دورية أكاديمية

Obtaining spatially resolved tumor purity maps using deep multiple instance learning in a pan-cancer study.

التفاصيل البيبلوغرافية
العنوان: Obtaining spatially resolved tumor purity maps using deep multiple instance learning in a pan-cancer study.
المؤلفون: Oner MU; Bioinformatics Institute, Agency for Science, Technology and Research (A∗STAR), Singapore 138671, Singapore.; School of Computing, National University of Singapore, Singapore 117417, Singapore., Chen J; Genome Institute of Singapore, Agency for Science, Technology and Research (A∗STAR), Singapore 138672, Singapore., Revkov E; Genome Institute of Singapore, Agency for Science, Technology and Research (A∗STAR), Singapore 138672, Singapore.; School of Computing, National University of Singapore, Singapore 117417, Singapore., James A; Department of Anatomical Pathology, Singapore General Hospital, Singapore 169608, Singapore., Heng SY; Department of Anatomical Pathology, Singapore General Hospital, Singapore 169608, Singapore., Kaya AN; Genome Institute of Singapore, Agency for Science, Technology and Research (A∗STAR), Singapore 138672, Singapore., Alvarez JJS; Genome Institute of Singapore, Agency for Science, Technology and Research (A∗STAR), Singapore 138672, Singapore.; School of Computing, National University of Singapore, Singapore 117417, Singapore., Takano A; Department of Anatomical Pathology, Singapore General Hospital, Singapore 169608, Singapore., Cheng XM; Department of Anatomical Pathology, Singapore General Hospital, Singapore 169608, Singapore., Lim TKH; Department of Anatomical Pathology, Singapore General Hospital, Singapore 169608, Singapore., Tan DSW; Division of Medical Oncology, National Cancer Centre Singapore, Singapore 169610, Singapore.; Oncology Academic Clinical Programme, Duke-NUS Medical School, Singapore 169857, Singapore.; Genome Institute of Singapore, Agency for Science, Technology and Research (A∗STAR), Singapore 138672, Singapore., Zhai W; Genome Institute of Singapore, Agency for Science, Technology and Research (A∗STAR), Singapore 138672, Singapore.; Key Laboratory of Zoological Systematics and Evolution, Institute of Zoology, Chinese Academy of Sciences, Beijing 100101, China.; Center for Excellence in Animal Evolution and Genetics, Chinese Academy of Sciences, Kunming 650223, China., Skanderup AJ; Genome Institute of Singapore, Agency for Science, Technology and Research (A∗STAR), Singapore 138672, Singapore.; School of Computing, National University of Singapore, Singapore 117417, Singapore.; Division of Medical Oncology, National Cancer Centre Singapore, Singapore 169610, Singapore., Sung WK; School of Computing, National University of Singapore, Singapore 117417, Singapore.; Genome Institute of Singapore, Agency for Science, Technology and Research (A∗STAR), Singapore 138672, Singapore., Lee HK; Bioinformatics Institute, Agency for Science, Technology and Research (A∗STAR), Singapore 138671, Singapore.; School of Computing, National University of Singapore, Singapore 117417, Singapore.; Singapore Eye Research Institute (SERI), Singapore 169856, Singapore.; Image and Pervasive Access Lab (IPAL), Singapore 138632, Singapore.; Rehabilitation Research Institute of Singapore, Singapore 308232, Singapore.; Singapore Institute for Clinical Sciences, Singapore 117609, Singapore.
المصدر: Patterns (New York, N.Y.) [Patterns (N Y)] 2021 Dec 09; Vol. 3 (2), pp. 100399. Date of Electronic Publication: 2021 Dec 09 (Print Publication: 2022).
نوع المنشور: Journal Article
اللغة: English
بيانات الدورية: Publisher: Elsevier Inc Country of Publication: United States NLM ID: 101767765 Publication Model: eCollection Cited Medium: Internet ISSN: 2666-3899 (Electronic) Linking ISSN: 26663899 NLM ISO Abbreviation: Patterns (N Y) Subsets: PubMed not MEDLINE
أسماء مطبوعة: Original Publication: [New York] : Elsevier Inc., [2020]-
مستخلص: Tumor purity is the percentage of cancer cells within a tissue section. Pathologists estimate tumor purity to select samples for genomic analysis by manually reading hematoxylin-eosin (H&E)-stained slides, which is tedious, time consuming, and prone to inter-observer variability. Besides, pathologists' estimates do not correlate well with genomic tumor purity values, which are inferred from genomic data and accepted as accurate for downstream analysis. We developed a deep multiple instance learning model predicting tumor purity from H&E-stained digital histopathology slides. Our model successfully predicted tumor purity in eight The Cancer Genome Atlas (TCGA) cohorts and a local Singapore cohort. The predictions were highly consistent with genomic tumor purity values. Thus, our model can be utilized to select samples for genomic analysis, which will help reduce pathologists' workload and decrease inter-observer variability. Furthermore, our model provided tumor purity maps showing the spatial variation within sections. They can help better understand the tumor microenvironment.
Competing Interests: The authors declare no competing interests.
(© 2021 The Authors.)
References: J Mol Diagn. 2017 May;19(3):341-365. (PMID: 28341590)
Nat Commun. 2015 Dec 04;6:8971. (PMID: 26634437)
Nat Med. 2019 Aug;25(8):1301-1309. (PMID: 31308507)
Oncogene. 2008 Oct 6;27(45):5904-12. (PMID: 18836471)
Bioinformatics. 2014 Feb 01;30(3):431-3. (PMID: 24292941)
Biopreserv Biobank. 2021 Aug;19(4):324-331. (PMID: 33780631)
J Clin Oncol. 2003 Nov 1;21(21):3902-8. (PMID: 14507943)
Nat Genet. 2015 Apr;47(4):312-9. (PMID: 25706627)
Nat Genet. 2013 Oct;45(10):1134-40. (PMID: 24071852)
Cancer Immunol Res. 2018 Jan;6(1):87-97. (PMID: 29141981)
Nat Genet. 2014 Mar;46(3):225-233. (PMID: 24487277)
Nat Biotechnol. 2019 Jul;37(7):773-782. (PMID: 31061481)
Elife. 2017 Nov 13;6:. (PMID: 29130882)
IEEE/ACM Trans Comput Biol Bioinform. 2021 Mar-Apr;18(2):539-549. (PMID: 31180897)
Nat Med. 2018 Oct;24(10):1559-1567. (PMID: 30224757)
Ann Oncol. 2015 Jan;26(1):64-70. (PMID: 25319062)
Nat Genet. 2015 Mar;47(3):209-16. (PMID: 25665006)
Genome Biol. 2014 Aug 07;15(8):419. (PMID: 25103624)
BMC Bioinformatics. 2012 May 08;13:86. (PMID: 22568884)
BMC Med Genomics. 2011 Jun 30;4:54. (PMID: 21718502)
Cancer Cell. 2015 Jan 12;27(1):15-26. (PMID: 25584892)
Nat Genet. 2020 Feb;52(2):177-186. (PMID: 32015526)
J Pathol Transl Med. 2017 May;51(3):191-204. (PMID: 28535585)
Science. 2015 Apr 24;348(6233):aaa6090. (PMID: 25858977)
IEEE/ACM Trans Comput Biol Bioinform. 2020 Jul-Aug;17(4):1141-1153. (PMID: 30489272)
Nature. 2013 Sep 19;501(7467):346-54. (PMID: 24048067)
Bioinformatics. 2015 Nov 1;31(21):3401-5. (PMID: 26112293)
Appl Immunohistochem Mol Morphol. 2019 Nov/Dec;27(10):764-772. (PMID: 30102605)
Proc IEEE Int Symp Biomed Imaging. 2017 Apr;2017:1137-1140. (PMID: 30364881)
Nat Biotechnol. 2012 May;30(5):413-21. (PMID: 22544022)
Bioinformatics. 2011 Jun 1;27(11):1473-80. (PMID: 21498400)
Front Mol Biosci. 2020 Dec 23;7:533196. (PMID: 33425983)
Bioinformatics. 2017 Sep 1;33(17):2651-2657. (PMID: 28472248)
Proc Natl Acad Sci U S A. 2010 Sep 28;107(39):16910-5. (PMID: 20837533)
N Engl J Med. 2017 Jun 1;376(22):2109-2121. (PMID: 28445112)
Nat Commun. 2016 Aug 16;7:12474. (PMID: 27527408)
Cancer Lett. 2013 Nov 1;340(2):284-95. (PMID: 23174106)
Nat Commun. 2017 Feb 27;8:4565. (PMID: 28240289)
Nature. 2014 Jul 31;511(7511):543-50. (PMID: 25079552)
Nature. 2015 Apr 16;520(7547):353-357. (PMID: 25830880)
Cancer Cell. 2012 Mar 20;21(3):309-22. (PMID: 22439926)
Genome Biol. 2017 Jan 25;18(1):17. (PMID: 28122605)
Cell. 2017 Nov 2;171(4):950-965.e28. (PMID: 29100075)
Genome Biol. 2013 Jul 29;14(7):R80. (PMID: 23895164)
Nucleic Acids Res. 2015 Feb 27;43(4):e23. (PMID: 25477383)
Bioinformatics. 2013 Aug 1;29(15):1888-9. (PMID: 23749958)
JAMA Netw Open. 2019 Nov 1;2(11):e1914645. (PMID: 31693124)
Comput Math Methods Med. 2019 Jun 9;2019:3041250. (PMID: 31281408)
Science. 2018 Nov 16;362(6416):. (PMID: 30385464)
J Thorac Oncol. 2020 Jan;15(1):130-137. (PMID: 31605798)
Bioinformatics. 2012 Sep 1;28(17):2265-6. (PMID: 22743227)
JCO Precis Oncol. 2020 Sep 4;4:. (PMID: 33015524)
Oncotarget. 2015 Sep 29;6(29):27938-52. (PMID: 26317646)
FEBS J. 2016 Jun;283(12):2245-58. (PMID: 26945550)
Appl Immunohistochem Mol Morphol. 2014 May-Jun;22(5):363-71. (PMID: 24162261)
Cancer Med. 2020 Dec;9(23):9052-9063. (PMID: 33030278)
Cell. 2019 Jun 13;177(7):1888-1902.e21. (PMID: 31178118)
Nat Commun. 2014 May 29;5:3887. (PMID: 24871328)
Nat Methods. 2008 Jan;5(1):16-8. (PMID: 18165802)
Nat Cancer. 2020 Aug;1(8):800-810. (PMID: 35122049)
Clin Cancer Res. 2017 Oct 15;23(20):6279-6291. (PMID: 28754819)
Front Genet. 2020 Apr 30;11:458. (PMID: 32425990)
Bioinformatics. 2014 Jan 1;30(1):50-60. (PMID: 24177718)
Nat Commun. 2013;4:2612. (PMID: 24113773)
J Mol Diagn. 2013 Sep;15(5):623-33. (PMID: 23810758)
Mod Pathol. 2014 Feb;27(2):168-74. (PMID: 23887293)
BMC Genomics. 2019 Dec 27;20(1):1021. (PMID: 31881847)
Cancer Manag Res. 2018 Sep 17;10:3569-3577. (PMID: 30271205)
Nat Methods. 2018 May;15(5):343-346. (PMID: 29553579)
فهرسة مساهمة: Keywords: computational pathology; deep learning; digital histopathology; digital pathology; genomic sequencing; multiple instance learning; spatial omics; tumor microenvironment; tumor purity; whole-slide images
تواريخ الأحداث: Date Created: 20220224 Latest Revision: 20220225
رمز التحديث: 20231215
مُعرف محوري في PubMed: PMC8848022
DOI: 10.1016/j.patter.2021.100399
PMID: 35199060
قاعدة البيانات: MEDLINE
الوصف
تدمد:2666-3899
DOI:10.1016/j.patter.2021.100399