Machine learning reveals mesenchymal breast carcinoma cell adaptation in response to matrix stiffness.
Epithelial-mesenchymal transition (EMT) and its reverse process, mesenchymal-epithelial transition (MET), are believed to play key roles in facilitating the metastatic cascade. Metastatic lesions often exhibit a similar epithelial-like state to that of the primary tumour, in particular, by forming c...
Main Authors: | , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Public Library of Science (PLoS)
2021-07-01
|
Series: | PLoS Computational Biology |
Online Access: | https://doi.org/10.1371/journal.pcbi.1009193 |
id |
doaj-b7bdaabf3ea64e01a3109b0a60295ea9 |
---|---|
record_format |
Article |
spelling |
doaj-b7bdaabf3ea64e01a3109b0a60295ea92021-08-08T04:32:23ZengPublic Library of Science (PLoS)PLoS Computational Biology1553-734X1553-73582021-07-01177e100919310.1371/journal.pcbi.1009193Machine learning reveals mesenchymal breast carcinoma cell adaptation in response to matrix stiffness.Vlada S RozovaAyad G AnwerAnna E GullerHamidreza Aboulkheyr EsZahra KhabirAnastasiya I SokolovaMaxim U GavrilovEwa M GoldysMajid Ebrahimi WarkianiJean Paul ThieryAndrei V ZvyaginEpithelial-mesenchymal transition (EMT) and its reverse process, mesenchymal-epithelial transition (MET), are believed to play key roles in facilitating the metastatic cascade. Metastatic lesions often exhibit a similar epithelial-like state to that of the primary tumour, in particular, by forming carcinoma cell clusters via E-cadherin-mediated junctional complexes. However, the factors enabling mesenchymal-like micrometastatic cells to resume growth and reacquire an epithelial phenotype in the target organ microenvironment remain elusive. In this study, we developed a workflow using image-based cell profiling and machine learning to examine morphological, contextual and molecular states of individual breast carcinoma cells (MDA-MB-231). MDA-MB-231 heterogeneous response to the host organ microenvironment was modelled by substrates with controllable stiffness varying from 0.2kPa (soft tissues) to 64kPa (bone tissues). We identified 3 distinct morphological cell types (morphs) varying from compact round-shaped to flattened irregular-shaped cells with lamellipodia, predominantly populating 2-kPa and >16kPa substrates, respectively. These observations were accompanied by significant changes in E-cadherin and vimentin expression. Furthermore, we demonstrate that the bone-mimicking substrate (64kPa) induced multicellular cluster formation accompanied by E-cadherin cell surface localisation. MDA-MB-231 cells responded to different substrate stiffness by morphological adaptation, changes in proliferation rate and cytoskeleton markers, and cluster formation on bone-mimicking substrate. Our results suggest that the stiffest microenvironment can induce MET.https://doi.org/10.1371/journal.pcbi.1009193 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Vlada S Rozova Ayad G Anwer Anna E Guller Hamidreza Aboulkheyr Es Zahra Khabir Anastasiya I Sokolova Maxim U Gavrilov Ewa M Goldys Majid Ebrahimi Warkiani Jean Paul Thiery Andrei V Zvyagin |
spellingShingle |
Vlada S Rozova Ayad G Anwer Anna E Guller Hamidreza Aboulkheyr Es Zahra Khabir Anastasiya I Sokolova Maxim U Gavrilov Ewa M Goldys Majid Ebrahimi Warkiani Jean Paul Thiery Andrei V Zvyagin Machine learning reveals mesenchymal breast carcinoma cell adaptation in response to matrix stiffness. PLoS Computational Biology |
author_facet |
Vlada S Rozova Ayad G Anwer Anna E Guller Hamidreza Aboulkheyr Es Zahra Khabir Anastasiya I Sokolova Maxim U Gavrilov Ewa M Goldys Majid Ebrahimi Warkiani Jean Paul Thiery Andrei V Zvyagin |
author_sort |
Vlada S Rozova |
title |
Machine learning reveals mesenchymal breast carcinoma cell adaptation in response to matrix stiffness. |
title_short |
Machine learning reveals mesenchymal breast carcinoma cell adaptation in response to matrix stiffness. |
title_full |
Machine learning reveals mesenchymal breast carcinoma cell adaptation in response to matrix stiffness. |
title_fullStr |
Machine learning reveals mesenchymal breast carcinoma cell adaptation in response to matrix stiffness. |
title_full_unstemmed |
Machine learning reveals mesenchymal breast carcinoma cell adaptation in response to matrix stiffness. |
title_sort |
machine learning reveals mesenchymal breast carcinoma cell adaptation in response to matrix stiffness. |
publisher |
Public Library of Science (PLoS) |
series |
PLoS Computational Biology |
issn |
1553-734X 1553-7358 |
publishDate |
2021-07-01 |
description |
Epithelial-mesenchymal transition (EMT) and its reverse process, mesenchymal-epithelial transition (MET), are believed to play key roles in facilitating the metastatic cascade. Metastatic lesions often exhibit a similar epithelial-like state to that of the primary tumour, in particular, by forming carcinoma cell clusters via E-cadherin-mediated junctional complexes. However, the factors enabling mesenchymal-like micrometastatic cells to resume growth and reacquire an epithelial phenotype in the target organ microenvironment remain elusive. In this study, we developed a workflow using image-based cell profiling and machine learning to examine morphological, contextual and molecular states of individual breast carcinoma cells (MDA-MB-231). MDA-MB-231 heterogeneous response to the host organ microenvironment was modelled by substrates with controllable stiffness varying from 0.2kPa (soft tissues) to 64kPa (bone tissues). We identified 3 distinct morphological cell types (morphs) varying from compact round-shaped to flattened irregular-shaped cells with lamellipodia, predominantly populating 2-kPa and >16kPa substrates, respectively. These observations were accompanied by significant changes in E-cadherin and vimentin expression. Furthermore, we demonstrate that the bone-mimicking substrate (64kPa) induced multicellular cluster formation accompanied by E-cadherin cell surface localisation. MDA-MB-231 cells responded to different substrate stiffness by morphological adaptation, changes in proliferation rate and cytoskeleton markers, and cluster formation on bone-mimicking substrate. Our results suggest that the stiffest microenvironment can induce MET. |
url |
https://doi.org/10.1371/journal.pcbi.1009193 |
work_keys_str_mv |
AT vladasrozova machinelearningrevealsmesenchymalbreastcarcinomacelladaptationinresponsetomatrixstiffness AT ayadganwer machinelearningrevealsmesenchymalbreastcarcinomacelladaptationinresponsetomatrixstiffness AT annaeguller machinelearningrevealsmesenchymalbreastcarcinomacelladaptationinresponsetomatrixstiffness AT hamidrezaaboulkheyres machinelearningrevealsmesenchymalbreastcarcinomacelladaptationinresponsetomatrixstiffness AT zahrakhabir machinelearningrevealsmesenchymalbreastcarcinomacelladaptationinresponsetomatrixstiffness AT anastasiyaisokolova machinelearningrevealsmesenchymalbreastcarcinomacelladaptationinresponsetomatrixstiffness AT maximugavrilov machinelearningrevealsmesenchymalbreastcarcinomacelladaptationinresponsetomatrixstiffness AT ewamgoldys machinelearningrevealsmesenchymalbreastcarcinomacelladaptationinresponsetomatrixstiffness AT majidebrahimiwarkiani machinelearningrevealsmesenchymalbreastcarcinomacelladaptationinresponsetomatrixstiffness AT jeanpaulthiery machinelearningrevealsmesenchymalbreastcarcinomacelladaptationinresponsetomatrixstiffness AT andreivzvyagin machinelearningrevealsmesenchymalbreastcarcinomacelladaptationinresponsetomatrixstiffness |
_version_ |
1721216532839661568 |