Intratumoral Resolution of Driver Gene Mutation Heterogeneity in Renal Cancer Using Deep Learning.
Journal
Cancer research
ISSN: 1538-7445
Titre abrégé: Cancer Res
Pays: United States
ID NLM: 2984705R
Informations de publication
Date de publication:
03 08 2022
03 08 2022
Historique:
received:
15
07
2021
revised:
16
11
2021
accepted:
27
05
2022
pubmed:
3
6
2022
medline:
5
8
2022
entrez:
2
6
2022
Statut:
ppublish
Résumé
Intratumoral heterogeneity arising from tumor evolution poses significant challenges biologically and clinically. Dissecting this complexity may benefit from deep learning (DL) algorithms, which can infer molecular features from ubiquitous hematoxylin and eosin (H&E)-stained tissue sections. Although DL algorithms have been developed to predict some driver mutations from H&E images, the ability of these DL algorithms to resolve intratumoral mutation heterogeneity at subclonal spatial resolution is unexplored. Here, we apply DL to a paradigm of intratumoral heterogeneity, clear cell renal cell carcinoma (ccRCC), the most common type of kidney cancer. Matched IHC and H&E images were leveraged to develop DL models for predicting intratumoral genetic heterogeneity of the three most frequently mutated ccRCC genes, BAP1, PBRM1, and SETD2. DL models were generated on a large cohort (N = 1,282) and tested on several independent cohorts, including a TCGA cohort (N = 363 patients) and two tissue microarray (TMA) cohorts (N = 118 and 365 patients). These models were also expanded to a patient-derived xenograft (PDX) TMA, affording analysis of homotopic and heterotopic interactions of tumor and stroma. The status of all three genes could be inferred by DL, with BAP1 showing the highest sensitivity and performance within and across tissue samples (AUC = 0.87-0.89 on holdout). BAP1 results were validated on independent human (AUC = 0.77-0.84) and PDX (AUC = 0.80) cohorts. Finally, BAP1 predictions correlated with clinical outputs such as disease-specific survival. Overall, these data show that DL models can resolve intratumoral heterogeneity in cancer with potential diagnostic, prognostic, and biological implications. This work demonstrates the potential for deep learning analysis of histopathologic images to serve as a fast, low-cost method to assess genetic intratumoral heterogeneity. See related commentary by Song et al., p. 2672.
Identifiants
pubmed: 35654752
pii: 707325
doi: 10.1158/0008-5472.CAN-21-2318
pmc: PMC9373732
mid: NIHMS1814674
doi:
Substances chimiques
Nuclear Proteins
0
Tumor Suppressor Proteins
0
Ubiquitin Thiolesterase
EC 3.4.19.12
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Research Support, N.I.H., Extramural
Research Support, U.S. Gov't, Non-P.H.S.
Langues
eng
Sous-ensembles de citation
IM
Pagination
2792-2806Subventions
Organisme : NCI NIH HHS
ID : R01 CA244579
Pays : United States
Organisme : NCI NIH HHS
ID : P50 CA196516
Pays : United States
Organisme : NCI NIH HHS
ID : R01 CA154475
Pays : United States
Organisme : NIDDK NIH HHS
ID : R01 DK115986
Pays : United States
Commentaires et corrections
Type : CommentIn
Informations de copyright
©2022 American Association for Cancer Research.
Références
Nat Med. 2018 Oct;24(10):1559-1567
pubmed: 30224757
J Urol. 2014 Jun;191(6):1671-7
pubmed: 24291548
Nat Cancer. 2020 Aug;1(8):789-799
pubmed: 33763651
Nat Commun. 2020 Nov 16;11(1):5727
pubmed: 33199723
Cytometry A. 2019 Sep;95(9):952-965
pubmed: 31313519
Clin Lab Med. 2005 Jun;25(2):305-16
pubmed: 15848738
J Urol. 2016 Jan;195(1):180-7
pubmed: 26300218
Nat Cancer. 2020 Aug;1(8):800-810
pubmed: 35122049
Cancer Discov. 2017 Aug;7(8):900-917
pubmed: 28473526
Med Image Anal. 2019 Dec;58:101544
pubmed: 31466046
Nat Med. 2019 Jul;25(7):1054-1056
pubmed: 31160815
Sci Transl Med. 2012 Jun 6;4(137):137ra75
pubmed: 22674553
Virchows Arch. 2021 Sep;479(3):617-621
pubmed: 32979109
Cancer Discov. 2014 Sep;4(9):998-1013
pubmed: 25185190
Mod Pathol. 2016 Jan;29(1):34-42
pubmed: 26516698
Nature. 2016 Jan 21;529(7586):298-306
pubmed: 26791720
Dev Cell. 2019 May 6;49(3):444-460.e9
pubmed: 31063759
N Engl J Med. 2012 Mar 8;366(10):883-892
pubmed: 22397650
Nat Med. 2019 Aug;25(8):1301-1309
pubmed: 31308507
Am J Surg Pathol. 2018 Apr;42(4):423-441
pubmed: 29356723
EBioMedicine. 2020 Jan;51:102526
pubmed: 31859241
BJU Int. 2014 Apr;113(4):668-73
pubmed: 23937277
J Urol. 2013 Nov;190(5):1662-7
pubmed: 23792148
Nature. 2020 Feb;578(7796):621-626
pubmed: 32051585
Cell. 2018 Apr 19;173(3):595-610.e11
pubmed: 29656894
IEEE Trans Med Imaging. 2016 Aug;35(8):1962-71
pubmed: 27164577
Pathology. 2010 Jun;42(4):374-83
pubmed: 20438412
JCO Clin Cancer Inform. 2020 Sep;4:811-821
pubmed: 32946287
Cell Rep. 2018 Apr 3;23(1):313-326.e5
pubmed: 29617669
Methods Mol Biol. 2021;2190:209-228
pubmed: 32804368
Cancer Discov. 2012 May;2(5):401-4
pubmed: 22588877
Lancet Oncol. 2013 Feb;14(2):159-167
pubmed: 23333114
Nat Rev Clin Oncol. 2018 Feb;15(2):81-94
pubmed: 29115304
Nat Genet. 2016 Dec;48(12):1500-1507
pubmed: 27749841
Nature. 2013 Jul 4;499(7456):43-9
pubmed: 23792563
Urology. 2013 Mar;81(3):581-6
pubmed: 23290145
J Clin Oncol. 2014 Jun 20;32(18):1968-76
pubmed: 24821879
Kidney Cancer J. 2020 Sep;18(3):68-76
pubmed: 34178206
Cancer. 2014 Apr 1;120(7):1059-67
pubmed: 24382589
Nat Med. 2015 Jul;21(7):751-9
pubmed: 26099045
Clin Cancer Res. 2021 May 15;27(10):2868-2878
pubmed: 33722896
J Clin Oncol. 2017 Nov 10;35(32):3706-3713
pubmed: 28976794
Nat Biomed Eng. 2020 Aug;4(8):827-834
pubmed: 32572199
Nat Cell Biol. 2018 Dec;20(12):1349-1360
pubmed: 30482943
BJU Int. 2017 May;119(5):741-747
pubmed: 28075543
Sci Signal. 2013 Apr 02;6(269):pl1
pubmed: 23550210
Nat Genet. 2012 Jun 10;44(7):751-9
pubmed: 22683710
Am J Clin Pathol. 2021 Apr 26;155(5):718-728
pubmed: 33210135