Show simple item record

dc.contributor.authorCheng, Y
dc.contributor.authorGadd, DA
dc.contributor.authorGieger, C
dc.contributor.authorMonterrubio-Gómez, K
dc.contributor.authorZhang, Y
dc.contributor.authorBerta, I
dc.contributor.authorStam, MJ
dc.contributor.authorSzlachetka, N
dc.contributor.authorLobzaev, E
dc.contributor.authorWrobel, N
dc.contributor.authorMurphy, L
dc.contributor.authorCampell, A
dc.contributor.authorNangle, C
dc.contributor.authorWalker, RM
dc.contributor.authorFawns-Ritchie, C
dc.contributor.authorPeters, A
dc.contributor.authorRathmann, W
dc.contributor.authorPorteous, DJ
dc.contributor.authorEvans, KL
dc.contributor.authorMcIntosh, AM
dc.contributor.authorCannings, TI
dc.contributor.authorWaldenberger, M
dc.contributor.authorGanna, A
dc.contributor.authorMcCartney, DL
dc.contributor.authorVallejos, CA
dc.contributor.authorMarioni, RE
dc.date.accessioned2023-03-29T09:56:13Z
dc.date.issued2023-04-06
dc.date.updated2023-03-29T09:23:31Z
dc.description.abstractType 2 diabetes mellitus (T2D) presents a major health and economic burden that could be alleviated with improved early prediction and intervention. While standard risk factors have shown good predictive performance, we show that the use of blood-based DNA methylation information leads to a significant improvement in the prediction of 10-year T2D incidence risk. Previous studies have been largely constrained by linear assumptions, the use of CpGs one-at43 a-time, and binary outcomes. We present a flexible approach (via an R package, MethylPipeR) based on a range of linear and tree-ensemble models that incorporate time-to-event data for prediction. Using the Generation Scotland cohort (training set ncases=374, ncontrols=9,461; test set ncases=252, ncontrols=4,526) our best-performing model (Area Under the Curve (AUC)=0.872, Precision Recall AUC (PRAUC)=0.302) showed notable improvement in 10-year onset prediction beyond standard risk factors (AUC=0.839, PRAUC=0.227). Replication was observed in the German-based KORA study (n=1,451, ncases = 142, p=1.6x10-5 49 ).en_GB
dc.description.sponsorshipWellcome Trusten_GB
dc.description.sponsorshipChief Scientist Office of the Scottish Government Health Directoratesen_GB
dc.description.sponsorshipScottish Funding Councilen_GB
dc.description.sponsorshipBrain & Behavior Research Foundation
dc.description.sponsorshipRoyal College of Physicians of Edinburgh
dc.description.sponsorshipUniversity of Edinburgh
dc.description.sponsorshipUniversity of Helsinki
dc.description.sponsorshipAlzheimer’s Research UK
dc.description.sponsorshipUKRI
dc.identifier.citationVol. 3, pp. 450–458en_GB
dc.identifier.doi10.1038/s43587-023-00391-4
dc.identifier.grantnumber104036/Z/14/Zen_GB
dc.identifier.grantnumber108890/Z/15/Zen_GB
dc.identifier.grantnumber216767/Z/19/Zen_GB
dc.identifier.grantnumberCZD/16/6en_GB
dc.identifier.grantnumberHR03006en_GB
dc.identifier.grantnumber27404
dc.identifier.grantnumber108890/Z/15/Z
dc.identifier.grantnumberARUK-PG2017B-10
dc.identifier.grantnumberAS-PG-19b-010
dc.identifier.grantnumberEP/S02431X/1
dc.identifier.urihttp://hdl.handle.net/10871/132801
dc.identifierORCID: 0000-0002-1060-4479 (Walker, Rosie May)
dc.language.isoenen_GB
dc.publisherNature Researchen_GB
dc.relation.urlhttps://epi.helmholtz-muenchen.de/en_GB
dc.relation.urlhttps://github.com/marioni-group/episcores-diabetes-prediction
dc.relation.urlhttps://doi.org/10.5281/zenodo.7628959
dc.relation.urlhttps://github.com/marioni-group/MethylPipeR
dc.relation.urlhttps://doi.org/10.5281/zenodo.7628816
dc.relation.urlhttps://github.com/marioni-group/MethylPipeR-UI
dc.relation.urlhttps://doi.org/10.5281/zenodo.7635952
dc.rights© The Author(s), under exclusive licence to Springer Nature America, Inc. 2023. This research was funded in whole, or in part, by the Wellcome Trust [104036/Z/14/Z, 108890/Z/15/Z, 216767/Z/19/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.
dc.titleDevelopment and validation of DNA methylation scores in two European cohorts augment 10-year risk prediction of type 2 diabetesen_GB
dc.typeArticleen_GB
dc.date.available2023-03-29T09:56:13Z
dc.identifier.issn2662-8465
dc.descriptionThis is the author accepted manuscript. The final version is available from Nature Research via the DOI in this recorden_GB
dc.descriptionData availability: According to the terms of consent for Generation Scotland participants, access to data must be reviewed by the Generation Scotland Access Committee. Applications should be made to access@generationscotland.org. The informed consent given by the KORA S4 study participants does not cover data posting in public databases. However, data are available upon request from the KORA Project Application Self-Service Tool (https://epi.helmholtz-muenchen.de/). Data requests can be submitted online and are subject to approval by the KORA board.en_GB
dc.descriptionCode availability: Analysis scripts for this study are available at https://github.com/marioni-group/episcores-diabetes-prediction and https://doi.org/10.5281/zenodo.7628959. MethylPipeR v.0.1.0 is available at https://github.com/marioni-group/MethylPipeR and https://doi.org/10.5281/zenodo.7628816. MethylPipeR-UI is available at https://github.com/marioni-group/MethylPipeR-UI and https://doi.org/10.5281/zenodo.7635952.
dc.identifier.journalNature Agingen_GB
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/en_GB
dcterms.dateAccepted2023-02-27
dcterms.dateSubmitted2021-11-19
rioxxterms.versionAMen_GB
rioxxterms.licenseref.startdate2023-01-06
rioxxterms.typeJournal Article/Reviewen_GB
refterms.dateFCD2023-03-29T09:23:40Z
refterms.versionFCDAM
refterms.dateFOA2023-07-27T14:30:09Z
refterms.panelAen_GB


Files in this item

This item appears in the following Collection(s)

Show simple item record

© The Author(s), under exclusive licence to Springer Nature America, 
Inc. 2023. This research was funded in whole, or in part, by the Wellcome Trust [104036/Z/14/Z, 108890/Z/15/Z, 216767/Z/19/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.
Except where otherwise noted, this item's licence is described as © The Author(s), under exclusive licence to Springer Nature America, Inc. 2023. This research was funded in whole, or in part, by the Wellcome Trust [104036/Z/14/Z, 108890/Z/15/Z, 216767/Z/19/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.