GenNet framework: interpretable deep learning for predicting phenotypes from genetic data.
Journal
Communications biology
ISSN: 2399-3642
Titre abrégé: Commun Biol
Pays: England
ID NLM: 101719179
Informations de publication
Date de publication:
17 09 2021
17 09 2021
Historique:
received:
04
02
2021
accepted:
26
08
2021
entrez:
18
9
2021
pubmed:
19
9
2021
medline:
15
12
2021
Statut:
epublish
Résumé
Applying deep learning in population genomics is challenging because of computational issues and lack of interpretable models. Here, we propose GenNet, a novel open-source deep learning framework for predicting phenotypes from genetic variants. In this framework, interpretable and memory-efficient neural network architectures are constructed by embedding biologically knowledge from public databases, resulting in neural networks that contain only biologically plausible connections. We applied the framework to seventeen phenotypes and found well-replicated genes such as HERC2 and OCA2 for hair and eye color, and novel genes such as ZNF773 and PCNT for schizophrenia. Additionally, the framework identified ubiquitin mediated proteolysis, endocrine system and viral infectious diseases as most predictive biological pathways for schizophrenia. GenNet is a freely available, end-to-end deep learning framework that allows researchers to develop and use interpretable neural networks to obtain novel insights into the genetic architecture of complex traits and diseases.
Identifiants
pubmed: 34535759
doi: 10.1038/s42003-021-02622-z
pii: 10.1038/s42003-021-02622-z
pmc: PMC8448759
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
1094Informations de copyright
© 2021. The Author(s).
Références
Nucleic Acids Res. 2014 Jan;42(Database issue):D472-7
pubmed: 24243840
Hum Mol Genet. 2018 Oct 15;27(20):3641-3649
pubmed: 30124842
Curr Opin Syst Biol. 2019 Jun;15:68-73
pubmed: 31777764
Bioinformatics. 2012 Jul 1;28(13):1797-9
pubmed: 22513993
Nature. 2014 Jul 24;511(7510):421-7
pubmed: 25056061
Nucleic Acids Res. 2018 Jan 4;46(D1):D794-D801
pubmed: 29126249
Nat Genet. 2013 Jun;45(6):580-5
pubmed: 23715323
Nat Methods. 2018 Apr;15(4):290-298
pubmed: 29505029
Med Image Anal. 2017 Dec;42:60-88
pubmed: 28778026
Nucleic Acids Res. 2000 Jan 1;28(1):27-30
pubmed: 10592173
Nature. 2020 Oct;586(7831):749-756
pubmed: 33087929
Nat Genet. 2020 Dec;52(12):1346-1354
pubmed: 33257898
PLoS Genet. 2008 May 16;4(5):e1000074
pubmed: 18483556
Nat Genet. 2018 May;50(5):652-656
pubmed: 29662168
Genome Res. 2012 Mar;22(3):446-55
pubmed: 22234890
PLoS Comput Biol. 2015 Apr 17;11(4):e1004219
pubmed: 25885710
Curr Biol. 2009 Mar 10;19(5):R192-3
pubmed: 19278628
Nucleic Acids Res. 2007 Jan;35(Database issue):D61-5
pubmed: 17130148
PLoS One. 2012;7(10):e48294
pubmed: 23118974
Schizophr Bull. 2009 May;35(3):528-48
pubmed: 19223657
Am J Hum Genet. 2008 Feb;82(2):411-23
pubmed: 18252221
Cell. 2018 Jun 14;173(7):1562-1565
pubmed: 29906441
EBioMedicine. 2019 Apr;42:188-202
pubmed: 30922963
Nature. 2014 Feb 13;506(7487):185-90
pubmed: 24463508
Sci Rep. 2016 Oct 26;6:36076
pubmed: 27782180
Nucleic Acids Res. 2010 Sep;38(16):e164
pubmed: 20601685
Am J Hum Genet. 2018 May 3;102(5):717-730
pubmed: 29727686
Science. 2018 Dec 14;362(6420):
pubmed: 30545857
Nature. 2018 Oct;562(7726):203-209
pubmed: 30305743
J Alzheimers Dis. 2016 Nov 19;55(2):473-484
pubmed: 27662287
Nat Genet. 2019 May;51(5):793-803
pubmed: 31043756
J Hum Genet. 2021 Apr;66(4):359-369
pubmed: 33009504
Neuropharmacology. 2012 Mar;62(3):1230-41
pubmed: 21195721
Am J Hum Genet. 2009 Jul;85(1):13-24
pubmed: 19539887
BMC Bioinformatics. 2016 Sep 13;17(1):365
pubmed: 27618934
Nat Genet. 2018 Apr;50(4):621-629
pubmed: 29632380
Eur J Epidemiol. 2020 May;35(5):483-517
pubmed: 32367290