Deep Analysis of Mitochondria and Cell Health Using Machine Learning

Zahedi, Atena; On, Vincent; Phandthong, Rattapol; Chaili, Angela; Remark, Guadalupe; Bhanu, Bir; Talbot, Prue

doi:10.1038/s41598-018-34455-y

Cited by 46 publications

(38 citation statements)

References 60 publications

(91 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Mitochondria undergoes coordinated fusion and fission cycles. In addition, they have an inner ability to sense their health condition, and stressed mitochondria activate compensatory quality control mechanism involving degradation of damaged mitochondria (mitophagy) and fission making them an excellent indicator for estimating cell state of health [62]. Changes in mitochondria dynamics and mitochondria membrane potential lead to cellular dysfunction in aged organisms.…”

Section: Discussionmentioning

confidence: 99%

Age-dependent impairment of adipose-derived stem cells isolated from horses

et al. 2020

View full text Add to dashboard Cite

BackgroundProgressive loss of cell functionality caused by an age-related impairment in cell metabolism concerns not only mature specialized cells but also its progenitors, which significantly reduces their regenerative potential. Adipose-derived stem cells (ASCs) are most commonly used in veterinary medicine as an alternative treatment option in ligaments and cartilage injuries, especially in case of high-value sport horses. Therefore, the main aim of this study was to identify the molecular alternations in ASCs derived from three age-matched horse groups: young (< 5), middle-aged (5–15), and old (> 15 years old).MethodsASCs were isolated from three age-matched horse groups using an enzymatic method. Molecular changes were assessed using qRT-PCR, ELISA and western blot methods, flow cytometry-based system, and confocal and scanning electron microscopy.ResultsOur findings showed that ASCs derived from the middle-aged and old groups exhibited a typical senescence phenotype, such as increased percentage of G1/G0-arrested cells, binucleation, enhanced β-galactosidase activity, and accumulation of γH2AX foci, as well as a reduction in cell proliferation. Moreover, aged ASCs were characterized by increased gene expression of pro-inflammatory cytokines and miRNAs (interleukin 8 (IL-8), IL-1β, tumor necrosis factor α (TNF-α), miR-203b-5p, and miR-16-5p), as well as apoptosis markers (p21, p53, caspase-3, caspase-9). In addition, our study revealed that the protein level of mitofusin 1 (MFN1) markedly decreased with increasing age. Aged ASCs also displayed a reduction in mRNA levels of genes involved in stem cell homeostasis and homing, like TET-3, TET-3 (TET family), and C-X-C chemokine receptor type 4 (CXCR4), as well as protein expression of DNA methyltransferase (DNMT1) and octamer transcription factor 3/4 (Oct 3/4). Furthermore, we observed a higher splicing ratio of XBP1 (X-box binding protein 1) mRNA, indicating elevated inositol-requiring enzyme 1 (IRE-1) activity and, consequently, increased endoplasmic reticulum (ER) stress. We also observed reduced levels of glucose transporter 4 (GLUT-4) and insulin receptor (INSR) which indicated impaired insulin sensitivity.ConclusionsObtained data suggest that ASCs derived from horses older than 5 years old exhibited several molecular alternations which markedly limit their regenerative capacity. The results provide valuable information that allows for a better understanding of the molecular events occurring in ASCs in the course of aging and may help to identify new potential drug targets to restore their regenerative potential.Graphical abstract

show abstract

Section: Discussionmentioning

confidence: 99%

Age-dependent impairment of adipose-derived stem cells isolated from horses

et al. 2020

View full text Add to dashboard Cite

show abstract

“…However, recent advances in imaging techniques and the availability of computational resources make more advanced analysis of morphology feasible. Several groups have developed software and codes/macros for the unbiased measurement and classification of mitochondrial morphology 23 – 26 . To further these efforts, we developed a machine-learning based classification pipeline for the identification of distinct physiological and pathological morphologies using free and open-source software with 2D and 3D capabilities.…”

Section: Discussionmentioning

confidence: 99%

“…Studies typically utilize a qualitative or semi-quantitative approach by developing a scoring system of fission/fusion profiles or binning mitochondria based on length 19 – 22 , both of which lack, on a large-scale, sampling size, and an accurate and precise assessment of physiologically relevant mitochondrial morphologies. To overcome this, recent studies have shifted to utilizing computational image analysis, commonly referred to as image cytometry, which limits observer and selection bias in morphological evaluations and demonstrates high throughput capabilities 23 – 26 .…”

Section: Introductionmentioning

confidence: 99%

Machine learning-based classification of mitochondrial morphology in primary neurons and brain

Fogo

Anzell

Maheras

et al. 2021

Sci Rep

View full text Add to dashboard Cite

The mitochondrial network continually undergoes events of fission and fusion. Under physiologic conditions, the network is in equilibrium and is characterized by the presence of both elongated and punctate mitochondria. However, this balanced, homeostatic mitochondrial profile can change morphologic distribution in response to various stressors. Therefore, it is imperative to develop a method that robustly measures mitochondrial morphology with high accuracy. Here, we developed a semi-automated image analysis pipeline for the quantitation of mitochondrial morphology for both in vitro and in vivo applications. The image analysis pipeline was generated and validated utilizing images of primary cortical neurons from transgenic mice, allowing genetic ablation of key components of mitochondrial dynamics. This analysis pipeline was further extended to evaluate mitochondrial morphology in vivo through immunolabeling of brain sections as well as serial block-face scanning electron microscopy. These data demonstrate a highly specific and sensitive method that accurately classifies distinct physiological and pathological mitochondrial morphologies. Furthermore, this workflow employs the use of readily available, free open-source software designed for high throughput image processing, segmentation, and analysis that is customizable to various biological models.

show abstract

“…Morphological measurements: MiA. Scientists have adopted different approaches to quantify mitochondrial morphology in cells 8,[13][14][15][16][17][18][19][20][21] . A closer analysis of the developed methodologies reveals that they lie within two major categories 22 : (i) Morphological classification of mitochondria.…”

Section: Description Of Toolsmentioning

confidence: 99%

Mito Hacker: a set of tools to enable high-throughput analysis of mitochondrial network morphology

Rohani

Kashatus

Sessions

et al. 2020

Sci Rep

View full text Add to dashboard Cite

Mitochondria are highly dynamic organelles that can exhibit a wide range of morphologies. Mitochondrial morphology can differ significantly across cell types, reflecting different physiological needs, but can also change rapidly in response to stress or the activation of signaling pathways. Understanding both the cause and consequences of these morphological changes is critical to fully understanding how mitochondrial function contributes to both normal and pathological physiology. However, while robust and quantitative analysis of mitochondrial morphology has become increasingly accessible, there is a need for new tools to generate and analyze large data sets of mitochondrial images in high throughput. The generation of such datasets is critical to fully benefit from rapidly evolving methods in data science, such as neural networks, that have shown tremendous value in extracting novel biological insights and generating new hypotheses. Here we describe a set of three computational tools, Cell Catcher, Mito Catcher and MiA, that we have developed to extract extensive mitochondrial network data on a single-cell level from multi-cell fluorescence images. Cell Catcher automatically separates and isolates individual cells from multi-cell images; Mito Catcher uses the statistical distribution of pixel intensities across the mitochondrial network to detect and remove background noise from the cell and segment the mitochondrial network; MiA uses the binarized mitochondrial network to perform more than 100 mitochondria-level and cell-level morphometric measurements. To validate the utility of this set of tools, we generated a database of morphological features for 630 individual cells that encode 0, 1 or 2 alleles of the mitochondrial fission GTPase Drp1 and demonstrate that these mitochondrial data could be used to predict Drp1 genotype with 87% accuracy. Together, this suite of tools enables the high-throughput and automated collection of detailed and quantitative mitochondrial structural information at a single-cell level. Furthermore, the data generated with these tools, when combined with advanced data science approaches, can be used to generate novel biological insights.

show abstract

Deep Analysis of Mitochondria and Cell Health Using Machine Learning

Cited by 46 publications

References 60 publications

Age-dependent impairment of adipose-derived stem cells isolated from horses

Age-dependent impairment of adipose-derived stem cells isolated from horses

Machine learning-based classification of mitochondrial morphology in primary neurons and brain

Mito Hacker: a set of tools to enable high-throughput analysis of mitochondrial network morphology

Contact Info

Product

Resources

About