Result: Deepometry, a framework for applying supervised and weakly supervised deep learning to imaging cytometry.

Title:
Deepometry, a framework for applying supervised and weakly supervised deep learning to imaging cytometry.
Authors:
Doan M; Imaging Platform, Broad Institute of Harvard and MIT, Cambridge, MA, USA. minh.x.doan@gsk.com.; Bioimaging Analytics, GlaxoSmithKline, Collegeville, PA, USA. minh.x.doan@gsk.com., Barnes C; College of Engineering, Swansea University, Bay Campus, Swansea, UK., McQuin C; Imaging Platform, Broad Institute of Harvard and MIT, Cambridge, MA, USA., Caicedo JC; Imaging Platform, Broad Institute of Harvard and MIT, Cambridge, MA, USA., Goodman A; Imaging Platform, Broad Institute of Harvard and MIT, Cambridge, MA, USA., Carpenter AE; Imaging Platform, Broad Institute of Harvard and MIT, Cambridge, MA, USA. anne@broadinstitute.org., Rees P; Imaging Platform, Broad Institute of Harvard and MIT, Cambridge, MA, USA. p.rees@swansea.ac.uk.; College of Engineering, Swansea University, Bay Campus, Swansea, UK. p.rees@swansea.ac.uk.
Source:
Nature protocols [Nat Protoc] 2021 Jul; Vol. 16 (7), pp. 3572-3595. Date of Electronic Publication: 2021 Jun 18.
Publication Type:
Journal Article; Research Support, N.I.H., Extramural; Research Support, Non-U.S. Gov't; Research Support, U.S. Gov't, Non-P.H.S.
Language:
English
Journal Info:
Publisher: Nature Pub. Group Country of Publication: England NLM ID: 101284307 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1750-2799 (Electronic) Linking ISSN: 17502799 NLM ISO Abbreviation: Nat Protoc Subsets: MEDLINE
Imprint Name(s):
Original Publication: London, UK : Nature Pub. Group, 2006-
MeSH Terms:
Deep Learning* , Supervised Machine Learning*, Image Cytometry/*methods, Software ; User-Computer Interface
References:
Front Bioeng Biotechnol. 2019 Apr 02;7:53. (PMID: 31001524)
Proc Natl Acad Sci U S A. 2020 Sep 1;117(35):21381-21390. (PMID: 32839303)
Gigascience. 2017 May 1;6(5):1-9. (PMID: 28327985)
Cytometry A. 2013 Dec;83(12):1085-95. (PMID: 24166880)
Cytometry A. 2011 Jun;79(6):461-9. (PMID: 21520400)
Nat Mater. 2019 May;18(5):422-427. (PMID: 30478452)
Trends Biotechnol. 2019 Mar;37(3):310-324. (PMID: 30301571)
Clin Lab Med. 2007 Sep;27(3):653-70, viii. (PMID: 17658411)
Cytometry A. 2020 Mar;97(3):308-319. (PMID: 31688997)
J Cell Biol. 2010 May 31;189(5):777-82. (PMID: 20513764)
Lab Chip. 2020 Aug 26;20(17):3074-3090. (PMID: 32644061)
J Phys Chem B. 2019 Mar 28;123(12):2654-2661. (PMID: 30830787)
Bioinformatics. 2015 Sep 15;31(18):2989-98. (PMID: 26002886)
Cell. 2018 Sep 20;175(1):266-276.e13. (PMID: 30166209)
Nat Methods. 2019 Dec;16(12):1233-1246. (PMID: 31133758)
Nat Commun. 2020 Mar 6;11(1):1162. (PMID: 32139684)
Cytometry A. 2020 Apr;97(4):407-414. (PMID: 32091180)
Autophagy. 2011 Sep;7(9):1045-51. (PMID: 21606680)
Cytometry A. 2019 Aug;95(8):836-842. (PMID: 31081599)
Nat Commun. 2016 Jan 07;7:10256. (PMID: 26739115)
Nat Biotechnol. 2019 Dec;37(12):1482-1492. (PMID: 31796933)
Lab Chip. 2020 Oct 21;20(20):3696-3708. (PMID: 32935707)
Anal Chem. 2019 Mar 5;91(5):3405-3411. (PMID: 30741527)
BMC Bioinformatics. 2008 Nov 15;9:482. (PMID: 19014601)
Adv Sci (Weinh). 2018 Oct 11;5(12):1800761. (PMID: 30581697)
Cytometry A. 2012 Feb;81(2):130-7. (PMID: 22170789)
Cytometry A. 2021 May;99(5):511-523. (PMID: 32910546)
Adv Sci (Weinh). 2021 Jun;8(11):e2003743. (PMID: 34105281)
Methods. 2017 Jan 1;112:201-210. (PMID: 27594698)
Cytometry A. 2011 Jul;79(7):496-506. (PMID: 21638766)
Nat Biotechnol. 2018 Dec 03;:. (PMID: 30531897)
Cytometry A. 2019 May;95(5):510-520. (PMID: 31012276)
ACS Sens. 2020 Oct 23;5(10):3281-3289. (PMID: 33092347)
Nat Methods. 2017 Aug 31;14(9):849-863. (PMID: 28858338)
Nat Rev Drug Discov. 2016 Mar;15(3):204-16. (PMID: 26669673)
J Cell Sci. 2013 Dec 15;126(Pt 24):5529-39. (PMID: 24259662)
Nat Commun. 2017 Sep 6;8(1):463. (PMID: 28878212)
Science. 2018 Jun 15;360(6394):1246-1251. (PMID: 29903975)
Hepatology. 2010 Jan;51(1):35-42. (PMID: 19821521)
Grant Information:
R35 GM122547 United States GM NIGMS NIH HHS; BB/P026818/1 RCUK | Biotechnology and Biological Sciences Research Council (BBSRC); DBI 1458626 NSF | BIO | Division of Biological Infrastructure (DBI)
Entry Date(s):
Date Created: 20210619 Date Completed: 20210720 Latest Revision: 20231107
Update Code:
20250114
PubMed Central ID:
PMC8506936
DOI:
10.1038/s41596-021-00549-7
PMID:
34145434
Database:
MEDLINE

Further Information

Deep learning offers the potential to extract more than meets the eye from images captured by imaging flow cytometry. This protocol describes the application of deep learning to single-cell images to perform supervised cell classification and weakly supervised learning, using example data from an experiment exploring red blood cell morphology. We describe how to acquire and transform suitable input data as well as the steps required for deep learning training and inference using an open-source web-based application. All steps of the protocol are provided as open-source Python as well as MATLAB runtime scripts, through both command-line and graphic user interfaces. The protocol enables a flexible and friendly environment for morphological phenotyping using supervised and weakly supervised learning and the subsequent exploration of the deep learning features using multi-dimensional visualization tools. The protocol requires 40 h when training from scratch and 1 h when using a pre-trained model.