MORPHIOUS: an unsupervised machine learning workflow to detect the activation of microglia and astrocytes.


Journal

Journal of neuroinflammation
ISSN: 1742-2094
Titre abrégé: J Neuroinflammation
Pays: England
ID NLM: 101222974

Informations de publication

Date de publication:
29 Jan 2022
Historique:
received: 26 03 2021
accepted: 29 12 2021
entrez: 30 1 2022
pubmed: 31 1 2022
medline: 8 4 2022
Statut: epublish

Résumé

In conditions of brain injury and degeneration, defining microglial and astrocytic activation using cellular markers alone remains a challenging task. We developed the MORPHIOUS software package, an unsupervised machine learning workflow which can learn the morphologies of non-activated astrocytes and microglia, and from this information, infer clusters of microglial and astrocytic activation in brain tissue. MORPHIOUS combines a one-class support vector machine with the density-based spatial clustering of applications with noise (DBSCAN) algorithm to identify clusters of microglial and astrocytic activation. Here, activation was triggered by permeabilizing the blood-brain barrier (BBB) in the mouse hippocampus using focused ultrasound (FUS). At 7 day post-treatment, MORPHIOUS was applied to evaluate microglial and astrocytic activation in histological tissue. MORPHIOUS was further evaluated on hippocampal sections of TgCRND8 mice, a model of amyloidosis that is prone to microglial and astrocytic activation. MORPHIOUS defined two classes of microglia, termed focal and proximal, that are spatially adjacent to the activating stimulus. Focal and proximal microglia demonstrated activity-associated features, including increased levels of ionized calcium-binding adapter molecule 1 expression, enlarged soma size, and deramification. MORPHIOUS further identified clusters of astrocytes characterized by activity-related changes in glial fibrillary acidic protein expression and branching. To validate these classifications following FUS, co-localization with activation markers were assessed. Focal and proximal microglia co-localized with the transforming growth factor beta 1, while proximal astrocytes co-localized with Nestin. In TgCRND8 mice, microglial and astrocytic activation clusters were found to correlate with amyloid-β plaque load. Thus, by only referencing control microglial and astrocytic morphologies, MORPHIOUS identified regions of interest corresponding to microglial and astrocytic activation. Overall, our algorithm is a reliable and sensitive method for characterizing microglial and astrocytic activation following FUS-induced BBB permeability and in animal models of neurodegeneration.

Sections du résumé

BACKGROUND BACKGROUND
In conditions of brain injury and degeneration, defining microglial and astrocytic activation using cellular markers alone remains a challenging task. We developed the MORPHIOUS software package, an unsupervised machine learning workflow which can learn the morphologies of non-activated astrocytes and microglia, and from this information, infer clusters of microglial and astrocytic activation in brain tissue.
METHODS METHODS
MORPHIOUS combines a one-class support vector machine with the density-based spatial clustering of applications with noise (DBSCAN) algorithm to identify clusters of microglial and astrocytic activation. Here, activation was triggered by permeabilizing the blood-brain barrier (BBB) in the mouse hippocampus using focused ultrasound (FUS). At 7 day post-treatment, MORPHIOUS was applied to evaluate microglial and astrocytic activation in histological tissue. MORPHIOUS was further evaluated on hippocampal sections of TgCRND8 mice, a model of amyloidosis that is prone to microglial and astrocytic activation.
RESULTS RESULTS
MORPHIOUS defined two classes of microglia, termed focal and proximal, that are spatially adjacent to the activating stimulus. Focal and proximal microglia demonstrated activity-associated features, including increased levels of ionized calcium-binding adapter molecule 1 expression, enlarged soma size, and deramification. MORPHIOUS further identified clusters of astrocytes characterized by activity-related changes in glial fibrillary acidic protein expression and branching. To validate these classifications following FUS, co-localization with activation markers were assessed. Focal and proximal microglia co-localized with the transforming growth factor beta 1, while proximal astrocytes co-localized with Nestin. In TgCRND8 mice, microglial and astrocytic activation clusters were found to correlate with amyloid-β plaque load. Thus, by only referencing control microglial and astrocytic morphologies, MORPHIOUS identified regions of interest corresponding to microglial and astrocytic activation.
CONCLUSIONS CONCLUSIONS
Overall, our algorithm is a reliable and sensitive method for characterizing microglial and astrocytic activation following FUS-induced BBB permeability and in animal models of neurodegeneration.

Identifiants

pubmed: 35093113
doi: 10.1186/s12974-021-02376-9
pii: 10.1186/s12974-021-02376-9
pmc: PMC8800241
doi:

Substances chimiques

Glial Fibrillary Acidic Protein 0

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Pagination

24

Subventions

Organisme : CIHR
ID : 137064
Pays : Canada
Organisme : CIHR
ID : 166184
Pays : Canada
Organisme : Weston Brain Institute
ID : TR130117

Informations de copyright

© 2022. The Author(s).

Références

Cell. 2017 Jun 15;169(7):1276-1290.e17
pubmed: 28602351
Immunity. 2017 Sep 19;47(3):566-581.e9
pubmed: 28930663
J Neurosci. 2012 May 2;32(18):6391-410
pubmed: 22553043
Front Cell Neurosci. 2017 Aug 08;11:235
pubmed: 28848398
Mol Neurobiol. 2014 Jun;49(3):1422-34
pubmed: 24395130
Mol Oncol. 2014 Jun;8(4):783-98
pubmed: 24725481
Neuroinformatics. 2019 Jul;17(3):373-389
pubmed: 30406865
J Biol Chem. 2001 Jun 15;276(24):21562-70
pubmed: 11279122
Theranostics. 2018 Sep 09;8(17):4837-4855
pubmed: 30279741
Acta Neuropathol. 2010 Jan;119(1):7-35
pubmed: 20012068
Exp Neurol. 2013 Oct;248:16-29
pubmed: 23707300
J Vis Exp. 2018 Jun 5;(136):
pubmed: 29939190
Immunity. 2019 Jan 15;50(1):253-271.e6
pubmed: 30471926
PLoS One. 2018 Jan 17;13(1):e0186937
pubmed: 29342151
J Neuroinflammation. 2016 Jun 17;13(1):153
pubmed: 27317566
Nat Rev Neurol. 2017 Jul;13(7):420-433
pubmed: 28524175
PLoS One. 2013 Jul 23;8(7):e69143
pubmed: 23935940
Nat Rev Neurol. 2015 Jan;11(1):56-64
pubmed: 25385337
Anat Rec (Hoboken). 2013 Mar;296(3):378-81
pubmed: 23382140
J Neuroinflammation. 2013 Jan 11;10:4
pubmed: 23311642
Front Neurosci. 2017 Apr 18;11:209
pubmed: 28458629
Brain. 2015 May;138(Pt 5):1138-59
pubmed: 25823474
Nat Methods. 2012 Jun 28;9(7):676-82
pubmed: 22743772
Physiol Rev. 2014 Oct;94(4):1077-98
pubmed: 25287860
Neural Comput. 2001 Jul;13(7):1443-71
pubmed: 11440593
Glia. 2019 Aug;67(8):1496-1509
pubmed: 30983036
Conf Proc IEEE Eng Med Biol Soc. 2005;2005:6411-4
pubmed: 17281735
Cell Death Dis. 2013 Mar 07;4:e525
pubmed: 23470532
Bioinformatics. 2016 Nov 15;32(22):3532-3534
pubmed: 27412086
Nat Commun. 2021 May 21;12(1):3015
pubmed: 34021136
J Clin Invest. 2017 Jan 3;127(1):280-292
pubmed: 27893460
Neurobiol Aging. 2010 Apr;31(4):578-90
pubmed: 18586353
Sci Rep. 2017 May 8;7(1):1576
pubmed: 28484229
Am J Pathol. 2011 Sep;179(3):1373-84
pubmed: 21777559
Sci Rep. 2017 Jun 14;7(1):3521
pubmed: 28615717
Nat Biotechnol. 2006 Dec;24(12):1565-7
pubmed: 17160063
J Neuroinflammation. 2011 Dec 10;8:174
pubmed: 22152337
J Neuroinflammation. 2019 Jul 25;16(1):155
pubmed: 31345243
Nat Neurosci. 2021 Mar;24(3):312-325
pubmed: 33589835
Nat Methods. 2018 Jan;15(1):5-6
pubmed: 30100821
Nat Neurosci. 2013 May;16(5):580-6
pubmed: 23542688
Comput Struct Biotechnol J. 2018 Feb 09;16:34-42
pubmed: 30275936
Stroke. 2001 May;32(5):1208-15
pubmed: 11340235
Neurobiol Dis. 1995 Apr;2(2):79-85
pubmed: 8980011
Expert Opin Drug Deliv. 2014 May;11(5):711-21
pubmed: 24650132
Front Cell Neurosci. 2013 Jan 30;7:3
pubmed: 23386810
Radiology. 2012 Apr;263(1):96-106
pubmed: 22332065
Sci Transl Med. 2015 Mar 11;7(278):278ra33
pubmed: 25761889
Front Cell Neurosci. 2018 Apr 19;12:106
pubmed: 29725290
Lab Invest. 2018 Jul;98(7):844-855
pubmed: 29849125
Nat Neurosci. 2016 Jul 26;19(8):987-91
pubmed: 27459405

Auteurs

Joseph Silburt (J)

Biological Sciences, Hurvitz Brain Sciences Research Program, Sunnybrook Research Institute, Sunnybrook Health Sciences Centre, 2075 Bayview Avenue, Toronto, ON, M4N 3M5, Canada. joey.silburt@mail.utoronto.ca.
Department of Laboratory Medicine and Pathobiology, Temerty Faculty of Medicine, University of Toronto, Toronto, ON, Canada. joey.silburt@mail.utoronto.ca.

Isabelle Aubert (I)

Biological Sciences, Hurvitz Brain Sciences Research Program, Sunnybrook Research Institute, Sunnybrook Health Sciences Centre, 2075 Bayview Avenue, Toronto, ON, M4N 3M5, Canada. isabelle.aubert@utoronto.ca.
Department of Laboratory Medicine and Pathobiology, Temerty Faculty of Medicine, University of Toronto, Toronto, ON, Canada. isabelle.aubert@utoronto.ca.

Articles similaires

Robotic Surgical Procedures Animals Humans Telemedicine Models, Animal

Odour generalisation and detection dog training.

Lyn Caldicott, Thomas W Pike, Helen E Zulch et al.
1.00
Animals Odorants Dogs Generalization, Psychological Smell
Animals TOR Serine-Threonine Kinases Colorectal Neoplasms Colitis Mice
Animals Tail Swine Behavior, Animal Animal Husbandry

Classifications MeSH