Molecular patterns identify distinct subclasses of myeloid neoplasia.
Journal
Nature communications
ISSN: 2041-1723
Titre abrégé: Nat Commun
Pays: England
ID NLM: 101528555
Informations de publication
Date de publication:
30 05 2023
30 05 2023
Historique:
received:
26
10
2022
accepted:
03
05
2023
medline:
1
6
2023
pubmed:
31
5
2023
entrez:
30
5
2023
Statut:
epublish
Résumé
Genomic mutations drive the pathogenesis of myelodysplastic syndromes and acute myeloid leukemia. While morphological and clinical features have dominated the classical criteria for diagnosis and classification, incorporation of molecular data can illuminate functional pathobiology. Here we show that unsupervised machine learning can identify functional objective molecular clusters, irrespective of anamnestic clinico-morphological features, despite the complexity of the molecular alterations in myeloid neoplasia. Our approach reflects disease evolution, informed classification, prognostication, and molecular interactions. We apply machine learning methods on 3588 patients with myelodysplastic syndromes and secondary acute myeloid leukemia to identify 14 molecularly distinct clusters. Remarkably, our model shows clinical implications in terms of overall survival and response to treatment even after adjusting to the molecular international prognostic scoring system (IPSS-M). In addition, the model is validated on an external cohort of 412 patients. Our subclassification model is available via a web-based open-access resource ( https://drmz.shinyapps.io/mds_latent ).
Identifiants
pubmed: 37253784
doi: 10.1038/s41467-023-38515-4
pii: 10.1038/s41467-023-38515-4
pmc: PMC10229666
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Research Support, N.I.H., Extramural
Langues
eng
Sous-ensembles de citation
IM
Pagination
3136Subventions
Organisme : NHLBI NIH HHS
ID : R01 HL118281
Pays : United States
Organisme : NHLBI NIH HHS
ID : R01 HL123904
Pays : United States
Organisme : NHLBI NIH HHS
ID : R01 HL132071
Pays : United States
Organisme : NHLBI NIH HHS
ID : R35 HL135795
Pays : United States
Informations de copyright
© 2023. The Author(s).
Références
Leukemia. 2018 Dec;32(12):2659-2671
pubmed: 29858584
Nat Genet. 2017 Feb;49(2):204-212
pubmed: 27992414
Blood. 2020 Nov 12;136(20):2249-2262
pubmed: 32961553
Haematologica. 2017 Sep;102(9):1502-1510
pubmed: 28642303
J Clin Oncol. 2021 Apr 10;39(11):1223-1233
pubmed: 33539200
Blood. 2006 Jul 15;108(2):419-25
pubmed: 16609072
Hematology Am Soc Hematol Educ Program. 2021 Dec 10;2021(1):418-427
pubmed: 34889424
Nat Commun. 2019 Nov 26;10(1):5386
pubmed: 31772163
Leukemia. 2015 Jan;29(1):66-75
pubmed: 24935723
J Clin Oncol. 2021 Nov 20;39(33):3737-3746
pubmed: 34406850
Blood. 2013 Dec 12;122(25):4021-34
pubmed: 24136165
Leuk Res. 2018 Aug;71:34-35
pubmed: 29957243
N Engl J Med. 2020 Oct 1;383(14):1358-1374
pubmed: 32997910
Blood. 2011 Oct 27;118(17):4690-3
pubmed: 21868570
Blood Adv. 2019 Oct 8;3(19):2845-2858
pubmed: 31582393
Int J Mol Sci. 2022 Mar 03;23(5):
pubmed: 35269943
Blood. 2012 Sep 20;120(12):2454-65
pubmed: 22740453
IEEE Trans Pattern Anal Mach Intell. 2021 Dec;43(12):4306-4322
pubmed: 32750790
Lancet Haematol. 2020 Jul;7(7):e541-e550
pubmed: 32589980
Nature. 2018 Oct;562(7728):526-531
pubmed: 30333627
Nature. 2011 Sep 11;478(7367):64-9
pubmed: 21909114
Br J Haematol. 2016 Nov;175(3):419-426
pubmed: 27447873
Leuk Res. 2021 Oct;109:106639
pubmed: 34171604
Blood. 2016 May 19;127(20):2391-405
pubmed: 27069254
Leukemia. 2018 Aug;32(8):1751-1761
pubmed: 29795413
Leukemia. 2014 Feb;28(2):241-7
pubmed: 24220272
Cancer Discov. 2022 Mar 1;12(3):836-855
pubmed: 34620690
Blood. 1997 Mar 15;89(6):2079-88
pubmed: 9058730
Blood. 2020 Oct 15;136(16):1851-1862
pubmed: 32573691
Leuk Lymphoma. 2021 May;62(5):1226-1233
pubmed: 33345655