Dataset Information

Machine Learning to Quantitate Neutrophil NETosis.

ABSTRACT: We introduce machine learning (ML) to perform classification and quantitation of images of nuclei from human blood neutrophils. Here we assessed the use of convolutional neural networks (CNNs) using free, open source software to accurately quantitate neutrophil NETosis, a recently discovered process involved in multiple human diseases. CNNs achieved >94% in performance accuracy in differentiating NETotic from non-NETotic cells and vastly facilitated dose-response analysis and screening of the NETotic response in neutrophils from patients. Using only features learned from nuclear morphology, CNNs can distinguish between NETosis and necrosis and between distinct NETosis signaling pathways, making them a precise tool for NETosis detection. Furthermore, by using CNNs and tools to determine object dispersion, we uncovered differences in NETotic nuclei clustering between major NETosis pathways that is useful in understanding NETosis signaling events. Our study also shows that neutrophils from patients with sickle cell disease were unresponsive to one of two major NETosis pathways. Thus, we demonstrate the design, performance, and implementation of ML tools for rapid quantitative and qualitative cell analysis in basic science.

SUBMITTER: Elsherif L

PROVIDER: S-EPMC6858304 | biostudies-literature | 2019 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine Learning to Quantitate Neutrophil NETosis.

Elsherif Laila L Sciaky Noah N Metts Carrington A CA Modasshir Md M Rekleitis Ioannis I Burris Christine A CA Walker Joshua A JA Ramadan Nadeem N Leisner Tina M TM Holly Stephen P SP Cowles Martis W MW Ataga Kenneth I KI Cooper Joshua N JN Parise Leslie V LV

Scientific reports 20191115 1

We introduce machine learning (ML) to perform classification and quantitation of images of nuclei from human blood neutrophils. Here we assessed the use of convolutional neural networks (CNNs) using free, open source software to accurately quantitate neutrophil NETosis, a recently discovered process involved in multiple human diseases. CNNs achieved >94% in performance accuracy in differentiating NETotic from non-NETotic cells and vastly facilitated dose-response analysis and screening of the NE ...[more]

PMID: 31729453

Similar Datasets

Project description:Acetylation is an important post translational modification of histone that plays a role in regulation of physiological and pathological process in the body. We have recently shown that the inhibition of histone deacetylases (HDAC) by low concentrations of HDAC inhibitors (HDACis), belinostat (up to 0.25 µM) and panobinostat (up to 0.04 µM) promote histone acetylation (e.g., AcH4) and neutrophil extracellular trap formation (NETosis). Clinical use of belinostat and panobinostat often leads to neutropenia and the in vivo concentrations vary with time and tissue locations. However, the effects of different concentrations of these HDACis on neutrophil death are not fully understood. We considered that increasing concentrations of belinostat and panobinostat could alter the type of neutrophil death. To test this hypothesis, we treated human neutrophils with belinostat and panobinostat in the presence or absence of agonists that promote NOX-dependent NETosis (phorbol myristate acetate or lipopolysaccharide from Escherichia coli 0128) and NOX-independent NETosis (calcium ionophores A23187 or ionomycin from Streptomyces conglobatus). Increasing concentrations of HDACis induced histone acetylation in a dose-dependent manner. ROS analyses showed that increasing concentrations of HDACis, increased the degree of NOX-derived ROS production. Higher levels (>1 µM belinostat and >0.2 µM panobinostat) of AcH4 resulted in a significant inhibition of spontaneous as well as the NOX-dependent and -independent NETosis. By contrast, the degree of neutrophil apoptosis significantly increased, particularly in non-activated cells. Collectively, this study establishes that increasing concentrations of belinostat and panobinostat initially increases NETosis but subsequently reduces NETosis or switches the form of cell death to apoptosis. This new information indicates that belinostat and panobinostat can induce different types of neutrophil death and may induce neutropenia and regulate inflammation at different concentrations.

Dataset Information

Machine Learning to Quantitate Neutrophil NETosis.

Publications

Machine Learning to Quantitate Neutrophil NETosis.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets