Deep integrative models for large-scale human genomics.
Journal
Nucleic acids research
ISSN: 1362-4962
Titre abrégé: Nucleic Acids Res
Pays: England
ID NLM: 0411011
Informations de publication
Date de publication:
07 07 2023
07 07 2023
Historique:
accepted:
28
04
2023
revised:
18
04
2023
received:
18
03
2022
medline:
10
7
2023
pubmed:
24
5
2023
entrez:
24
5
2023
Statut:
ppublish
Résumé
Polygenic risk scores (PRSs) are expected to play a critical role in precision medicine. Currently, PRS predictors are generally based on linear models using summary statistics, and more recently individual-level data. However, these predictors mainly capture additive relationships and are limited in data modalities they can use. We developed a deep learning framework (EIR) for PRS prediction which includes a model, genome-local-net (GLN), specifically designed for large-scale genomics data. The framework supports multi-task learning, automatic integration of other clinical and biochemical data, and model explainability. When applied to individual-level data from the UK Biobank, the GLN model demonstrated a competitive performance compared to established neural network architectures, particularly for certain traits, showcasing its potential in modeling complex genetic relationships. Furthermore, the GLN model outperformed linear PRS methods for Type 1 Diabetes, likely due to modeling non-additive genetic effects and epistasis. This was supported by our identification of widespread non-additive genetic effects and epistasis in the context of T1D. Finally, we constructed PRS models that integrated genotype, blood, urine, and anthropometric data and found that this improved performance for 93% of the 290 diseases and disorders considered. EIR is available at https://github.com/arnor-sigurdsson/EIR.
Identifiants
pubmed: 37224538
pii: 7177885
doi: 10.1093/nar/gkad373
pmc: PMC10325897
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
e67Investigateurs
Karina Banasik
(K)
Jakob Bay
(J)
Jens Kjærgaard Boldsen
(JK)
Thorsten Brodersen
(T)
Søren Brunak
(S)
Kristoffer Burgdorf
(K)
Mona Ameri Chalmer
(MA)
Maria Didriksen
(M)
Khoa Manh Dinh
(KM)
Joseph Dowsett
(J)
Christian Erikstrup
(C)
Bjarke Feenstra
(B)
Frank Geller
(F)
Daniel Gudbjartsson
(D)
Thomas Folkmann Hansen
(TF)
Lotte Hindhede
(L)
Henrik Hjalgrim
(H)
Rikke Louise Jacobsen
(RL)
Gregor Jemec
(G)
Katrine Kaspersen
(K)
Bertram Dalskov Kjerulff
(BD)
Lisette Kogelman
(L)
Margit Anita Hørup Larsen
(MA)
Ioannis Louloudis
(I)
Agnete Lundgaard
(A)
Susan Mikkelsen
(S)
Christina Mikkelsen
(C)
Kaspar Rene Nielsen
(KR)
Ioanna Nissen
(I)
Mette Nyegaard
(M)
Sisse Rye Ostrowski
(SR)
Ole Birger Pedersen
(OB)
Alexander Pil Henriksen
(AP)
Palle Duun Rohde
(PD)
Klaus Rostgaard
(K)
Michael Schwinn
(M)
Kari Stefansson
(K)
Hreinn Stefónsson
(H)
Erik Sørensen
(E)
Unnur Thorsteinsdóttir
(U)
Lise Wegner Thørner
(LW)
Mie Topholm Bruun
(MT)
Henrik Ullum
(H)
Thomas Werge
(T)
David Westergaard
(D)
Informations de copyright
© The Author(s) 2023. Published by Oxford University Press on behalf of Nucleic Acids Research.
Références
Nat Rev Genet. 2014 Jan;15(1):22-33
pubmed: 24296533
Nature. 2020 May;581(7809):434-443
pubmed: 32461654
Nat Genet. 2015 Jul;47(7):702-9
pubmed: 25985137
Genetics. 2017 Nov;207(3):1135-1145
pubmed: 28893854
BMJ Open. 2019 Jun 9;9(6):e028401
pubmed: 31182452
Nat Genet. 2010 Nov;42(11):985-90
pubmed: 20953190
Nature. 2020 Jan;577(7792):706-710
pubmed: 31942072
Bioinformatics. 2021 Nov 18;37(22):4148-4155
pubmed: 34146108
BMC Genomics. 2012;13 Suppl 7:S2
pubmed: 23281813
Nat Genet. 2015 Aug;47(8):898-905
pubmed: 26168013
Nat Genet. 2015 Sep;47(9):1085-90
pubmed: 26258845
BMC Proc. 2009 Dec 15;3 Suppl 7:S29
pubmed: 20018019
Diabetes. 2004 Dec;53(12):3286-91
pubmed: 15561961
Am J Hum Genet. 2012 Jun 8;90(6):962-72
pubmed: 22633398
Nat Genet. 2015 Mar;47(3):284-90
pubmed: 25642633
Diabetologia. 2008 Apr;51(4):589-96
pubmed: 18292987
Nat Mach Intell. 2020 Jan;2(1):56-67
pubmed: 32607472
Bioinformatics. 2020 Aug 15;36(16):4415-4422
pubmed: 32415966
Am J Hum Genet. 2021 Jun 3;108(6):1001-1011
pubmed: 33964208
Nat Commun. 2019 Jan 23;10(1):390
pubmed: 30674886
Diabetes Care. 2019 Mar;42(3):406-415
pubmed: 30659077
Nat Rev Genet. 2019 Nov;20(11):693-701
pubmed: 31455890
Int J Health Sci (Qassim). 2017 Apr-Jun;11(2):65-71
pubmed: 28539866
Genetics. 2018 Nov;210(3):809-819
pubmed: 30171033
Hum Genet. 2014 May;133(5):547-58
pubmed: 24241240
Commun Biol. 2022 Aug 22;5(1):856
pubmed: 35995843
J R Soc Interface. 2018 Apr;15(141):
pubmed: 29618526
Am J Hum Genet. 2022 Jan 6;109(1):12-23
pubmed: 34995502
Diabetes Care. 2019 Feb;42(2):200-207
pubmed: 30655379
Nat Biotechnol. 2018 Nov;36(10):983-987
pubmed: 30247488
Am J Hum Genet. 2019 Jan 3;104(1):21-34
pubmed: 30554720
Genetics. 2018 Oct;210(2):477-497
pubmed: 30150289
Genes Immun. 2002 Aug;3(5):235-49
pubmed: 12140742
Bioinformatics. 2021 Apr 1;36(22-23):5424-5431
pubmed: 33326037
PLoS Genet. 2015 Apr 07;11(4):e1004969
pubmed: 25849665
Nat Commun. 2019 Nov 8;10(1):5086
pubmed: 31704910
Genome Med. 2020 May 18;12(1):44
pubmed: 32423490
Nat Rev Genet. 2019 Jul;20(7):389-403
pubmed: 30971806
Genome Biol. 2022 Jun 20;23(1):131
pubmed: 35725481
HGG Adv. 2022 Aug 18;3(4):100136
pubmed: 36105883
Nature. 2018 Oct;562(7726):203-209
pubmed: 30305743
J Am Coll Cardiol. 2018 Oct 16;72(16):1883-1893
pubmed: 30309464
IEEE Trans Pattern Anal Mach Intell. 2022 Jul;44(7):3614-3633
pubmed: 33497328
Bioinformatics. 2018 Aug 15;34(16):2781-2787
pubmed: 29617937
Nat Commun. 2019 Apr 16;10(1):1776
pubmed: 30992449
Nat Genet. 2015 Oct;47(10):1107-1113
pubmed: 26343388
Nat Genet. 2022 Mar;54(3):263-273
pubmed: 35256806
Hum Mol Genet. 2019 Nov 21;28(R2):R133-R142
pubmed: 31363735
PLoS Genet. 2008 Feb 29;4(2):e1000008
pubmed: 18454194
Am J Hum Genet. 2007 Sep;81(3):559-75
pubmed: 17701901
PLoS Genet. 2020 Oct 23;16(10):e1009141
pubmed: 33095761
Nat Genet. 2018 Sep;50(9):1219-1224
pubmed: 30104762
Am J Hum Genet. 2015 Oct 1;97(4):576-92
pubmed: 26430803
Mol Psychiatry. 2018 Jan;23(1):6-14
pubmed: 28924187
Nature. 1997 Nov 27;390(6658):395-8
pubmed: 9389477
Nat Biotechnol. 2021 May;39(5):555-560
pubmed: 33398153
Genetics. 1997 Sep;147(1):157-63
pubmed: 9286676
Biol Cybern. 1980;36(4):193-202
pubmed: 7370364
Cell Genom. 2022 Jan 12;2(1):None
pubmed: 35072137
Nature. 2009 Oct 8;461(7265):747-53
pubmed: 19812666
Neural Netw. 2018 Nov;107:3-11
pubmed: 29395652
Nature. 2021 Aug;596(7871):E1-E3
pubmed: 34381229
Nat Rev Genet. 2018 Sep;19(9):581-590
pubmed: 29789686
Nature. 2020 Oct;586(7831):749-756
pubmed: 33087929
Genet Epidemiol. 2017 Sep;41(6):469-480
pubmed: 28480976
Nature. 2021 Feb;590(7845):290-299
pubmed: 33568819
Sci Rep. 2016 Apr 25;6:25014
pubmed: 27109064