No Cover Image

Journal article 687 views 211 downloads

Inter-laboratory automation of the in vitro micronucleus assay using imaging flow cytometry and deep learning

John Wills, Jatin Verma, Benjamin Rees, Danielle Harte, Chelly Haxhiraj, Claire Barnes Orcid Logo, Rachel Barnes, Matthew A. Rodrigues, Minh Doan, Andrew Filby, Rachel E. Hewitt, Cathy Thornton Orcid Logo, James Cronin Orcid Logo, Julia D. Kenny, Ruby Buckley, Anthony Lynch, Anne E. Carpenter, Huw Summers Orcid Logo, George Johnson Orcid Logo, Paul Rees Orcid Logo

Archives of Toxicology, Volume: 95, Issue: 9, Pages: 3101 - 3115

Swansea University Authors: John Wills, Jatin Verma, Benjamin Rees, Danielle Harte, Chelly Haxhiraj, Claire Barnes Orcid Logo, Rachel Barnes, Cathy Thornton Orcid Logo, James Cronin Orcid Logo, Anthony Lynch, Huw Summers Orcid Logo, George Johnson Orcid Logo, Paul Rees Orcid Logo

  • 57403.pdf

    PDF | Version of Record

    © The Author(s) 2021. This article is licensed under a Creative Commons Attribution 4.0 International License

    Download (7.03MB)

Check full text

DOI (Published version): 10.1007/s00204-021-03113-0

Abstract

The in vitro micronucleus assay is a globally significant method for DNA damage quantification used for regulatory compound safety testing in addition to inter-individual monitoring of environmental, lifestyle and occupational factors. However, it relies on time-consuming and user-subjective manual...

Full description

Published in: Archives of Toxicology
ISSN: 0340-5761 1432-0738
Published: Springer Science and Business Media LLC 2021
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa57403
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2021-07-16T08:31:12Z
last_indexed 2023-01-11T14:37:17Z
id cronfa57403
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2022-12-06T15:07:47.2896944</datestamp><bib-version>v2</bib-version><id>57403</id><entry>2021-07-16</entry><title>Inter-laboratory automation of the in vitro micronucleus assay using imaging flow cytometry and deep learning</title><swanseaauthors><author><sid>9f113236244f4f54d584f1fb3278061b</sid><ORCID/><firstname>John</firstname><surname>Wills</surname><name>John Wills</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>6c11cec3815148d928211f6648a6dce9</sid><firstname>Jatin</firstname><surname>Verma</surname><name>Jatin Verma</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>e593a2c30aada43a4bcf0542558aff13</sid><firstname>Benjamin</firstname><surname>Rees</surname><name>Benjamin Rees</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>183eddc613937f235a28c10f63079678</sid><firstname>Danielle</firstname><surname>Harte</surname><name>Danielle Harte</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>31db63cad9464efd88803895a4a3edda</sid><firstname>Chelly</firstname><surname>Haxhiraj</surname><name>Chelly Haxhiraj</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>024232879fc13d5ceac584360af8742c</sid><ORCID>0000-0003-1031-7127</ORCID><firstname>Claire</firstname><surname>Barnes</surname><name>Claire Barnes</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>ee057ea66de3c09af573e2dcf939f9ac</sid><firstname>Rachel</firstname><surname>Barnes</surname><name>Rachel Barnes</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>c71a7a4be7361094d046d312202bce0c</sid><ORCID>0000-0002-5153-573X</ORCID><firstname>Cathy</firstname><surname>Thornton</surname><name>Cathy Thornton</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>9cfd17551c0d1f7438895121e4fbb6e8</sid><ORCID>0000-0002-0590-9462</ORCID><firstname>James</firstname><surname>Cronin</surname><name>James Cronin</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>94e539dab2511bf7fa596450e5cadabf</sid><firstname>Anthony</firstname><surname>Lynch</surname><name>Anthony Lynch</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>a61c15e220837ebfa52648c143769427</sid><ORCID>0000-0002-0898-5612</ORCID><firstname>Huw</firstname><surname>Summers</surname><name>Huw Summers</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>37d0f121db69fd09f364df89e4405e31</sid><ORCID>0000-0001-5643-9942</ORCID><firstname>George</firstname><surname>Johnson</surname><name>George Johnson</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>537a2fe031a796a3bde99679ee8c24f5</sid><ORCID>0000-0002-7715-6914</ORCID><firstname>Paul</firstname><surname>Rees</surname><name>Paul Rees</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2021-07-16</date><abstract>The in vitro micronucleus assay is a globally significant method for DNA damage quantification used for regulatory compound safety testing in addition to inter-individual monitoring of environmental, lifestyle and occupational factors. However, it relies on time-consuming and user-subjective manual scoring. Here we show that imaging flow cytometry and deep learning image classification represents a capable platform for automated, inter-laboratory operation. Images were captured for the cytokinesis-block micronucleus (CBMN) assay across three laboratories using methyl methanesulphonate (1.25&#x2013;5.0 &#x3BC;g/mL) and/or carbendazim (0.8&#x2013;1.6 &#x3BC;g/mL) exposures to TK6 cells. Human-scored image sets were assembled and used to train and test the classification abilities of the &#x201C;DeepFlow&#x201D; neural network in both intra- and inter-laboratory contexts. Harnessing image diversity across laboratories yielded a network able to score unseen data from an entirely new laboratory without any user configuration. Image classification accuracies of 98%, 95%, 82% and 85% were achieved for &#x2018;mononucleates&#x2019;, &#x2018;binucleates&#x2019;, &#x2018;mononucleates with MN&#x2019; and &#x2018;binucleates with MN&#x2019;, respectively. Successful classifications of &#x2018;trinucleates&#x2019; (90%) and &#x2018;tetranucleates&#x2019; (88%) in addition to &#x2018;other or unscorable&#x2019; phenotypes (96%) were also achieved. Attempts to classify extremely rare, tri- and tetranucleated cells with micronuclei into their own categories were less successful (&#x2264; 57%). Benchmark dose analyses of human or automatically scored micronucleus frequency data yielded quantitation of the same equipotent concentration regardless of scoring method. We conclude that this automated approach offers significant potential to broaden the practical utility of the CBMN method across industry, research and clinical domains. We share our strategy using openly-accessible frameworks.</abstract><type>Journal Article</type><journal>Archives of Toxicology</journal><volume>95</volume><journalNumber>9</journalNumber><paginationStart>3101</paginationStart><paginationEnd>3115</paginationEnd><publisher>Springer Science and Business Media LLC</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>0340-5761</issnPrint><issnElectronic>1432-0738</issnElectronic><keywords>Compound screening; Genetic toxicology; High throughput; Image analysis; Machine learning; Micronucleus test</keywords><publishedDay>1</publishedDay><publishedMonth>9</publishedMonth><publishedYear>2021</publishedYear><publishedDate>2021-09-01</publishedDate><doi>10.1007/s00204-021-03113-0</doi><url/><notes/><college>COLLEGE NANME</college><CollegeCode>COLLEGE CODE</CollegeCode><institution>Swansea University</institution><apcterm>SU Library paid the OA fee (TA Institutional Deal)</apcterm><funders>The authors acknowledge the UK Engineering and Physical Sciences Research Council (EP/N013506/1) and UK Biotechnology and Biological Sciences Research Council (BB/P026818/1) for supporting this work. We also thank the Life Science Bridging Fund within the Life Science Research Network Wales (LSBF/R3-007), AgorIP (WEFO), and the National Institutes of Health (R35 GM122547) for providing funding in support of the project</funders><projectreference/><lastEdited>2022-12-06T15:07:47.2896944</lastEdited><Created>2021-07-16T09:29:09.8711179</Created><path><level id="1">Faculty of Medicine, Health and Life Sciences</level><level id="2">Swansea University Medical School - Medicine</level></path><authors><author><firstname>John</firstname><surname>Wills</surname><orcid/><order>1</order></author><author><firstname>Jatin</firstname><surname>Verma</surname><order>2</order></author><author><firstname>Benjamin</firstname><surname>Rees</surname><order>3</order></author><author><firstname>Danielle</firstname><surname>Harte</surname><order>4</order></author><author><firstname>Chelly</firstname><surname>Haxhiraj</surname><order>5</order></author><author><firstname>Claire</firstname><surname>Barnes</surname><orcid>0000-0003-1031-7127</orcid><order>6</order></author><author><firstname>Rachel</firstname><surname>Barnes</surname><order>7</order></author><author><firstname>Matthew A.</firstname><surname>Rodrigues</surname><order>8</order></author><author><firstname>Minh</firstname><surname>Doan</surname><order>9</order></author><author><firstname>Andrew</firstname><surname>Filby</surname><order>10</order></author><author><firstname>Rachel E.</firstname><surname>Hewitt</surname><order>11</order></author><author><firstname>Cathy</firstname><surname>Thornton</surname><orcid>0000-0002-5153-573X</orcid><order>12</order></author><author><firstname>James</firstname><surname>Cronin</surname><orcid>0000-0002-0590-9462</orcid><order>13</order></author><author><firstname>Julia D.</firstname><surname>Kenny</surname><order>14</order></author><author><firstname>Ruby</firstname><surname>Buckley</surname><order>15</order></author><author><firstname>Anthony</firstname><surname>Lynch</surname><order>16</order></author><author><firstname>Anne E.</firstname><surname>Carpenter</surname><order>17</order></author><author><firstname>Huw</firstname><surname>Summers</surname><orcid>0000-0002-0898-5612</orcid><order>18</order></author><author><firstname>George</firstname><surname>Johnson</surname><orcid>0000-0001-5643-9942</orcid><order>19</order></author><author><firstname>Paul</firstname><surname>Rees</surname><orcid>0000-0002-7715-6914</orcid><order>20</order></author></authors><documents><document><filename>57403__20490__1888b77ae6df4529842c5e7c95865e8a.pdf</filename><originalFilename>57403.pdf</originalFilename><uploaded>2021-07-30T10:07:00.9202835</uploaded><type>Output</type><contentLength>7366908</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>&#xA9; The Author(s) 2021. This article is licensed under a Creative Commons Attribution 4.0 International License</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2022-12-06T15:07:47.2896944 v2 57403 2021-07-16 Inter-laboratory automation of the in vitro micronucleus assay using imaging flow cytometry and deep learning 9f113236244f4f54d584f1fb3278061b John Wills John Wills true false 6c11cec3815148d928211f6648a6dce9 Jatin Verma Jatin Verma true false e593a2c30aada43a4bcf0542558aff13 Benjamin Rees Benjamin Rees true false 183eddc613937f235a28c10f63079678 Danielle Harte Danielle Harte true false 31db63cad9464efd88803895a4a3edda Chelly Haxhiraj Chelly Haxhiraj true false 024232879fc13d5ceac584360af8742c 0000-0003-1031-7127 Claire Barnes Claire Barnes true false ee057ea66de3c09af573e2dcf939f9ac Rachel Barnes Rachel Barnes true false c71a7a4be7361094d046d312202bce0c 0000-0002-5153-573X Cathy Thornton Cathy Thornton true false 9cfd17551c0d1f7438895121e4fbb6e8 0000-0002-0590-9462 James Cronin James Cronin true false 94e539dab2511bf7fa596450e5cadabf Anthony Lynch Anthony Lynch true false a61c15e220837ebfa52648c143769427 0000-0002-0898-5612 Huw Summers Huw Summers true false 37d0f121db69fd09f364df89e4405e31 0000-0001-5643-9942 George Johnson George Johnson true false 537a2fe031a796a3bde99679ee8c24f5 0000-0002-7715-6914 Paul Rees Paul Rees true false 2021-07-16 The in vitro micronucleus assay is a globally significant method for DNA damage quantification used for regulatory compound safety testing in addition to inter-individual monitoring of environmental, lifestyle and occupational factors. However, it relies on time-consuming and user-subjective manual scoring. Here we show that imaging flow cytometry and deep learning image classification represents a capable platform for automated, inter-laboratory operation. Images were captured for the cytokinesis-block micronucleus (CBMN) assay across three laboratories using methyl methanesulphonate (1.25–5.0 μg/mL) and/or carbendazim (0.8–1.6 μg/mL) exposures to TK6 cells. Human-scored image sets were assembled and used to train and test the classification abilities of the “DeepFlow” neural network in both intra- and inter-laboratory contexts. Harnessing image diversity across laboratories yielded a network able to score unseen data from an entirely new laboratory without any user configuration. Image classification accuracies of 98%, 95%, 82% and 85% were achieved for ‘mononucleates’, ‘binucleates’, ‘mononucleates with MN’ and ‘binucleates with MN’, respectively. Successful classifications of ‘trinucleates’ (90%) and ‘tetranucleates’ (88%) in addition to ‘other or unscorable’ phenotypes (96%) were also achieved. Attempts to classify extremely rare, tri- and tetranucleated cells with micronuclei into their own categories were less successful (≤ 57%). Benchmark dose analyses of human or automatically scored micronucleus frequency data yielded quantitation of the same equipotent concentration regardless of scoring method. We conclude that this automated approach offers significant potential to broaden the practical utility of the CBMN method across industry, research and clinical domains. We share our strategy using openly-accessible frameworks. Journal Article Archives of Toxicology 95 9 3101 3115 Springer Science and Business Media LLC 0340-5761 1432-0738 Compound screening; Genetic toxicology; High throughput; Image analysis; Machine learning; Micronucleus test 1 9 2021 2021-09-01 10.1007/s00204-021-03113-0 COLLEGE NANME COLLEGE CODE Swansea University SU Library paid the OA fee (TA Institutional Deal) The authors acknowledge the UK Engineering and Physical Sciences Research Council (EP/N013506/1) and UK Biotechnology and Biological Sciences Research Council (BB/P026818/1) for supporting this work. We also thank the Life Science Bridging Fund within the Life Science Research Network Wales (LSBF/R3-007), AgorIP (WEFO), and the National Institutes of Health (R35 GM122547) for providing funding in support of the project 2022-12-06T15:07:47.2896944 2021-07-16T09:29:09.8711179 Faculty of Medicine, Health and Life Sciences Swansea University Medical School - Medicine John Wills 1 Jatin Verma 2 Benjamin Rees 3 Danielle Harte 4 Chelly Haxhiraj 5 Claire Barnes 0000-0003-1031-7127 6 Rachel Barnes 7 Matthew A. Rodrigues 8 Minh Doan 9 Andrew Filby 10 Rachel E. Hewitt 11 Cathy Thornton 0000-0002-5153-573X 12 James Cronin 0000-0002-0590-9462 13 Julia D. Kenny 14 Ruby Buckley 15 Anthony Lynch 16 Anne E. Carpenter 17 Huw Summers 0000-0002-0898-5612 18 George Johnson 0000-0001-5643-9942 19 Paul Rees 0000-0002-7715-6914 20 57403__20490__1888b77ae6df4529842c5e7c95865e8a.pdf 57403.pdf 2021-07-30T10:07:00.9202835 Output 7366908 application/pdf Version of Record true © The Author(s) 2021. This article is licensed under a Creative Commons Attribution 4.0 International License true eng http://creativecommons.org/licenses/by/4.0/
title Inter-laboratory automation of the in vitro micronucleus assay using imaging flow cytometry and deep learning
spellingShingle Inter-laboratory automation of the in vitro micronucleus assay using imaging flow cytometry and deep learning
John Wills
Jatin Verma
Benjamin Rees
Danielle Harte
Chelly Haxhiraj
Claire Barnes
Rachel Barnes
Cathy Thornton
James Cronin
Anthony Lynch
Huw Summers
George Johnson
Paul Rees
title_short Inter-laboratory automation of the in vitro micronucleus assay using imaging flow cytometry and deep learning
title_full Inter-laboratory automation of the in vitro micronucleus assay using imaging flow cytometry and deep learning
title_fullStr Inter-laboratory automation of the in vitro micronucleus assay using imaging flow cytometry and deep learning
title_full_unstemmed Inter-laboratory automation of the in vitro micronucleus assay using imaging flow cytometry and deep learning
title_sort Inter-laboratory automation of the in vitro micronucleus assay using imaging flow cytometry and deep learning
author_id_str_mv 9f113236244f4f54d584f1fb3278061b
6c11cec3815148d928211f6648a6dce9
e593a2c30aada43a4bcf0542558aff13
183eddc613937f235a28c10f63079678
31db63cad9464efd88803895a4a3edda
024232879fc13d5ceac584360af8742c
ee057ea66de3c09af573e2dcf939f9ac
c71a7a4be7361094d046d312202bce0c
9cfd17551c0d1f7438895121e4fbb6e8
94e539dab2511bf7fa596450e5cadabf
a61c15e220837ebfa52648c143769427
37d0f121db69fd09f364df89e4405e31
537a2fe031a796a3bde99679ee8c24f5
author_id_fullname_str_mv 9f113236244f4f54d584f1fb3278061b_***_John Wills
6c11cec3815148d928211f6648a6dce9_***_Jatin Verma
e593a2c30aada43a4bcf0542558aff13_***_Benjamin Rees
183eddc613937f235a28c10f63079678_***_Danielle Harte
31db63cad9464efd88803895a4a3edda_***_Chelly Haxhiraj
024232879fc13d5ceac584360af8742c_***_Claire Barnes
ee057ea66de3c09af573e2dcf939f9ac_***_Rachel Barnes
c71a7a4be7361094d046d312202bce0c_***_Cathy Thornton
9cfd17551c0d1f7438895121e4fbb6e8_***_James Cronin
94e539dab2511bf7fa596450e5cadabf_***_Anthony Lynch
a61c15e220837ebfa52648c143769427_***_Huw Summers
37d0f121db69fd09f364df89e4405e31_***_George Johnson
537a2fe031a796a3bde99679ee8c24f5_***_Paul Rees
author John Wills
Jatin Verma
Benjamin Rees
Danielle Harte
Chelly Haxhiraj
Claire Barnes
Rachel Barnes
Cathy Thornton
James Cronin
Anthony Lynch
Huw Summers
George Johnson
Paul Rees
author2 John Wills
Jatin Verma
Benjamin Rees
Danielle Harte
Chelly Haxhiraj
Claire Barnes
Rachel Barnes
Matthew A. Rodrigues
Minh Doan
Andrew Filby
Rachel E. Hewitt
Cathy Thornton
James Cronin
Julia D. Kenny
Ruby Buckley
Anthony Lynch
Anne E. Carpenter
Huw Summers
George Johnson
Paul Rees
format Journal article
container_title Archives of Toxicology
container_volume 95
container_issue 9
container_start_page 3101
publishDate 2021
institution Swansea University
issn 0340-5761
1432-0738
doi_str_mv 10.1007/s00204-021-03113-0
publisher Springer Science and Business Media LLC
college_str Faculty of Medicine, Health and Life Sciences
hierarchytype
hierarchy_top_id facultyofmedicinehealthandlifesciences
hierarchy_top_title Faculty of Medicine, Health and Life Sciences
hierarchy_parent_id facultyofmedicinehealthandlifesciences
hierarchy_parent_title Faculty of Medicine, Health and Life Sciences
department_str Swansea University Medical School - Medicine{{{_:::_}}}Faculty of Medicine, Health and Life Sciences{{{_:::_}}}Swansea University Medical School - Medicine
document_store_str 1
active_str 0
description The in vitro micronucleus assay is a globally significant method for DNA damage quantification used for regulatory compound safety testing in addition to inter-individual monitoring of environmental, lifestyle and occupational factors. However, it relies on time-consuming and user-subjective manual scoring. Here we show that imaging flow cytometry and deep learning image classification represents a capable platform for automated, inter-laboratory operation. Images were captured for the cytokinesis-block micronucleus (CBMN) assay across three laboratories using methyl methanesulphonate (1.25–5.0 μg/mL) and/or carbendazim (0.8–1.6 μg/mL) exposures to TK6 cells. Human-scored image sets were assembled and used to train and test the classification abilities of the “DeepFlow” neural network in both intra- and inter-laboratory contexts. Harnessing image diversity across laboratories yielded a network able to score unseen data from an entirely new laboratory without any user configuration. Image classification accuracies of 98%, 95%, 82% and 85% were achieved for ‘mononucleates’, ‘binucleates’, ‘mononucleates with MN’ and ‘binucleates with MN’, respectively. Successful classifications of ‘trinucleates’ (90%) and ‘tetranucleates’ (88%) in addition to ‘other or unscorable’ phenotypes (96%) were also achieved. Attempts to classify extremely rare, tri- and tetranucleated cells with micronuclei into their own categories were less successful (≤ 57%). Benchmark dose analyses of human or automatically scored micronucleus frequency data yielded quantitation of the same equipotent concentration regardless of scoring method. We conclude that this automated approach offers significant potential to broaden the practical utility of the CBMN method across industry, research and clinical domains. We share our strategy using openly-accessible frameworks.
published_date 2021-09-01T04:13:07Z
_version_ 1763753892326146048
score 11.013148

Similar Items