Cross-Platform Omics Prediction procedure: a statistical machine learning framework for wider implementation of precision medicine.
Journal
NPJ digital medicine
ISSN: 2398-6352
Titre abrégé: NPJ Digit Med
Pays: England
ID NLM: 101731738
Informations de publication
Date de publication:
04 Jul 2022
04 Jul 2022
Historique:
received:
10
11
2021
accepted:
19
05
2022
entrez:
5
7
2022
pubmed:
6
7
2022
medline:
6
7
2022
Statut:
epublish
Résumé
In this modern era of precision medicine, molecular signatures identified from advanced omics technologies hold great promise to better guide clinical decisions. However, current approaches are often location-specific due to the inherent differences between platforms and across multiple centres, thus limiting the transferability of molecular signatures. We present Cross-Platform Omics Prediction (CPOP), a penalised regression model that can use omics data to predict patient outcomes in a platform-independent manner and across time and experiments. CPOP improves on the traditional prediction framework of using gene-based features by selecting ratio-based features with similar estimated effect sizes. These components gave CPOP the ability to have a stable performance across datasets of similar biology, minimising the effect of technical noise often generated by omics platforms. We present a comprehensive evaluation using melanoma transcriptomics data to demonstrate its potential to be used as a critical part of a clinical screening framework for precision medicine. Additional assessment of generalisation was demonstrated with ovarian cancer and inflammatory bowel disease studies.
Identifiants
pubmed: 35788693
doi: 10.1038/s41746-022-00618-5
pii: 10.1038/s41746-022-00618-5
pmc: PMC9253123
doi:
Types de publication
Journal Article
Langues
eng
Pagination
85Informations de copyright
© 2022. The Author(s).
Références
Clin Cancer Res. 2012 Mar 1;18(5):1374-85
pubmed: 22241791
Biostatistics. 2007 Jan;8(1):118-27
pubmed: 16632515
Cancer Res. 2009 Apr 1;69(7):3077-85
pubmed: 19293190
Nucleic Acids Res. 2015 Apr 20;43(7):e47
pubmed: 25605792
Melanoma Res. 2019 Jun;29(3):342-344
pubmed: 31026248
Cell. 2015 Jun 18;161(7):1681-96
pubmed: 26091043
Am J Pathol. 2019 Oct;189(10):2102-2114
pubmed: 31369756
Am J Clin Dermatol. 2019 Dec;20(6):763-770
pubmed: 31359351
Eur J Cancer. 2021 Jan;143:11-18
pubmed: 33278769
J Natl Cancer Inst. 2014 Apr 03;106(5):
pubmed: 24700801
BMC Med. 2013 Oct 17;11:220
pubmed: 24228635
Trends Genet. 2003 Jul;19(7):362-5
pubmed: 12850439
Nat Commun. 2021 Feb 18;12(1):1137
pubmed: 33602918
J Stat Softw. 2010;33(1):1-22
pubmed: 20808728
Int J Cancer. 2015 Feb 15;136(4):863-74
pubmed: 24975271
Sci Rep. 2020 May 12;10(1):7876
pubmed: 32398793
Bioinformatics. 2017 Jan 15;33(2):219-226
pubmed: 27634945
Br J Cancer. 2013 Oct 29;109(9):2412-23
pubmed: 24129241
J Invest Dermatol. 2013 Feb;133(2):509-17
pubmed: 22931913
Front Oncol. 2021 Apr 22;11:561763
pubmed: 33968711
Oncotarget. 2015 May 20;6(14):12297-309
pubmed: 25909218
Bioinformatics. 2015 Jun 1;31(11):1851-3
pubmed: 25644269
JAMA Dermatol. 2020 Sep 1;156(9):1004-1011
pubmed: 32725204
Bioinformatics. 2017 Jul 15;33(14):i333-i340
pubmed: 28881975
Eur J Cancer. 2020 Jan;125:38-45
pubmed: 31838403
Oncotarget. 2015 Oct 6;6(30):29111-28
pubmed: 26320180
J Am Acad Dermatol. 2020 Sep;83(3):745-753
pubmed: 32229276
JCI Insight. 2016 Aug 18;1(13):e87899
pubmed: 27668286
Cancers (Basel). 2020 Aug 10;12(8):
pubmed: 32785074
Clin Cancer Res. 2008 Aug 15;14(16):5198-208
pubmed: 18698038