A graph-embedded topic model enables characterization of diverse pain phenotypes among UK biobank individuals.

bioinformatics general medicine health sciences medical informatics

Journal

iScience
ISSN: 2589-0042
Titre abrégé: iScience
Pays: United States
ID NLM: 101724038

Informations de publication

Date de publication:
17 Jun 2022
Historique:
received: 25 02 2022
revised: 08 04 2022
accepted: 06 05 2022
entrez: 31 5 2022
pubmed: 1 6 2022
medline: 1 6 2022
Statut: epublish

Résumé

Large biobank repositories of clinical conditions and medications data open opportunities to investigate the phenotypic disease network. We present a graph embedded topic model (GETM). We integrate existing biomedical knowledge graph information in the form of pre-trained graph embedding into the embedded topic model. Via a variational autoencoder framework, we infer patient phenotypic mixture by modeling multi-modal discrete patient medical records. We applied GETM to UK Biobank (UKB) self-reported clinical phenotype data, which contains 443 self-reported medical conditions and 802 medications for 457,461 individuals. Compared to existing methods, GETM demonstrates good imputation performance. With a more focused application on characterizing pain phenotypes, we observe that GETM-inferred phenotypes not only accurately predict the status of chronic musculoskeletal (CMK) pain but also reveal known pain-related topics. Intriguingly, medications and conditions in the cardiovascular category are enriched among the most predictive topics of chronic pain.

Identifiants

pubmed: 35637735
doi: 10.1016/j.isci.2022.104390
pii: S2589-0042(22)00661-7
pmc: PMC9142639
doi:

Types de publication

Journal Article

Langues

eng

Pagination

104390

Subventions

Organisme : Medical Research Council
ID : MC_PC_17228
Pays : United Kingdom
Organisme : Medical Research Council
ID : MC_QA137853
Pays : United Kingdom

Informations de copyright

© 2022 The Author(s).

Déclaration de conflit d'intérêts

The authors declare no competing interests.

Références

Pain. 2020 Aug;161(8):1755-1767
pubmed: 32701836
Neurosci Biobehav Rev. 2004 Jul;28(4):395-414
pubmed: 15341037
BMC Med. 2020 Sep 29;18(1):308
pubmed: 32988400
Nat Rev Immunol. 2019 Jul;19(7):433-447
pubmed: 30874629
Postgrad Med. 2021 Apr;133(3):345-350
pubmed: 33317375
J Hypertens. 2020 Aug;38(8):1420-1435
pubmed: 32687269
KDD. 2016 Aug;2016:855-864
pubmed: 27853626
PLoS One. 2019 Mar 20;14(3):e0212785
pubmed: 30893319
Biol Sex Differ. 2021 Feb 10;12(1):22
pubmed: 33568220
J Pain Res. 2016 Jun 28;9:457-67
pubmed: 27418853
BMJ Open. 2016 Jun 20;6(6):e010364
pubmed: 27324708
Cochrane Database Syst Rev. 2008 Oct 08;(4):CD003823
pubmed: 18843651
Pharmacol Biochem Behav. 2020 Feb;189:172842
pubmed: 31899220
Pain Med. 2020 Jun 1;21(6):1106-1121
pubmed: 31591645
J Allergy Clin Immunol Pract. 2019 Jan;7(1):279-285.e6
pubmed: 30053594
Nat Commun. 2020 May 21;11(1):2536
pubmed: 32439869
Hypertension. 1996 Sep;28(3):494-504
pubmed: 8794839
Pharmacogenet Genomics. 2010 Apr;20(4):239-48
pubmed: 20216107
Nature. 2018 Oct;562(7726):203-209
pubmed: 30305743
Nat Rev Genet. 2012 May 02;13(6):395-405
pubmed: 22549152
Anesthesiology. 2019 Apr;130(4):634-650
pubmed: 30418212
BMJ. 2018 Apr 24;361:k1687
pubmed: 29691228
Mol Med. 2017 Nov;23:285-294
pubmed: 28861588
Allergy. 2021 Feb;76(2):483-496
pubmed: 32716553
Scand J Pain. 2016 Oct;13:76-90
pubmed: 28850537

Auteurs

Yuening Wang (Y)

School of Computer Science, McGill University, Canada.

Rodrigo Benavides (R)

Department of Anesthesiology, Centro Nacional de Rehabilitación, San Jose, Costa Rica.

Luda Diatchenko (L)

Department of Anesthesia, McGill University, Canada.
Faculty of Dentistry, McGill University, Canada.
Alan Edwards Centre for Research on Pain, McGill University, Canada.

Audrey V Grant (AV)

Department of Anesthesia, McGill University, Canada.
Faculty of Dentistry, McGill University, Canada.
Alan Edwards Centre for Research on Pain, McGill University, Canada.

Yue Li (Y)

School of Computer Science, McGill University, Canada.

Classifications MeSH