Machine learning-based tissue of origin classification for cancer of unknown primary diagnostics using genome-wide mutation features.
Journal
Nature communications
ISSN: 2041-1723
Titre abrégé: Nat Commun
Pays: England
ID NLM: 101528555
Informations de publication
Date de publication:
11 07 2022
11 07 2022
Historique:
received:
13
10
2021
accepted:
23
06
2022
entrez:
11
7
2022
pubmed:
12
7
2022
medline:
14
7
2022
Statut:
epublish
Résumé
Cancers of unknown primary (CUP) origin account for ∼3% of all cancer diagnoses, whereby the tumor tissue of origin (TOO) cannot be determined. Using a uniformly processed dataset encompassing 6756 whole-genome sequenced primary and metastatic tumors, we develop Cancer of Unknown Primary Location Resolver (CUPLR), a random forest TOO classifier that employs 511 features based on simple and complex somatic driver and passenger mutations. CUPLR distinguishes 35 cancer (sub)types with ∼90% recall and ∼90% precision based on cross-validation and test set predictions. We find that structural variant derived features increase the performance and utility for classifying specific cancer types. With CUPLR, we could determine the TOO for 82/141 (58%) of CUP patients. Although CUPLR is based on machine learning, it provides a human interpretable graphical report with detailed feature explanations. The comprehensive output of CUPLR complements existing histopathological procedures and can enable improved diagnostics for CUP patients.
Identifiants
pubmed: 35817764
doi: 10.1038/s41467-022-31666-w
pii: 10.1038/s41467-022-31666-w
pmc: PMC9273599
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
4013Informations de copyright
© 2022. The Author(s).
Références
Cancer Cell. 2018 Apr 9;33(4):676-689.e3
pubmed: 29622463
Appl Immunohistochem Mol Morphol. 2010 Jan;18(1):3-8
pubmed: 19550296
J Mol Diagn. 2021 Jul;23(7):816-833
pubmed: 33964451
Nat Commun. 2021 Jun 15;12(1):3628
pubmed: 34131135
JAMA. 2019 Jan 22;321(3):288-300
pubmed: 30667505
Nat Commun. 2015 Dec 07;6:8866
pubmed: 26638776
Nat Rev Clin Oncol. 2018 Apr;15(4):219-233
pubmed: 29311715
Eur J Cancer. 2010 Jul;46(10):1773-80
pubmed: 20418096
Nature. 2012 Aug 23;488(7412):504-7
pubmed: 22820252
Nature. 2020 Feb;578(7793):122-128
pubmed: 32025013
Leukemia. 2005 Aug;19(8):1452-8
pubmed: 15973455
Nature. 2012 May 16;486(7403):400-4
pubmed: 22722201
Am Soc Clin Oncol Educ Book. 2018 May 23;38:925-938
pubmed: 30231352
N Engl J Med. 2021 Nov 11;385(20):1868-1880
pubmed: 34758253
Viruses. 2017 Apr 10;9(4):
pubmed: 28394272
Nature. 2020 Feb;578(7793):112-121
pubmed: 32025012
EBioMedicine. 2020 Nov;61:103030
pubmed: 33039710
Mol Oncol. 2021 Oct;15(10):2732-2751
pubmed: 34075699
EBioMedicine. 2020 Mar;53:102643
pubmed: 32081602
Nat Commun. 2020 Nov 4;11(1):5584
pubmed: 33149131
Nature. 2019 Oct;574(7779):532-537
pubmed: 31645730
CA Cancer J Clin. 2019 Jul;69(4):258-279
pubmed: 31074865
Cancer Discov. 2011 Jul;1(2):170-85
pubmed: 21984976
Neoplasia. 2017 Dec;19(12):991-1002
pubmed: 29091800
J Gynecol Oncol. 2011 Dec;22(4):239-43
pubmed: 22247800
Lancet. 2012 Apr 14;379(9824):1428-35
pubmed: 22414598
Oncogene. 2009 Jan 15;28(2):270-8
pubmed: 18850010
BMC Bioinformatics. 2020 Jan 6;21(1):7
pubmed: 31906867
J Invest Dermatol. 2009 Dec;129(12):2868-74
pubmed: 19554019
Nat Genet. 2016 Oct;48(10):1131-41
pubmed: 27595477
J Neuropathol Exp Neurol. 2015 Sep;74(9):867-72
pubmed: 26222501
Nat Rev Cancer. 2015 Dec;15(12):701-11
pubmed: 26563462
Nature. 2020 Apr;580(7802):269-273
pubmed: 32106218
Am J Pathol. 1989 Jun;134(6):1347-63
pubmed: 2474256
Nat Commun. 2020 Feb 5;11(1):728
pubmed: 32024849
Science. 2016 Nov 4;354(6312):618-622
pubmed: 27811275
BMC Med Genomics. 2015 Oct 01;8:58
pubmed: 26429708
Proc Natl Acad Sci U S A. 2001 Dec 18;98(26):15149-54
pubmed: 11742071
World J Clin Cases. 2014 Dec 16;2(12):732-41
pubmed: 25516849
Nature. 2020 Feb;578(7793):82-93
pubmed: 32025007
Oncologist. 2012;17(6):801-12
pubmed: 22618571
Nature. 2021 Jun;594(7861):106-110
pubmed: 33953404
Infect Agent Cancer. 2018 Nov 09;13:32
pubmed: 30455727
Nat Genet. 2020 Mar;52(3):331-341
pubmed: 32025003
Nat Genet. 2020 Mar;52(3):306-319
pubmed: 32024998
Genome Biol. 2021 Jul 12;22(1):202
pubmed: 34253237
Curr Treat Options Oncol. 2013 Dec;14(4):634-42
pubmed: 23990214
Nat Rev Cancer. 2021 Oct;21(10):619-637
pubmed: 34316057
Nature. 2020 Feb;578(7793):94-101
pubmed: 32025018
Nature. 2019 Nov;575(7781):210-216
pubmed: 31645765
Nat Biotechnol. 2008 Apr;26(4):462-9
pubmed: 18362881
Nat Genet. 2021 Jul;53(7):1088-1096
pubmed: 34045764
Nat Clin Pract Oncol. 2008 Jan;5(1):24-31
pubmed: 18097454
Nat Commun. 2019 Oct 8;10(1):4571
pubmed: 31594944
Breast Cancer Res. 2020 Feb 3;22(1):16
pubmed: 32014063
Hum Mol Genet. 2014 Mar 15;23(6):1527-37
pubmed: 24163242
JAMA Netw Open. 2019 Apr 5;2(4):e192597
pubmed: 31026023
Nat Genet. 2019 Dec;51(12):1732-1740
pubmed: 31740835
Neoplasia. 2008 Feb;10(2):177-88
pubmed: 18283340
J Clin Epidemiol. 2016 Feb;70:214-23
pubmed: 26441289
Nat Commun. 2017 Jun 06;8:15180
pubmed: 28585546
N Engl J Med. 2019 Nov 28;381(22):2145-2156
pubmed: 31774959
Arch Pathol Lab Med. 2009 Jan;133(1):67-71
pubmed: 19123739
Nature. 2015 Feb 19;518(7539):360-364
pubmed: 25693567
Nat Rev Clin Oncol. 2019 Dec;16(12):763-771
pubmed: 31388125
Lancet Oncol. 2016 Oct;17(10):1386-1395
pubmed: 27575023
Cell. 2017 Nov 16;171(5):1029-1041.e21
pubmed: 29056346
PLoS Comput Biol. 2019 Apr 15;15(4):e1006953
pubmed: 30986244