, with polyester and cotton dominating, significantly contributing to textile waste and increasing demand for sustainable solutions. This study presents innovative method to recycle polyester/cotton (PET/CO) blends using hydrophobic deep eutectic solvents (DESs), eliminating the need for toxic chemicals while achieving high dissolution yields. PET was completely dissolved within 5 min, substantially outperforming state-of-the-art methods and facilitating the efficient and selective recovery of both components, PET (97%) and CO (100%). SEM imaging confirmed no morphological changes in cotton fibres after treatment. The thermal stability of the recovered materials was validated using DSC and TGA analyses, while ATR-FTIR spectroscopy indicated no chemical changes. Mechanical testing confirmed recovered cotton’s tenacity and elongation are within expected ranges despite showing a decrease of 28% in tenacity and 34% in elongation. Hence, the proposed process provides an efficient and sustainable recycling solution for PET/CO blends, retaining both polymers in a condition similar to virgin materials used in textile manufacturing with minimal processing time."}],"publication":"Waste Management","date_published":"2025-11-01T00:00:00Z","file_date_updated":"2025-10-20T10:57:36Z","tmp":{"legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","short":"CC BY (4.0)","image":"/images/cc_by.png","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)"},"day":"01"},{"author":[{"last_name":"Robertson","full_name":"Robertson, Josephine A.","first_name":"Josephine A."},{"last_name":"Bajzik","full_name":"Bajzik, Jakub","first_name":"Jakub","id":"b995e25b-8c4b-11ed-a6d8-f71b7bcd6122"},{"first_name":"Spyros","full_name":"Vernardis, Spyros","last_name":"Vernardis"},{"last_name":"Chybowska","first_name":"Aleksandra D.","full_name":"Chybowska, Aleksandra D."},{"first_name":"Daniel L.","full_name":"Mccartney, Daniel L.","last_name":"Mccartney"},{"first_name":"Arturas","full_name":"Grauslys, Arturas","last_name":"Grauslys"},{"first_name":"Jure","full_name":"Mur, Jure","last_name":"Mur"},{"last_name":"Smith","full_name":"Smith, Hannah M.","first_name":"Hannah M."},{"last_name":"Campbell","first_name":"Archie","full_name":"Campbell, Archie"},{"full_name":"Drake, Camilla","first_name":"Camilla","last_name":"Drake"},{"first_name":"Hannah","full_name":"Grant, Hannah","last_name":"Grant"},{"last_name":"Pearce","full_name":"Pearce, Jamie","first_name":"Jamie"},{"last_name":"Russ","full_name":"Russ, Tom C.","first_name":"Tom C."},{"full_name":"Adkin, Poppy","first_name":"Poppy","last_name":"Adkin"},{"last_name":"White","first_name":"Matthew","full_name":"White, Matthew"},{"last_name":"Brigden","full_name":"Brigden, Charles","first_name":"Charles"},{"last_name":"Messner","first_name":"Christoph B.","full_name":"Messner, Christoph B."},{"first_name":"David J.","full_name":"Porteous, David J.","last_name":"Porteous"},{"full_name":"Hayward, Caroline","first_name":"Caroline","last_name":"Hayward"},{"last_name":"Cox","full_name":"Cox, Simon R.","first_name":"Simon R."},{"full_name":"Zelezniak, Aleksej","first_name":"Aleksej","last_name":"Zelezniak"},{"first_name":"Markus","full_name":"Ralser, Markus","last_name":"Ralser"},{"first_name":"Matthew Richard","full_name":"Robinson, Matthew Richard","orcid":"0000-0001-8982-8813","last_name":"Robinson","id":"E5D42276-F5DA-11E9-8E24-6303E6697425"},{"first_name":"Riccardo E.","full_name":"Marioni, Riccardo E.","last_name":"Marioni"}],"external_id":{"pmid":["41361833"]},"scopus_import":"1","file":[{"success":1,"file_size":2206991,"date_updated":"2025-12-15T13:18:07Z","content_type":"application/pdf","date_created":"2025-12-15T13:18:07Z","file_name":"2025_GenomeBiology_Robertson.pdf","checksum":"7c92919af1b5820d01e91e08906a411f","creator":"dernst","relation":"main_file","access_level":"open_access","file_id":"20825"}],"type":"journal_article","oa_version":"Published Version","doi":"10.1186/s13059-025-03892-0","intvolume":"        26","OA_place":"publisher","volume":26,"ddc":["570"],"citation":{"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).","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>.","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>","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>","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.","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>.","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."},"article_processing_charge":"Yes","publication_status":"published","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","day":"08","tmp":{"legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","short":"CC BY (4.0)","image":"/images/cc_by.png","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)"},"file_date_updated":"2025-12-15T13:18:07Z","date_published":"2025-12-08T00:00:00Z","publication":"Genome Biology","abstract":[{"lang":"eng","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."}],"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"}],"status":"public","date_created":"2025-12-14T23:02:04Z","quality_controlled":"1","department":[{"_id":"MaRo"}],"publication_identifier":{"issn":["1474-7596"],"eissn":["1474-760X"]},"year":"2025","publisher":"Springer Nature","fulldoi":"https://doi.org/10.1186/s13059-025-03892-0","DOAJ_listed":"1","title":"Methylome-wide association studies and epigenetic biomarker development for 133 mass spectrometry-assessed circulating proteins in 14,671 Generation Scotland participants","OA_type":"gold","article_type":"original","month":"12","pmid":1,"has_accepted_license":"1","oa":1,"date_updated":"2025-12-15T13:19:41Z","article_number":"417","_id":"20816"},{"publication_status":"published","issue":"1","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","volume":112,"OA_place":"publisher","article_processing_charge":"No","citation":{"apa":"Smith, H. M., Ng, H. K., Moodie, J. E., Gadd, D. A., Mccartney, D. L., Bernabeu, E., … Hillary, R. F. (2025). DNA methylation-based predictors of metabolic traits in Scottish and Singaporean cohorts. <i>American Journal of Human Genetics</i>. Cell Press. <a href=\"https://doi.org/10.1016/j.ajhg.2024.11.012\">https://doi.org/10.1016/j.ajhg.2024.11.012</a>","ama":"Smith HM, Ng HK, Moodie JE, et al. DNA methylation-based predictors of metabolic traits in Scottish and Singaporean cohorts. <i>American Journal of Human Genetics</i>. 2025;112(1):106-115. doi:<a href=\"https://doi.org/10.1016/j.ajhg.2024.11.012\">10.1016/j.ajhg.2024.11.012</a>","ieee":"H. M. Smith <i>et al.</i>, “DNA methylation-based predictors of metabolic traits in Scottish and Singaporean cohorts,” <i>American Journal of Human Genetics</i>, vol. 112, no. 1. Cell Press, pp. 106–115, 2025.","chicago":"Smith, Hannah M., Hong Kiat Ng, Joanna E. Moodie, Danni A. Gadd, Daniel L. Mccartney, Elena Bernabeu, Archie Campbell, et al. “DNA Methylation-Based Predictors of Metabolic Traits in Scottish and Singaporean Cohorts.” <i>American Journal of Human Genetics</i>. Cell Press, 2025. <a href=\"https://doi.org/10.1016/j.ajhg.2024.11.012\">https://doi.org/10.1016/j.ajhg.2024.11.012</a>.","short":"H.M. Smith, H.K. Ng, J.E. Moodie, D.A. Gadd, D.L. Mccartney, E. Bernabeu, A. Campbell, P. Redmond, A. Taylor, D. Page, J. Corley, S.E. Harris, D. Tay, I.J. Deary, K.L. Evans, M.R. Robinson, J.C. Chambers, M. Loh, S.R. Cox, R.E. Marioni, R.F. Hillary, American Journal of Human Genetics 112 (2025) 106–115.","ista":"Smith HM, Ng HK, Moodie JE, Gadd DA, Mccartney DL, Bernabeu E, Campbell A, Redmond P, Taylor A, Page D, Corley J, Harris SE, Tay D, Deary IJ, Evans KL, Robinson MR, Chambers JC, Loh M, Cox SR, Marioni RE, Hillary RF. 2025. DNA methylation-based predictors of metabolic traits in Scottish and Singaporean cohorts. American Journal of Human Genetics. 112(1), 106–115.","mla":"Smith, Hannah M., et al. “DNA Methylation-Based Predictors of Metabolic Traits in Scottish and Singaporean Cohorts.” <i>American Journal of Human Genetics</i>, vol. 112, no. 1, Cell Press, 2025, pp. 106–15, doi:<a href=\"https://doi.org/10.1016/j.ajhg.2024.11.012\">10.1016/j.ajhg.2024.11.012</a>."},"ddc":["570"],"oa_version":"Published Version","intvolume":"       112","doi":"10.1016/j.ajhg.2024.11.012","external_id":{"isi":["001412498600001"],"pmid":["39706196"]},"author":[{"last_name":"Smith","full_name":"Smith, Hannah M.","first_name":"Hannah M."},{"last_name":"Ng","full_name":"Ng, Hong Kiat","first_name":"Hong Kiat"},{"last_name":"Moodie","full_name":"Moodie, Joanna E.","first_name":"Joanna E."},{"last_name":"Gadd","full_name":"Gadd, Danni A.","first_name":"Danni A."},{"full_name":"Mccartney, Daniel L.","first_name":"Daniel L.","last_name":"Mccartney"},{"last_name":"Bernabeu","first_name":"Elena","full_name":"Bernabeu, Elena"},{"full_name":"Campbell, Archie","first_name":"Archie","last_name":"Campbell"},{"full_name":"Redmond, Paul","first_name":"Paul","last_name":"Redmond"},{"last_name":"Taylor","full_name":"Taylor, Adele","first_name":"Adele"},{"first_name":"Danielle","full_name":"Page, Danielle","last_name":"Page"},{"last_name":"Corley","first_name":"Janie","full_name":"Corley, Janie"},{"last_name":"Harris","full_name":"Harris, Sarah E.","first_name":"Sarah E."},{"last_name":"Tay","first_name":"Darwin","full_name":"Tay, Darwin"},{"last_name":"Deary","full_name":"Deary, Ian J.","first_name":"Ian J."},{"full_name":"Evans, Kathryn L.","first_name":"Kathryn L.","last_name":"Evans"},{"full_name":"Robinson, Matthew Richard","first_name":"Matthew Richard","last_name":"Robinson","orcid":"0000-0001-8982-8813","id":"E5D42276-F5DA-11E9-8E24-6303E6697425"},{"full_name":"Chambers, John C.","first_name":"John C.","last_name":"Chambers"},{"first_name":"Marie","full_name":"Loh, Marie","last_name":"Loh"},{"last_name":"Cox","full_name":"Cox, Simon R.","first_name":"Simon R."},{"first_name":"Riccardo E.","full_name":"Marioni, Riccardo E.","last_name":"Marioni"},{"last_name":"Hillary","full_name":"Hillary, Robert F.","first_name":"Robert F."}],"type":"journal_article","file":[{"access_level":"open_access","file_id":"18776","relation":"main_file","creator":"dernst","date_created":"2025-01-08T09:26:42Z","file_name":"2025_AJHG_Smith.pdf","checksum":"891d120554f07da2c35d38388c29a690","success":1,"file_size":2266488,"date_updated":"2025-01-08T09:26:42Z","content_type":"application/pdf"}],"scopus_import":"1","date_created":"2025-01-05T23:01:56Z","abstract":[{"lang":"eng","text":"Exploring the molecular correlates of metabolic health measures may identify their shared and unique biological processes and pathways. Molecular proxies of these traits may also provide a more objective approach to their measurement. Here, DNA methylation (DNAm) data were used in epigenome-wide association studies (EWASs) and for training epigenetic scores (EpiScores) of six metabolic traits: body mass index (BMI), body fat percentage, waist-hip ratio, and blood-based measures of glucose, high-density lipoprotein cholesterol, and total cholesterol in >17,000 volunteers from the Generation Scotland (GS) cohort. We observed a maximum of 12,033 significant findings (p < 3.6 × 10−8) for BMI in a marginal linear regression EWAS. By contrast, a joint and conditional Bayesian penalized regression approach yielded 27 high-confidence associations with BMI. EpiScores trained in GS performed well in both Scottish and Singaporean test cohorts (Lothian Birth Cohort 1936 [LBC1936] and Health for Life in Singapore [HELIOS]). The EpiScores for BMI and total cholesterol performed best in HELIOS, explaining 20.8% and 7.1% of the variance in the measured traits, respectively. The corresponding results in LBC1936 were 14.4% and 3.2%, respectively. Differences were observed in HELIOS for body fat, where the EpiScore explained ∼9% of the variance in Chinese and Malay -subgroups but ∼3% in the Indian subgroup. The EpiScores also correlated with cognitive function in LBC1936 (standardized βrange: 0.08–0.12, false discovery rate p [pFDR] < 0.05). Accounting for the correlation structure across the methylome can vastly affect the number of lead findings in EWASs. The EpiScores of metabolic traits are broadly applicable across populations and can reflect differences in cognition."}],"publication":"American Journal of Human Genetics","status":"public","language":[{"iso":"eng"}],"page":"106-115","file_date_updated":"2025-01-08T09:26:42Z","date_published":"2025-01-02T00:00:00Z","day":"02","related_material":{"link":[{"relation":"software","url":"https://github.com/marioni-group/Metabolic_trait"}]},"tmp":{"legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","short":"CC BY (4.0)","image":"/images/cc_by.png","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)"},"publisher":"Cell Press","year":"2025","publication_identifier":{"issn":["0002-9297"],"eissn":["1537-6605"]},"fulldoi":"https://doi.org/10.1016/j.ajhg.2024.11.012","quality_controlled":"1","department":[{"_id":"MaRo"}],"_id":"18754","date_updated":"2026-10-20T08:53:52Z","month":"01","article_type":"original","OA_type":"hybrid","oa":1,"pmid":1,"has_accepted_license":"1","isi":1,"title":"DNA methylation-based predictors of metabolic traits in Scottish and Singaporean cohorts"},{"fulldoi":"https://doi.org/10.1007/s11692-023-09624-1","publication_identifier":{"eissn":["1934-2845"],"issn":["0071-3260"]},"year":"2024","publisher":"Springer Nature","department":[{"_id":"MaRo"}],"quality_controlled":"1","has_accepted_license":"1","oa":1,"article_type":"original","month":"03","isi":1,"title":"Antler allometry, the Irish elk and Gould revisited","_id":"14932","date_updated":"2026-10-16T10:43:26Z","doi":"10.1007/s11692-023-09624-1","researchdata_availability":"upon request","intvolume":"        51","oa_version":"Published Version","scopus_import":"1","file":[{"access_level":"open_access","file_id":"17311","relation":"main_file","creator":"dernst","file_name":"2024_EvolutionaryBio_Tsuboi.pdf","date_created":"2024-07-22T11:53:43Z","checksum":"416ab4dac751c443b9de51fb58278ff2","file_size":1705974,"success":1,"content_type":"application/pdf","date_updated":"2024-07-22T11:53:43Z"}],"type":"journal_article","author":[{"first_name":"Masahito","full_name":"Tsuboi, Masahito","last_name":"Tsuboi"},{"full_name":"Kopperud, Bjørn Tore","first_name":"Bjørn Tore","last_name":"Kopperud"},{"first_name":"Michael","full_name":"Matschiner, Michael","last_name":"Matschiner"},{"last_name":"Grabowski","full_name":"Grabowski, Mark","first_name":"Mark"},{"id":"205ffb76-7fe7-11eb-aa17-958bd11b99ad","first_name":"Chrsitine","full_name":"Syrowatka, Chrsitine","last_name":"Syrowatka"},{"last_name":"Pélabon","first_name":"Christophe","full_name":"Pélabon, Christophe"},{"first_name":"Thomas F.","full_name":"Hansen, Thomas F.","last_name":"Hansen"}],"external_id":{"isi":["001151285200001"]},"user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","publication_status":"published","ddc":["570"],"citation":{"chicago":"Tsuboi, Masahito, Bjørn Tore Kopperud, Michael Matschiner, Mark Grabowski, Chrsitine Syrowatka, Christophe Pélabon, and Thomas F. Hansen. “Antler Allometry, the Irish Elk and Gould Revisited.” <i>Evolutionary Biology</i>. Springer Nature, 2024. <a href=\"https://doi.org/10.1007/s11692-023-09624-1\">https://doi.org/10.1007/s11692-023-09624-1</a>.","short":"M. Tsuboi, B.T. Kopperud, M. Matschiner, M. Grabowski, C. Syrowatka, C. Pélabon, T.F. Hansen, Evolutionary Biology 51 (2024) 149–165.","apa":"Tsuboi, M., Kopperud, B. T., Matschiner, M., Grabowski, M., Syrowatka, C., Pélabon, C., &#38; Hansen, T. F. (2024). Antler allometry, the Irish elk and Gould revisited. <i>Evolutionary Biology</i>. Springer Nature. <a href=\"https://doi.org/10.1007/s11692-023-09624-1\">https://doi.org/10.1007/s11692-023-09624-1</a>","ama":"Tsuboi M, Kopperud BT, Matschiner M, et al. Antler allometry, the Irish elk and Gould revisited. <i>Evolutionary Biology</i>. 2024;51:149-165. doi:<a href=\"https://doi.org/10.1007/s11692-023-09624-1\">10.1007/s11692-023-09624-1</a>","ieee":"M. Tsuboi <i>et al.</i>, “Antler allometry, the Irish elk and Gould revisited,” <i>Evolutionary Biology</i>, vol. 51. Springer Nature, pp. 149–165, 2024.","mla":"Tsuboi, Masahito, et al. “Antler Allometry, the Irish Elk and Gould Revisited.” <i>Evolutionary Biology</i>, vol. 51, Springer Nature, 2024, pp. 149–65, doi:<a href=\"https://doi.org/10.1007/s11692-023-09624-1\">10.1007/s11692-023-09624-1</a>.","ista":"Tsuboi M, Kopperud BT, Matschiner M, Grabowski M, Syrowatka C, Pélabon C, Hansen TF. 2024. Antler allometry, the Irish elk and Gould revisited. Evolutionary Biology. 51, 149–165."},"supplementarymaterial":"yes","article_processing_charge":"Yes (via OA deal)","volume":51,"dataavailabilitystatement":"All data used in this paper are available from the authors on request.","das_tickbox":"1","date_published":"2024-03-01T00:00:00Z","file_date_updated":"2024-07-22T11:53:43Z","page":"149-165","tmp":{"legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","short":"CC BY (4.0)","image":"/images/cc_by.png","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)"},"day":"01","date_created":"2024-02-04T23:00:53Z","status":"public","language":[{"iso":"eng"}],"acknowledgement":"Open access funding provided by University of Oslo (incl Oslo University Hospital).\r\nWe thank Adrian Lister, Louis Tomsett, Roberto Portela Miguez and Roula Pappa (NHMUK), Brian O'Toole and Eileen Westwig (AMNH), Daniela Kalthoff (NHRM), Alexander Bibl and Zachos Frank (NHMW), Darrin Lunde and John Ososky (NMNH), Matthew Parkes and Nigel Monaghan (NMI), Elizabetta Cioppi and Luca Bellucci (IGF), and Yoshihiro Tanaka and Hiroyuki Taruno (OMNH), who helped us in obtaining the museum data, and a special thanks to Jørgen Sikkeland (NTNU NHM) for assistance in obtaining the ontogenetic data for the red deer. We thank Olja Toljagic and Kjetil L. Voje for discussions, Ayumu Tsuboi for assistance with data collection, and Jean-Michel Gaillard and the anonymous reviewers for comments on the manuscript. We thank the Centre of Advanced Study (CAS) at the Norwegian Academy of Sciences and Letters for hosting us during the academic year of 2019/2020 when much of the analysis and writing were done. MT was funded by JSPS Research Fellowship for Young Scientists (201603238).","publication":"Evolutionary Biology","abstract":[{"text":"The huge antlers of the extinct Irish elk have invited evolutionary speculation since Darwin. In the 1970s, Stephen Jay Gould presented the first extensive data on antler size in the Irish elk and combined these with comparative data from other deer to test the hypothesis that the gigantic antlers were the outcome of a positive allometry that constrained large-bodied deer to have proportionally even larger antlers. He concluded that the Irish elk had antlers as predicted for its size and interpreted this within his emerging framework of developmental constraints as an explanatory factor in evolution. Here we reanalyze antler allometry based on new morphometric data for 57 taxa of the family Cervidae. We also present a new phylogeny for the Cervidae, which we use for comparative analyses. In contrast to Gould, we find that the antlers of Irish elk were larger than predicted from the allometry within the true deer, Cervini, as analyzed by Gould, but follow the allometry across Cervidae as a whole. After dissecting the discrepancy, we reject the allometric-constraint hypothesis because, contrary to Gould, we find no similarity between static and evolutionary allometries, and because we document extensive non-allometric evolution of antler size across the Cervidae.","lang":"eng"}]},{"date_updated":"2026-10-16T10:42:55Z","_id":"17147","title":"Inference of genetic effects via approximate message passing","isi":1,"OA_type":"green","acknowledged_ssus":[{"_id":"ScienComp"}],"month":"04","oa":1,"main_file_link":[{"open_access":"1","url":"https://openreview.net/forum?id=aQYCDxfZV0"}],"quality_controlled":"1","department":[{"_id":"MaMo"},{"_id":"MaRo"}],"year":"2024","publication_identifier":{"isbn":["9798350344851"],"issn":["1520-6149"]},"publisher":"IEEE","fulldoi":"https://doi.org/10.1109/ICASSP48485.2024.10447198","publication":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing","abstract":[{"lang":"eng","text":"Efficient utilization of large-scale biobank data is crucial for inferring the genetic basis of disease and predicting health outcomes from the DNA. Yet we lack efficient, accurate methods that scale to data where electronic health records are linked to whole genome sequence information. To address this issue, our paper develops a new algorithmic paradigm based on Approximate Message Passing (AMP), which is specifically tailored for genomic prediction and association testing. Our method yields comparable out-of-sample prediction accuracy to the state of the art on UK Biobank traits, whilst dramatically improving computational complexity, with a 8x-speed up in the run time. In addition, AMP theory provides a joint association testing framework, which outperforms the currently used REGENIE method, in roughly a third of the compute time. This first, truly large-scale application of the AMP framework lays the foundations for a far wider range of statistical analyses for hundreds of millions of variables measured on millions of people."}],"acknowledgement":"This work was supported by a Lopez-Loreta Prize to MM, an SNSF Eccellenza Grant to MRR (PCEGP3-181181), and core funding from ISTA. The authors thank Philip Schniter, Matthew Stephens and Pragya Sur for valuable suggestions on an early version of the work. The authors acknowledge the participants and investigators of the UK Biobank study. High-performance\r\ncomputing was supported by the Scientific Service Units (SSU) of IST Austria through resources provided by Scientific Computing (SciComp).","status":"public","language":[{"iso":"eng"}],"date_created":"2024-06-16T22:01:07Z","day":"19","corr_author":"1","page":"13151-13155","das_tickbox":"0","date_published":"2024-04-19T00:00:00Z","OA_place":"repository","supplementarymaterial":"no","citation":{"short":"A. Depope, M. Mondelli, M.R. Robinson, in:, 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, IEEE, 2024, pp. 13151–13155.","chicago":"Depope, Al, Marco Mondelli, and Matthew Richard Robinson. “Inference of Genetic Effects via Approximate Message Passing.” In <i>2024 IEEE International Conference on Acoustics, Speech, and Signal Processing</i>, 13151–55. IEEE, 2024. <a href=\"https://doi.org/10.1109/ICASSP48485.2024.10447198\">https://doi.org/10.1109/ICASSP48485.2024.10447198</a>.","ieee":"A. Depope, M. Mondelli, and M. R. Robinson, “Inference of genetic effects via approximate message passing,” in <i>2024 IEEE International Conference on Acoustics, Speech, and Signal Processing</i>, Seoul, Korea, 2024, pp. 13151–13155.","ama":"Depope A, Mondelli M, Robinson MR. Inference of genetic effects via approximate message passing. In: <i>2024 IEEE International Conference on Acoustics, Speech, and Signal Processing</i>. IEEE; 2024:13151-13155. doi:<a href=\"https://doi.org/10.1109/ICASSP48485.2024.10447198\">10.1109/ICASSP48485.2024.10447198</a>","apa":"Depope, A., Mondelli, M., &#38; Robinson, M. R. (2024). Inference of genetic effects via approximate message passing. In <i>2024 IEEE International Conference on Acoustics, Speech, and Signal Processing</i> (pp. 13151–13155). Seoul, Korea: IEEE. <a href=\"https://doi.org/10.1109/ICASSP48485.2024.10447198\">https://doi.org/10.1109/ICASSP48485.2024.10447198</a>","mla":"Depope, Al, et al. “Inference of Genetic Effects via Approximate Message Passing.” <i>2024 IEEE International Conference on Acoustics, Speech, and Signal Processing</i>, IEEE, 2024, pp. 13151–55, doi:<a href=\"https://doi.org/10.1109/ICASSP48485.2024.10447198\">10.1109/ICASSP48485.2024.10447198</a>.","ista":"Depope A, Mondelli M, Robinson MR. 2024. Inference of genetic effects via approximate message passing. 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing. ICASSP: International Conference on Acoustics, Speech and Signal Processing, 13151–13155."},"conference":{"location":"Seoul, Korea","start_date":"2024-04-14","end_date":"2024-04-19","name":"ICASSP: International Conference on Acoustics, Speech and Signal Processing"},"article_processing_charge":"No","publication_status":"published","project":[{"_id":"059876FA-7A3F-11EA-A408-12923DDC885E","name":"Prix Lopez-Loretta 2019 - Marco Mondelli"},{"_id":"9B8D11D6-BA93-11EA-9121-9846C619BF3A","grant_number":"PCEGP3_181181","name":"Improving estimation and prediction of common complex disease risk"}],"user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","author":[{"last_name":"Depope","full_name":"Depope, Al","first_name":"Al","id":"0b77531d-dbcd-11ea-9d1d-a8eee0bf3830"},{"id":"27EB676C-8706-11E9-9510-7717E6697425","first_name":"Marco","full_name":"Mondelli, Marco","orcid":"0000-0002-3242-7020","last_name":"Mondelli"},{"first_name":"Matthew Richard","full_name":"Robinson, Matthew Richard","orcid":"0000-0001-8982-8813","last_name":"Robinson","id":"E5D42276-F5DA-11E9-8E24-6303E6697425"}],"external_id":{"isi":["001396233806078"]},"scopus_import":"1","type":"conference","oa_version":"Submitted Version","doi":"10.1109/ICASSP48485.2024.10447198","researchdata_availability":"no"},{"fulldoi":"https://doi.org/10.15479/at:ista:17368","publisher":"Institute of Science and Technology Austria","publication_identifier":{"issn":["2791-4585"]},"year":"2024","department":[{"_id":"GradSch"},{"_id":"MaRo"}],"alternative_title":["ISTA Master's Thesis"],"oa":1,"has_accepted_license":"1","month":"08","title":"Bayesian linear regression for analyzing general omics data with time-to-event phenotypes","_id":"17368","keyword":["Epigenetics","Multi-omics","Bayesian regression"],"date_updated":"2026-10-02T11:35:19Z","researchdata_availability":"no","doi_confirm":"1","doi":"10.15479/at:ista:17368","oa_version":"Published Version","type":"dissertation","file":[{"creator":"avillanu","relation":"main_file","file_id":"17433","access_level":"open_access","date_updated":"2025-02-14T23:30:03Z","content_type":"application/pdf","file_size":13052436,"embargo":"2025-02-14","checksum":"0c2daa174609f0c00919dccc5701d375","file_name":"Masters_thesis_AriadnaVillanueva.pdf","date_created":"2024-08-14T11:51:24Z"},{"file_id":"17434","access_level":"closed","relation":"source_file","creator":"avillanu","checksum":"e9ed4465dfa539ac4c3a8d4d0b6271a1","embargo_to":"open_access","file_name":"Masters thesis-AriadnaVillanueva.zip","date_created":"2024-08-14T11:51:57Z","date_updated":"2025-02-14T23:30:03Z","content_type":"application/zip","file_size":45642547}],"author":[{"id":"e0ae4864-133f-11ed-8f02-adaa8dd27540","full_name":"Villanueva Marijuan, Ariadna","first_name":"Ariadna","last_name":"Villanueva Marijuan"}],"user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","publication_status":"published","article_processing_charge":"No","ddc":["610"],"supplementarymaterial":"no","citation":{"ista":"Villanueva Marijuan A. 2024. Bayesian linear regression for analyzing general omics data with time-to-event phenotypes. Institute of Science and Technology Austria.","mla":"Villanueva Marijuan, Ariadna. <i>Bayesian Linear Regression for Analyzing General Omics Data with Time-to-Event Phenotypes</i>. Institute of Science and Technology Austria, 2024, doi:<a href=\"https://doi.org/10.15479/at:ista:17368\">10.15479/at:ista:17368</a>.","apa":"Villanueva Marijuan, A. (2024). <i>Bayesian linear regression for analyzing general omics data with time-to-event phenotypes</i>. Institute of Science and Technology Austria. <a href=\"https://doi.org/10.15479/at:ista:17368\">https://doi.org/10.15479/at:ista:17368</a>","ama":"Villanueva Marijuan A. Bayesian linear regression for analyzing general omics data with time-to-event phenotypes. 2024. doi:<a href=\"https://doi.org/10.15479/at:ista:17368\">10.15479/at:ista:17368</a>","ieee":"A. Villanueva Marijuan, “Bayesian linear regression for analyzing general omics data with time-to-event phenotypes,” Institute of Science and Technology Austria, 2024.","short":"A. Villanueva Marijuan, Bayesian Linear Regression for Analyzing General Omics Data with Time-to-Event Phenotypes, Institute of Science and Technology Austria, 2024.","chicago":"Villanueva Marijuan, Ariadna. “Bayesian Linear Regression for Analyzing General Omics Data with Time-to-Event Phenotypes.” Institute of Science and Technology Austria, 2024. <a href=\"https://doi.org/10.15479/at:ista:17368\">https://doi.org/10.15479/at:ista:17368</a>."},"degree_awarded":"MS","OA_place":"publisher","date_published":"2024-08-13T00:00:00Z","das_tickbox":"0","file_date_updated":"2025-02-14T23:30:03Z","page":"60","tmp":{"image":"/images/cc_by_nc_sa.png","short":"CC BY-NC-SA (4.0)","legal_code_url":"https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode","name":"Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)"},"corr_author":"1","day":"13","date_created":"2024-08-02T10:52:40Z","supervisor":[{"id":"E5D42276-F5DA-11E9-8E24-6303E6697425","first_name":"Matthew Richard","full_name":"Robinson, Matthew Richard","orcid":"0000-0001-8982-8813","last_name":"Robinson"}],"language":[{"iso":"eng"}],"status":"public","abstract":[{"lang":"eng","text":"Recent advancements in molecular diagnostic techniques have enabled the collection of\r\nmultiple types of omics data from patients, including genomics, epigenomics, proteomics,\r\nand transcriptomics. However, we lack effective methods for integrating all these different\r\ndata types and combining them with clinical outcomes to study the molecular mechanisms\r\nthat govern pathological phenotypes. We present multi-omics BayesW, a penalized Bayesian\r\nregression method that can handle general omics data for survival analysis of time-to-event\r\nphenotypes. Our method can: (1) accommodate incomplete data by allowing censored\r\nindividuals, (2) use continuous time-to-event data to test associations of markers with a\r\nphenotype and (3) estimate effects jointly while allowing for independent groups of biological\r\nmarkers. Extensive simulations using planted signals on real data demonstrate that our model\r\naccurately retrieves the true parameters of the model while controlling for false discoveries\r\nand maintaining the expected prediction accuracy. We address data correlations by estimating\r\nthe effects jointly, even between omic groups, while also estimating the individual variance\r\nexplained by each group. We apply our model to two datasets. Using 18,000 individuals from\r\nthe Generation Scotland study we model the association of time at onset of Type 2 Diabetes,\r\nStroke, Ischemic Disease, and Osteoarthritis from baseline study entry, with 831,724 CpG\r\nmethylation probes. We find that large proportions of variation in disease onset times can\r\nbe attributed to methylation as measured in whole blood at baseline in individuals without\r\ndisease symptoms. We then apply our model to The Cancer Genome Atlas (TCGA) pan-cancer\r\ndataset, in which we use 5 types of omics: copy number variation, epigenetics, somatic\r\nmutations, miRNA, and gene expression. For cancer survival age-at-onset we find that, when\r\nfitting the 5 groups together, almost all variation attributable to \"omics\" data is explained by\r\nDNA methylation. When considering progression times, both methylation and gene expression\r\nexplain a large part of the variance. We found 2 genes that are significantly associated (95%\r\nposterior inclusion probability) with cancer survival time, conditional on all other genome-wide\r\nomics data variation. Owing to the vast variability of mechanisms characterizing different\r\ncancers, there are likely few specific genes with a strong signal in a pan-cancer setting. Taken\r\ntogether, we showed the applicability of our multi-omics BayesW model to a wide-range of\r\nbiological questions in multi-omics data.\r\n"}]},{"alternative_title":["ISTA Thesis"],"department":[{"_id":"GradSch"},{"_id":"MaRo"}],"fulldoi":"https://doi.org/10.15479/at:ista:18642","publisher":"Institute of Science and Technology Austria","year":"2024","publication_identifier":{"issn":["2663-337X"]},"date_updated":"2026-10-16T11:01:16Z","_id":"18642","title":"Algorithms for causal learning and comparative analysis for genomic data","oa":1,"has_accepted_license":"1","month":"12","article_processing_charge":"No","supplementarymaterial":"unclear","ddc":["576"],"citation":{"short":"N.N. Machnik, Algorithms for Causal Learning and Comparative Analysis for Genomic Data, Institute of Science and Technology Austria, 2024.","chicago":"Machnik, Nick N. “Algorithms for Causal Learning and Comparative Analysis for Genomic Data.” Institute of Science and Technology Austria, 2024. <a href=\"https://doi.org/10.15479/at:ista:18642\">https://doi.org/10.15479/at:ista:18642</a>.","apa":"Machnik, N. N. (2024). <i>Algorithms for causal learning and comparative analysis for genomic data</i>. Institute of Science and Technology Austria. <a href=\"https://doi.org/10.15479/at:ista:18642\">https://doi.org/10.15479/at:ista:18642</a>","ama":"Machnik NN. Algorithms for causal learning and comparative analysis for genomic data. 2024. doi:<a href=\"https://doi.org/10.15479/at:ista:18642\">10.15479/at:ista:18642</a>","ieee":"N. N. Machnik, “Algorithms for causal learning and comparative analysis for genomic data,” Institute of Science and Technology Austria, 2024.","mla":"Machnik, Nick N. <i>Algorithms for Causal Learning and Comparative Analysis for Genomic Data</i>. Institute of Science and Technology Austria, 2024, doi:<a href=\"https://doi.org/10.15479/at:ista:18642\">10.15479/at:ista:18642</a>.","ista":"Machnik NN. 2024. Algorithms for causal learning and comparative analysis for genomic data. Institute of Science and Technology Austria."},"degree_awarded":"PhD","OA_place":"publisher","user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","project":[{"name":"Improving estimation and prediction of common complex disease risk","grant_number":"PCEGP3_181181","_id":"9B8D11D6-BA93-11EA-9121-9846C619BF3A"}],"publication_status":"published","type":"dissertation","file":[{"relation":"main_file","creator":"nmachnik","file_id":"18649","access_level":"open_access","content_type":"application/pdf","date_updated":"2025-06-12T22:30:02Z","file_size":12845009,"checksum":"d45e4d170f9a70a1f69b44b99bd058e4","embargo":"2025-06-12","date_created":"2024-12-11T11:59:54Z","file_name":"NickMachnikThesisFinal_pdfa_conv.pdf"},{"date_updated":"2025-06-12T22:30:02Z","content_type":"application/zip","file_size":14189810,"embargo_to":"open_access","checksum":"f88c9acc62002395ec4dcbdb5eea8b82","file_name":"thesis.zip","date_created":"2024-12-11T11:59:34Z","creator":"nmachnik","relation":"source_file","file_id":"18650","access_level":"closed"}],"author":[{"id":"3591A0AA-F248-11E8-B48F-1D18A9856A87","full_name":"Machnik, Nick N","first_name":"Nick N","last_name":"Machnik","orcid":"0000-0001-6617-9742"}],"doi_confirm":"1","researchdata_availability":"unclear","doi":"10.15479/at:ista:18642","oa_version":"Published Version","supervisor":[{"full_name":"Robinson, Matthew Richard","first_name":"Matthew Richard","last_name":"Robinson","orcid":"0000-0001-8982-8813","id":"E5D42276-F5DA-11E9-8E24-6303E6697425"}],"status":"public","acknowledgement":"I would like to thank the Swiss National Science Foundation for funding parts of this work\r\nthrough the Eccellenza Grant \"Improving estimation and prediction of common complex\r\ndisease risk\" with grant number PCEGP3_181181.","language":[{"iso":"eng"}],"abstract":[{"text":"This thesis consists of two pieces of work in the broader field of computational biology,\r\nboth of which are methods for the analysis of large scale biological data, implemented in\r\nefficient software.\r\nChapter 2 introduces a statistical software for causal discovery and inference from observed\r\ngenetic marker and phenotypic trait data. We explore in simulation how well the method\r\ncan fine-map genetic effects, find the correct causal structure among tens of traits and\r\nmillions of genetic markers, and infer the causal effect size for the discovered causal\r\nrelations. We then apply the method to 8 million markers and 17 traits from the UK\r\nBiobank and show that many relationships found with other methods are likely due to\r\nthe effects of hidden confounders.\r\nChapter 3 describes how this method can be applied to longitudinal data. I show how one\r\ncan incorporate the background knowledge present in the known order of measurements to\r\nimprove the accuracy of the causal discovery process, and explore the method’s ability to\r\nidentify age specific genetic effects, and how the error rates of this recovery are influenced\r\nby missing data due to different censoring mechanisms.\r\nChapter 4 introduces a statistical software for the comparison of chromatin contact maps\r\nbased on the structural similarity index. We explore the robustness of the method to\r\nnoise and size differences of the compared maps, show how it can measure evolutionary\r\nconservation of topological features by providing a similarity ranking of syntenic regions,\r\nand finally how it can detect alterations in 3D genome structure due to genetic mutations\r\nin samples of medical relevance.\r\n","lang":"eng"}],"date_created":"2024-12-10T13:49:15Z","related_material":{"record":[{"relation":"part_of_dissertation","status":"public","id":"8707"},{"status":"public","relation":"part_of_dissertation","id":"18648"}]},"corr_author":"1","day":"11","date_published":"2024-12-11T00:00:00Z","file_date_updated":"2025-06-12T22:30:02Z","page":"138"},{"_id":"18648","date_updated":"2026-11-21T23:31:17Z","oa":1,"month":"08","acknowledged_ssus":[{"_id":"ScienComp"}],"OA_type":"free access","title":"Causal inference for multiple risk factors and diseases from genomics data","main_file_link":[{"url":"https://doi.org/10.1101/2023.12.06.570392","open_access":"1"}],"fulldoi":"https://doi.org/10.1101/2023.12.06.570392","year":"2024","department":[{"_id":"MaRo"}],"date_created":"2024-12-11T10:42:59Z","status":"public","language":[{"iso":"eng"}],"acknowledgement":"We thank Zoltan Kutalik and members of the Robinson group \r\nat ISTA for their comments, which improved this manuscript. This work was funded \r\nby a research collaboration agreement between Boehringer Ingelheim and the research \r\ngroup of MRR at the Institute of Science and Technology Austria. Additional funding \r\nwas also provided by an SNSF Eccellenza Grant to MRR (PCEGP3-181181), and by \r\ncore funding from the Institute of Science and Technology Austria. We would like \r\nto acknowledge the participants and investigators of the UK Biobank study. High- \r\nperformance computing was supported by the Scientific Service Units (SSU) of IST \r\nAustria through resources provided by Scientific Computing (SciComp). ","abstract":[{"lang":"eng","text":"Statistical causal learning in genomics relies on the instrumental variable method of\r\nMendelian Randomization (MR). Currently, an overwhelming number of MR studies\r\npurport to show causal relationships among a wide range of risk factors and outcomes.\r\nHere, we show that selecting instrument variables from genome-wide association study\r\nestimates leads to high false discovery rates for many MR approaches, which can be\r\ngreatly reduced by employing a graphical inference approach which: (i) explicitly tests\r\ninstrumental variable assumptions; (ii) distinguishes direct from indirect factors in very\r\nhigh-dimensional data; (iii) discriminates pleiotropic from trait-specific markers, controlling for LD genome-wide; (iv) accommodates rare variants and binary outcomes in a\r\nprincipled way; and (v) identifies potential unobserved latent confounding. For 17 traits\r\nand 8.4M variants recorded for 458,747 individuals in the UK Biobank, we show that\r\nstandard MR analysis gives an abundance of findings that disappear under stringent\r\nassumption checks, with many relationships reflecting potential unmeasured confounding. This implies that mixtures of temporal precedence and potential for reverse-causality\r\nprohibit understanding the underlying nature of phenotypic and genetic correlations in\r\nbiobank data. We propose that well-curated longitudinal records are likely needed and\r\nthat our approach provides a first-step toward robust principled screening for potential\r\ncausal links.\r\n"}],"publication":"bioRxiv","das_tickbox":"0","date_published":"2024-08-10T00:00:00Z","tmp":{"legal_code_url":"https://creativecommons.org/licenses/by-nc/4.0/legalcode","image":"/images/cc_by_nc.png","short":"CC BY-NC (4.0)","name":"Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)"},"related_material":{"record":[{"id":"23043","relation":"later_version","status":"public"},{"id":"18642","relation":"dissertation_contains","status":"public"}]},"corr_author":"1","day":"10","user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","project":[{"name":"Improving estimation and prediction of common complex disease risk","grant_number":"PCEGP3_181181","_id":"9B8D11D6-BA93-11EA-9121-9846C619BF3A"},{"_id":"bd936e6f-d553-11ed-ba76-a82299f63e8c","grant_number":"590359","name":"Advanced statistical modelling to facilitate more accurate characterisation of disease phenotypes, improved genetic mapping, and effective therapeutic hypothesis generation"}],"publication_status":"published","article_processing_charge":"No","supplementarymaterial":"yes","citation":{"short":"N.N. Machnik, S.M. Mahmoudi, M. Borczyk, I. Krätschmer, M.J. Bauer, M.R. Robinson, BioRxiv (2024).","chicago":"Machnik, Nick N, Seyed Mahdi Mahmoudi, Malgorzata Borczyk, Ilse Krätschmer, Markus J. Bauer, and Matthew Richard Robinson. “Causal Inference for Multiple Risk Factors and Diseases from Genomics Data.” <i>BioRxiv</i>, 2024. <a href=\"https://doi.org/10.1101/2023.12.06.570392\">https://doi.org/10.1101/2023.12.06.570392</a>.","ama":"Machnik NN, Mahmoudi SM, Borczyk M, Krätschmer I, Bauer MJ, Robinson MR. Causal inference for multiple risk factors and diseases from genomics data. <i>bioRxiv</i>. 2024. doi:<a href=\"https://doi.org/10.1101/2023.12.06.570392\">10.1101/2023.12.06.570392</a>","apa":"Machnik, N. N., Mahmoudi, S. M., Borczyk, M., Krätschmer, I., Bauer, M. J., &#38; Robinson, M. R. (2024). Causal inference for multiple risk factors and diseases from genomics data. <i>bioRxiv</i>. <a href=\"https://doi.org/10.1101/2023.12.06.570392\">https://doi.org/10.1101/2023.12.06.570392</a>","ieee":"N. N. Machnik, S. M. Mahmoudi, M. Borczyk, I. Krätschmer, M. J. Bauer, and M. R. Robinson, “Causal inference for multiple risk factors and diseases from genomics data,” <i>bioRxiv</i>. 2024.","mla":"Machnik, Nick N., et al. “Causal Inference for Multiple Risk Factors and Diseases from Genomics Data.” <i>BioRxiv</i>, 2024, doi:<a href=\"https://doi.org/10.1101/2023.12.06.570392\">10.1101/2023.12.06.570392</a>.","ista":"Machnik NN, Mahmoudi SM, Borczyk M, Krätschmer I, Bauer MJ, Robinson MR. 2024. Causal inference for multiple risk factors and diseases from genomics data. bioRxiv, <a href=\"https://doi.org/10.1101/2023.12.06.570392\">10.1101/2023.12.06.570392</a>."},"OA_place":"repository","researchdata_availability":"not applicable","doi":"10.1101/2023.12.06.570392","oa_version":"Preprint","type":"preprint","author":[{"id":"3591A0AA-F248-11E8-B48F-1D18A9856A87","full_name":"Machnik, Nick N","first_name":"Nick N","last_name":"Machnik","orcid":"0000-0001-6617-9742"},{"id":"b9f6d5ef-7774-11eb-a47f-df2c75c02ee7","full_name":"Mahmoudi, Seyed Mahdi","first_name":"Seyed Mahdi","last_name":"Mahmoudi"},{"last_name":"Borczyk","full_name":"Borczyk, Malgorzata","first_name":"Malgorzata"},{"full_name":"Krätschmer, Ilse","first_name":"Ilse","last_name":"Krätschmer","orcid":"0000-0002-5636-9259","id":"30d4014e-7753-11eb-b44b-db6d61112e73"},{"last_name":"Bauer","full_name":"Bauer, Markus J.","first_name":"Markus J."},{"first_name":"Matthew Richard","full_name":"Robinson, Matthew Richard","orcid":"0000-0001-8982-8813","last_name":"Robinson","id":"E5D42276-F5DA-11E9-8E24-6303E6697425"}]},{"publication_status":"published","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","volume":15,"citation":{"mla":"Bernabeu, Elena, et al. “Refining Epigenetic Prediction of Chronological and Biological Age.” <i>Genome Medicine</i>, vol. 15, 12, Springer Nature, 2023, doi:<a href=\"https://doi.org/10.1186/s13073-023-01161-y\">10.1186/s13073-023-01161-y</a>.","ista":"Bernabeu E, Mccartney DL, Gadd DA, Hillary RF, Lu AT, Murphy L, Wrobel N, Campbell A, Harris SE, Liewald D, Hayward C, Sudlow C, Cox SR, Evans KL, Horvath S, Mcintosh AM, Robinson MR, Vallejos CA, Marioni RE. 2023. Refining epigenetic prediction of chronological and biological age. Genome Medicine. 15, 12.","chicago":"Bernabeu, Elena, Daniel L. Mccartney, Danni A. Gadd, Robert F. Hillary, Ake T. Lu, Lee Murphy, Nicola Wrobel, et al. “Refining Epigenetic Prediction of Chronological and Biological Age.” <i>Genome Medicine</i>. Springer Nature, 2023. <a href=\"https://doi.org/10.1186/s13073-023-01161-y\">https://doi.org/10.1186/s13073-023-01161-y</a>.","short":"E. Bernabeu, D.L. Mccartney, D.A. Gadd, R.F. Hillary, A.T. Lu, L. Murphy, N. Wrobel, A. Campbell, S.E. Harris, D. Liewald, C. Hayward, C. Sudlow, S.R. Cox, K.L. Evans, S. Horvath, A.M. Mcintosh, M.R. Robinson, C.A. Vallejos, R.E. Marioni, Genome Medicine 15 (2023).","apa":"Bernabeu, E., Mccartney, D. L., Gadd, D. A., Hillary, R. F., Lu, A. T., Murphy, L., … Marioni, R. E. (2023). Refining epigenetic prediction of chronological and biological age. <i>Genome Medicine</i>. Springer Nature. <a href=\"https://doi.org/10.1186/s13073-023-01161-y\">https://doi.org/10.1186/s13073-023-01161-y</a>","ama":"Bernabeu E, Mccartney DL, Gadd DA, et al. Refining epigenetic prediction of chronological and biological age. <i>Genome Medicine</i>. 2023;15. doi:<a href=\"https://doi.org/10.1186/s13073-023-01161-y\">10.1186/s13073-023-01161-y</a>","ieee":"E. Bernabeu <i>et al.</i>, “Refining epigenetic prediction of chronological and biological age,” <i>Genome Medicine</i>, vol. 15. Springer Nature, 2023."},"ddc":["570"],"article_processing_charge":"No","oa_version":"Published Version","doi":"10.1186/s13073-023-01161-y","intvolume":"        15","author":[{"last_name":"Bernabeu","first_name":"Elena","full_name":"Bernabeu, Elena"},{"full_name":"Mccartney, Daniel L.","first_name":"Daniel L.","last_name":"Mccartney"},{"full_name":"Gadd, Danni A.","first_name":"Danni A.","last_name":"Gadd"},{"first_name":"Robert F.","full_name":"Hillary, Robert F.","last_name":"Hillary"},{"last_name":"Lu","full_name":"Lu, Ake T.","first_name":"Ake T."},{"full_name":"Murphy, Lee","first_name":"Lee","last_name":"Murphy"},{"full_name":"Wrobel, Nicola","first_name":"Nicola","last_name":"Wrobel"},{"last_name":"Campbell","first_name":"Archie","full_name":"Campbell, Archie"},{"full_name":"Harris, Sarah E.","first_name":"Sarah E.","last_name":"Harris"},{"last_name":"Liewald","full_name":"Liewald, David","first_name":"David"},{"full_name":"Hayward, Caroline","first_name":"Caroline","last_name":"Hayward"},{"last_name":"Sudlow","first_name":"Cathie","full_name":"Sudlow, Cathie"},{"last_name":"Cox","full_name":"Cox, Simon R.","first_name":"Simon R."},{"full_name":"Evans, Kathryn L.","first_name":"Kathryn L.","last_name":"Evans"},{"first_name":"Steve","full_name":"Horvath, Steve","last_name":"Horvath"},{"full_name":"Mcintosh, Andrew M.","first_name":"Andrew M.","last_name":"Mcintosh"},{"id":"E5D42276-F5DA-11E9-8E24-6303E6697425","orcid":"0000-0001-8982-8813","last_name":"Robinson","first_name":"Matthew Richard","full_name":"Robinson, Matthew Richard"},{"last_name":"Vallejos","full_name":"Vallejos, Catalina A.","first_name":"Catalina A."},{"full_name":"Marioni, Riccardo E.","first_name":"Riccardo E.","last_name":"Marioni"}],"external_id":{"pmid":["36855161"],"isi":["000940286600001"]},"scopus_import":"1","file":[{"file_id":"12722","access_level":"open_access","relation":"main_file","creator":"cchlebak","checksum":"833b837910c4db42fb5f0f34125f77a7","file_name":"2023_GenomeMed_Bernabeu.pdf","date_created":"2023-03-14T10:29:47Z","date_updated":"2023-03-14T10:29:47Z","content_type":"application/pdf","file_size":4275987,"success":1}],"type":"journal_article","date_created":"2023-03-12T23:01:02Z","publication":"Genome Medicine","abstract":[{"lang":"eng","text":"Background\r\nEpigenetic clocks can track both chronological age (cAge) and biological age (bAge). The latter is typically defined by physiological biomarkers and risk of adverse health outcomes, including all-cause mortality. As cohort sample sizes increase, estimates of cAge and bAge become more precise. Here, we aim to develop accurate epigenetic predictors of cAge and bAge, whilst improving our understanding of their epigenomic architecture.\r\n\r\nMethods\r\nFirst, we perform large-scale (N = 18,413) epigenome-wide association studies (EWAS) of chronological age and all-cause mortality. Next, to create a cAge predictor, we use methylation data from 24,674 participants from the Generation Scotland study, the Lothian Birth Cohorts (LBC) of 1921 and 1936, and 8 other cohorts with publicly available data. In addition, we train a predictor of time to all-cause mortality as a proxy for bAge using the Generation Scotland cohort (1214 observed deaths). For this purpose, we use epigenetic surrogates (EpiScores) for 109 plasma proteins and the 8 component parts of GrimAge, one of the current best epigenetic predictors of survival. We test this bAge predictor in four external cohorts (LBC1921, LBC1936, the Framingham Heart Study and the Women’s Health Initiative study).\r\n\r\nResults\r\nThrough the inclusion of linear and non-linear age-CpG associations from the EWAS, feature pre-selection in advance of elastic net regression, and a leave-one-cohort-out (LOCO) cross-validation framework, we obtain cAge prediction with a median absolute error equal to 2.3 years. Our bAge predictor was found to slightly outperform GrimAge in terms of the strength of its association to survival (HRGrimAge = 1.47 [1.40, 1.54] with p = 1.08 × 10−52, and HRbAge = 1.52 [1.44, 1.59] with p = 2.20 × 10−60). Finally, we introduce MethylBrowsR, an online tool to visualise epigenome-wide CpG-age associations.\r\n\r\nConclusions\r\nThe integration of multiple large datasets, EpiScores, non-linear DNAm effects, and new approaches to feature selection has facilitated improvements to the blood-based epigenetic prediction of biological and chronological age."}],"language":[{"iso":"eng"}],"status":"public","acknowledgement":"We are grateful to all the families who took part, the general practitioners, and the Scottish School of Primary Care for their help in recruiting them and the whole GS team that includes interviewers, computer and laboratory technicians, clerical workers, research scientists, volunteers, managers, receptionists, healthcare assistants, and nurses.","file_date_updated":"2023-03-14T10:29:47Z","date_published":"2023-02-28T00:00:00Z","day":"28","tmp":{"legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","short":"CC BY (4.0)","image":"/images/cc_by.png","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)"},"year":"2023","publication_identifier":{"eissn":["1756-994X"]},"publisher":"Springer Nature","fulldoi":"https://doi.org/10.1186/s13073-023-01161-y","department":[{"_id":"MaRo"}],"quality_controlled":"1","_id":"12719","date_updated":"2025-04-23T08:49:38Z","article_number":"12","month":"02","article_type":"original","pmid":1,"has_accepted_license":"1","oa":1,"title":"Refining epigenetic prediction of chronological and biological age","isi":1},{"oa":1,"has_accepted_license":"1","pmid":1,"article_type":"original","month":"03","title":"Using AlphaFold to predict the impact of single mutations on protein stability and function","isi":1,"_id":"12758","article_number":"e0282689","date_updated":"2025-04-23T08:50:30Z","fulldoi":"https://doi.org/10.1371/journal.pone.0282689","publisher":"Public Library of Science","year":"2023","publication_identifier":{"eissn":["1932-6203"]},"quality_controlled":"1","department":[{"_id":"FyKo"},{"_id":"MaRo"}],"date_published":"2023-03-16T00:00:00Z","file_date_updated":"2023-03-27T07:09:08Z","tmp":{"legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","short":"CC BY (4.0)","image":"/images/cc_by.png","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)"},"day":"16","date_created":"2023-03-26T22:01:07Z","language":[{"iso":"eng"}],"status":"public","acknowledgement":"The authors acknowledge the use of Zhores supercomputer [28] for obtaining the results presented in this paper.The authors thank Zimin Foundation and Petrovax for support of the presented study at the School of Molecular and Theoretical Biology 2021.","abstract":[{"lang":"eng","text":"AlphaFold changed the field of structural biology by achieving three-dimensional (3D) structure prediction from protein sequence at experimental quality. The astounding success even led to claims that the protein folding problem is “solved”. However, protein folding problem is more than just structure prediction from sequence. Presently, it is unknown if the AlphaFold-triggered revolution could help to solve other problems related to protein folding. Here we assay the ability of AlphaFold to predict the impact of single mutations on protein stability (ΔΔG) and function. To study the question we extracted the pLDDT and <pLDDT> metrics from AlphaFold predictions before and after single mutation in a protein and correlated the predicted change with the experimentally known ΔΔG values. Additionally, we correlated the same AlphaFold pLDDT metrics with the impact of a single mutation on structure using a large scale dataset of single mutations in GFP with the experimentally assayed levels of fluorescence. We found a very weak or no correlation between AlphaFold output metrics and change of protein stability or fluorescence. Our results imply that AlphaFold may not be immediately applied to other problems or applications in protein folding."}],"publication":"PLoS ONE","intvolume":"        18","doi":"10.1371/journal.pone.0282689","oa_version":"Published Version","type":"journal_article","scopus_import":"1","file":[{"file_id":"12771","access_level":"open_access","relation":"main_file","creator":"dernst","checksum":"0281bdfccf8d76c4e08dd011c603f6b6","file_name":"2023_PLoSOne_Pak.pdf","date_created":"2023-03-27T07:09:08Z","content_type":"application/pdf","date_updated":"2023-03-27T07:09:08Z","file_size":856625,"success":1}],"external_id":{"isi":["000985134400106"],"pmid":["36928239"]},"author":[{"full_name":"Pak, Marina A.","first_name":"Marina A.","last_name":"Pak"},{"last_name":"Markhieva","full_name":"Markhieva, Karina A.","first_name":"Karina A."},{"last_name":"Novikova","first_name":"Mariia S.","full_name":"Novikova, Mariia S."},{"last_name":"Petrov","full_name":"Petrov, Dmitry S.","first_name":"Dmitry S."},{"last_name":"Vorobyev","first_name":"Ilya S.","full_name":"Vorobyev, Ilya S."},{"first_name":"Ekaterina","full_name":"Maksimova, Ekaterina","last_name":"Maksimova","id":"2FBE0DE4-F248-11E8-B48F-1D18A9856A87"},{"id":"44FDEF62-F248-11E8-B48F-1D18A9856A87","full_name":"Kondrashov, Fyodor","first_name":"Fyodor","last_name":"Kondrashov","orcid":"0000-0001-8243-4694"},{"first_name":"Dmitry N.","full_name":"Ivankov, Dmitry N.","last_name":"Ivankov"}],"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","publication_status":"published","issue":"3","article_processing_charge":"No","citation":{"short":"M.A. Pak, K.A. Markhieva, M.S. Novikova, D.S. Petrov, I.S. Vorobyev, E. Maksimova, F. Kondrashov, D.N. Ivankov, PLoS ONE 18 (2023).","chicago":"Pak, Marina A., Karina A. Markhieva, Mariia S. Novikova, Dmitry S. Petrov, Ilya S. Vorobyev, Ekaterina Maksimova, Fyodor Kondrashov, and Dmitry N. Ivankov. “Using AlphaFold to Predict the Impact of Single Mutations on Protein Stability and Function.” <i>PLoS ONE</i>. Public Library of Science, 2023. <a href=\"https://doi.org/10.1371/journal.pone.0282689\">https://doi.org/10.1371/journal.pone.0282689</a>.","apa":"Pak, M. A., Markhieva, K. A., Novikova, M. S., Petrov, D. S., Vorobyev, I. S., Maksimova, E., … Ivankov, D. N. (2023). Using AlphaFold to predict the impact of single mutations on protein stability and function. <i>PLoS ONE</i>. Public Library of Science. <a href=\"https://doi.org/10.1371/journal.pone.0282689\">https://doi.org/10.1371/journal.pone.0282689</a>","ama":"Pak MA, Markhieva KA, Novikova MS, et al. Using AlphaFold to predict the impact of single mutations on protein stability and function. <i>PLoS ONE</i>. 2023;18(3). doi:<a href=\"https://doi.org/10.1371/journal.pone.0282689\">10.1371/journal.pone.0282689</a>","ieee":"M. A. Pak <i>et al.</i>, “Using AlphaFold to predict the impact of single mutations on protein stability and function,” <i>PLoS ONE</i>, vol. 18, no. 3. Public Library of Science, 2023.","mla":"Pak, Marina A., et al. “Using AlphaFold to Predict the Impact of Single Mutations on Protein Stability and Function.” <i>PLoS ONE</i>, vol. 18, no. 3, e0282689, Public Library of Science, 2023, doi:<a href=\"https://doi.org/10.1371/journal.pone.0282689\">10.1371/journal.pone.0282689</a>.","ista":"Pak MA, Markhieva KA, Novikova MS, Petrov DS, Vorobyev IS, Maksimova E, Kondrashov F, Ivankov DN. 2023. Using AlphaFold to predict the impact of single mutations on protein stability and function. PLoS ONE. 18(3), e0282689."},"ddc":["570"],"volume":18}]
