A guide to automated apoptosis detection: How to make sense of imaging flow cytometry data

Machine learning implementation strategy in imaging and impedance flow cytometry

Imaging and impedance flow cytometry is a label-free technique that has shown promise as a potential replacement for standard flow cytometry. This is due to its ability to provide rich information and archive high-throughput analysis. Recently, significant efforts have been made to leverage machine learning for processing the abundant data generated by those techniques, enabling rapid and accurate analysis. Harnessing the power of machine learning, imaging and impedance flow cytometry has demonstrated its capability to address various complex phenotyping scenarios. Herein, we present a comprehensive overview of the detailed strategies for implementing machine learning in imaging and impedance flow cytometry. We initiate the discussion by outlining the commonly employed setup to acquire the data (i.e., image or signal) from the cell. Subsequently, we delve into the necessary processes for extracting features from the acquired image or signal data. Finally, we discuss how these features can be utilized for cell phenotyping through the application of machine learning algorithms. Furthermore, we discuss the existing challenges and provide insights for future perspectives of intelligent imaging and impedance flow cytometry.

Recent Approaches to Design and Analysis of Electrical Impedance Systems for Single Cells Using Machine Learning

Individual cells have many unique properties that can be quantified to develop a holistic understanding of a population. This can include understanding population characteristics, identifying subpopulations, or elucidating outlier characteristics that may be indicators of disease. Electrical impedance measurements are rapid and label-free for the monitoring of single cells and generate large datasets of many cells at single or multiple frequencies. To increase the accuracy and sensitivity of measurements and define the relationships between impedance and biological features, many electrical measurement systems have incorporated machine learning (ML) paradigms for control and analysis. Considering the difficulty capturing complex relationships using traditional modelling and statistical methods due to population heterogeneity, ML offers an exciting approach to the systemic collection and analysis of electrical properties in a data-driven way. In this work, we discuss incorporation of ML to improve the field of electrical single cell analysis by addressing the design challenges to manipulate single cells and sophisticated analysis of electrical properties that distinguish cellular changes. Looking forward, we emphasize the opportunity to build on integrated systems to address common challenges in data quality and generalizability to save time and resources at every step in electrical measurement of single cells.

Machine learning-based approaches for identifying human blood cells harboring CRISPR-mediated fetal chromatin domain ablations

Two common hemoglobinopathies, sickle cell disease (SCD) and β-thalassemia, arise from genetic mutations within the β-globin gene. In this work, we identified a 500-bp motif (Fetal Chromatin Domain, FCD) upstream of human ϒ-globin locus and showed that the removal of this motif using CRISPR technology reactivates the expression of ϒ-globin. Next, we present two different cell morphology-based machine learning approaches that can be used identify human blood cells (KU-812) that harbor CRISPR-mediated FCD genetic modifications. Three candidate models from the first approach, which uses multilayer perceptron algorithm (MLP 20-26, MLP26-18, and MLP 30-26) and flow cytometry-derived cellular data, yielded 0.83 precision, 0.80 recall, 0.82 accuracy, and 0.90 area under the ROC (receiver operating characteristic) curve when predicting the edited cells. In comparison, the candidate model from the second approach, which uses deep learning (T2D5) and DIC microscopy-derived imaging data, performed with less accuracy (0.80) and ROC AUC (0.87). We envision that equivalent machine learning-based models can complement currently available genotyping protocols for specific genetic modifications which result in morphological changes in human cells.

Feature selection revisited in the single-cell era

Recent advances in single-cell biotechnologies have resulted in high-dimensional datasets with increased complexity, making feature selection an essential technique for single-cell data analysis. Here, we revisit feature selection techniques and summarise recent developments. We review their application to a range of single-cell data types generated from traditional cytometry and imaging technologies and the latest array of single-cell omics technologies. We highlight some of the challenges and future directions and finally consider their scalability and make general recommendations on each type of feature selection method. We hope this review stimulates future research and application of feature selection in the single-cell era.

Application of Micropore Device for Accurate, Easy, and Rapid Discrimination of Saccharomyces pastorianus from Dekkera spp

Traceability analysis, such as identification and discrimination of yeasts used for fermentation, is important for ensuring manufacturing efficiency and product safety during brewing. However, conventional methods based on morphological and physiological properties have disadvantages such as time consumption and low sensitivity. In this study, the resistive pulse method (RPM) was employed to discriminate between Saccharomyces pastorianus and Dekkera anomala and S. pastorianus and D. bruxellensis by measuring the ionic current response of cells flowing through a microsized pore. The height and shape of the pulse signal were used for the simultaneous measurement of the size, shape, and surface charge of individual cells. Accurate discrimination of S. pastorianus from Dekkera spp. was observed with a recall rate of 96.3 ± 0.8%. Furthermore, budding S. pastorianus was quantitatively detected by evaluating the shape of the waveform of the current ionic blockade. We showed a proof-of-concept demonstration of RPM for the detection of contamination of Dekkera spp. in S. pastorianus and for monitoring the fermentation of S. pastorianus through the quantitative detection of budding cells.

Evaluation of DNA double-strand break repair capacity in human cells: Critical overview of current functional methods

DNA double-strand breaks (DSBs) are highly deleterious lesions, responsible for mutagenesis, chromosomal translocation or cell death. DSB repair (DSBR) is therefore a critical part of the DNA damage response (DDR) to restore molecular and genomic integrity. In humans, this process is achieved through different pathways with various outcomes. The balance between DSB repair activities varies depending on cell types, tissues or individuals. Over the years, several methods have been developed to study variations in DSBR capacity. Here, we mainly focus on functional techniques, which provide dynamic information regarding global DSB repair proficiency or the activity of specific pathways. These methods rely on two kinds of approaches. Indirect techniques, such as pulse field gel electrophoresis (PFGE), the comet assay and immunofluorescence (IF), measure DSB repair capacity by quantifying the time-dependent decrease in DSB levels after exposure to a DNA-damaging agent. On the other hand, cell-free assays and reporter-based methods directly track the repair of an artificial DNA substrate. Each approach has intrinsic advantages and limitations and despite considerable efforts, there is currently no ideal method to quantify DSBR capacity. All techniques provide different information and can be regarded as complementary, but some studies report conflicting results. Parameters such as the type of biological material, the required equipment or the cost of analysis may also limit available options. Improving currently available methods measuring DSBR capacity would be a major step forward and we present direct applications in mechanistic studies, drug development, human biomonitoring and personalized medicine, where DSBR analysis may improve the identification of patients eligible for chemo- and radiotherapy.

Cell morphology-based machine learning models for human cell state classification

Herein, we implement and access machine learning architectures to ascertain models that differentiate healthy from apoptotic cells using exclusively forward (FSC) and side (SSC) scatter flow cytometry information. To generate training data, colorectal cancer HCT116 cells were subjected to miR-34a treatment and then classified using a conventional Annexin V/propidium iodide (PI)-staining assay. The apoptotic cells were defined as Annexin V-positive cells, which include early and late apoptotic cells, necrotic cells, as well as other dying or dead cells. In addition to fluorescent signal, we collected cell size and granularity information from the FSC and SSC parameters. Both parameters are subdivided into area, height, and width, thus providing a total of six numerical features that informed and trained our models. A collection of logistical regression, random forest, k-nearest neighbor, multilayer perceptron, and support vector machine was trained and tested for classification performance in predicting cell states using only the six aforementioned numerical features. Out of 1046 candidate models, a multilayer perceptron was chosen with 0.91 live precision, 0.93 live recall, 0.92 live f value and 0.97 live area under the ROC curve when applied on standardized data. We discuss and highlight differences in classifier performance and compare the results to the standard practice of forward and side scatter gating, typically performed to select cells based on size and/or complexity. We demonstrate that our model, a ready-to-use module for any flow cytometry-based analysis, can provide automated, reliable, and stain-free classification of healthy and apoptotic cells using exclusively size and granularity information.

Innovative Betulin Nanosuspension exhibits enhanced anticancer activity in a Triple Negative Breast Cancer Cell line and Zebrafish angiogenesis model

We present a nanosuspension of betulin, a BCS class II anticancer drug, particularly effective against resistant breast cancer. As anticancer efficacy of betulin is hampered by poor aqueous solubility, a nanosuspension with surface area was considered to enhance efficacy. An innovative approach wherein the betulin nanosuspension is generated instantaneously in situ, by adding a betulin preconcentrate (BeTPC) comprising drug and excipients, to aqueous medium, is successfully demonstrated. The optimal BeTPC when added to isotonic dextrose solution instantaneously generated an in situ nanosuspension (BeTNS-15) with high precipitation efficiency (92.7 ± 1.21%), average particle size (383.74 ± 7.24 nm) and good stability as per ICH guidelines. TEM revealed elongated particles while DSC and XRD indicated partial amorphization. Significantly higher cytotoxicity of BeTNS-15 (IC₅₀ 38.44 µg/ml) compared to betulin (BetS) (IC₅₀ 69.54 µg/ml) in the resistant triple negative human breast cancer cell line MDA-MB-231, was attributed to high intracellular uptake confirmed by HPLC and Imaging Flow cytometry (IFC). IFC confirmed superior anti-cancer efficacy of BeTNS-15 mediated by mitochondrial membrane disruption and inhibition of the G0/G1 phase. BeTNS-15 also exhibited significantly greater anti-angiogenic efficacy (p < 0.05) in the zebrafish model confirming superior efficacy. Simplicity of the innovative in situ approach coupled with superior efficacy proposes BeTNS as an innovative and highly promising anticancer formulation.

Effect of Electrolyte Concentration on Cell Sensing by Measuring Ionic Current Waveform through Micropores

Immunostaining has been widely used in cancer prognosis for the quantitative detection of cancer cells present in the bloodstream. However, conventional detection methods based on the target membrane protein expression exhibit the risk of missing cancer cells owing to variable protein expressions. In this study, the resistive pulse method (RPM) was employed to discriminate between cultured cancer cells (NCI-H1650) and T lymphoblastoid leukemia cells (CCRF-CEM) by measuring the ionic current response of cells flowing through a micro-space. The height and shape of a pulse signal were used for the simultaneous measurement of size, deformability, and surface charge of individual cells. An accurate discrimination of cancer cells could not be obtained using 1.0 × phosphate-buffered saline (PBS) as an electrolyte solution to compare the size measurements by a microscopic observation. However, an accurate discrimination of cancer cells with a discrimination error rate of 4.5 ± 0.5% was achieved using 0.5 × PBS containing 2.77% glucose as the electrolyte solution. The potential application of RPM for the accurate discrimination of cancer cells from leukocytes was demonstrated through the measurement of the individual cell size, deformability, and surface charge in a solution with a low electrolyte concentration.

Dissecting Response to Cancer Immunotherapy by Applying Bayesian Network Analysis to Flow Cytometry Data

Cancer immunotherapy, specifically immune checkpoint blockade, has been found to be effective in the treatment of metastatic cancers. However, only a subset of patients achieve clinical responses. Elucidating pretreatment biomarkers predictive of sustained clinical response is a major research priority. Another research priority is evaluating changes in the immune system before and after treatment in responders vs. nonresponders. Our group has been studying immune networks as an accurate reflection of the global immune state. Flow cytometry (FACS, fluorescence-activated cell sorting) data characterizing immune cell panels in peripheral blood mononuclear cells (PBMC) from gastroesophageal adenocarcinoma (GEA) patients were used to analyze changes in immune networks in this setting. Here, we describe a novel computational pipeline to perform secondary analyses of FACS data using systems biology/machine learning techniques and concepts. The pipeline is centered around comparative Bayesian network analyses of immune networks and is capable of detecting strong signals that conventional methods (such as FlowJo manual gating) might miss. Future studies are planned to validate and follow up the immune biomarkers (and combinations/interactions thereof) associated with clinical responses identified with this computational pipeline.

Automated Classification of Apoptosis in Phase Contrast Microscopy Using Capsule Network

Automatic and accurate classification of apoptosis, or programmed cell death, will facilitate cell biology research. The state-of-the-art approaches in apoptosis classification use deep convolutional neural networks (CNNs). However, these networks are not efficient in encoding the part-whole relationships, thus requiring a large number of training samples to achieve robust generalization. This paper proposes an efficient variant of capsule networks (CapsNets) as an alternative to CNNs. Extensive experimental results demonstrate that the proposed CapsNets achieve competitive performances in target cell apoptosis classification, while significantly outperforming CNNs when the number of training samples is small. To utilize temporal information within microscopy videos, we propose a recurrent CapsNet constructed by stacking a CapsNet and a bi-directional long short-term recurrent structure. Our experiments show that when considering temporal constraints, the recurrent CapsNet achieves 93.8% accuracy and makes significantly more consistent prediction than NNs.

Molecular mechanism of antimicrobial activity of chlorhexidine against carbapenem-resistant Acinetobacter baumannii

Acinetobacter baumannii causes hospital-acquired infections, especially in those with impaired immune function. Biocides or disinfectants are widely used antibacterial agents used to eradicate the effect of A. baumannii on inanimate objects and health care environments. In the current study, the antimicrobial activity of chlorhexidine has been investigated against carbapenem-resistant (RS-307, RS-7434, RS-6694, and RS-122), and sensitive (ATCC-19606 and RS-10953) strains of A. baumannii. We have determined growth kinetics, antimicrobial susceptibility, ROS production, lipid peroxidation, cell viability using flow cytometry assay (FACS), and membrane integrity by scanning electron microscope (SEM). The effect of chlorhexidine on the bacterial membrane has also been investigated using Fourier transform infrared (FTIR) spectroscopy. The present study showed that 32μg/ml chlorhexidine treatment results in the decreased bacterial growth, CFU count and cell viability. The antibacterial activity of chlorhexidine is due to the elevated ROS production and higher lipid peroxidation. These biochemical changes result in the membrane damage and alteration in the membrane proteins, phospholipids, carbohydrates, nucleic acids as evident from the FTIR and SEM data. Therefore, chlorhexidine has the potential to be used in the hospital setups to remove the spread of A. baumannii.

Development of a high-throughput γ-H2AX assay based on imaging flow cytometry

Background

Measurement of γ-H2AX foci levels in cells provides a sensitive and reliable method for quantitation of the radiation-induced DNA damage response. The objective of the present study was to develop a rapid, high-throughput γ-H2AX assay based on imaging flow cytometry (IFC) using the ImageStream®^X Mk II (ISX) platform to evaluate DNA double strand break (DSB) repair kinetics in human peripheral blood cells after exposure to ionizing irradiation.

Methods

The γ-H2AX protocol was developed and optimized for small volumes (100 μL) of human blood in Matrix™ 96-tube format. Blood cell lymphocytes were identified and captured by ISX INSPIRE™ software and analyzed by Data Exploration and Analysis Software.

Results

Dose- and time-dependent γ-H2AX levels corresponding to radiation exposure were measured at various time points over 24 h using the IFC system. γ-H2AX fluorescence intensity at 1 h after exposure, increased linearly with increasing radiation dose (R² = 0.98) for the four human donors tested, whereas the dose response for the mean number of γ-H2AX foci/cell was not as robust (R² = 0.81). Radiation-induced γ-H2AX levels rapidly increased within 30 min and reached a maximum by ~ 1 h, after which time there was fast decline by 6 h, followed by a much slower rate of disappearance up to 24 h. A mathematical approach for quantifying DNA repair kinetics using the rate of γ-H2AX decay (decay constant, K_dec), and yield of residual unrepaired breaks (F_res) demonstrated differences in individual repair capacity between the healthy donors.

Conclusions

The results indicate that the IFC-based γ-H2AX protocol may provide a practical and high-throughput platform for measurements of individual global DNA DSB repair capacity which can facilitate precision medicine by predicting individual radiosensitivity and risk of developing adverse effects related to radiotherapy treatment.

Electronic supplementary material

The online version of this article (10.1186/s13014-019-1344-7) contains supplementary material, which is available to authorized users.

Design, Synthesis and in Vitro Tumor Cytotoxicity Evaluation of 3,5-Diamino-N-substituted Benzamide Derivatives as Novel GSK-3β Small Molecule Inhibitors

Glycogen synthase kinase-3 (GSK-3) plays an important regulatory role in various signaling pathways; such as PI3 K/AKT, which is closely related to the occurrence and development of tumors. At present, the most reported active GSK-3 inhibitors have the same structure: lactam ring or amide structure. To find out the GSK-3β small molecule inhibitor with novel, safe, efficient and more uncomplicated synthesis method, we analyzed in-depth reported crystal-binding patterns of GSK-3β small molecule inhibitor with GSK-3β protein, and designed and synthesized 17 non-reported 3,5-diamino-N-substituted benzamide compounds. Their structures were confirmed by ¹ H-NMR, ¹³ C-NMR, and HR-MS. The preliminary screening of tumor cytotoxicity of compounds in vitro was detected by MTT, and their structure-activity relationships were illustrated. The results have shown that 3,5-diamino-N-[3-(trifluoromethyl)phenyl]benzamide (4d) exhibited significant tumor cytotoxicity against human colon cancer cells (HCT-116) with IC₅₀ of 8.3 μm and showed commendable selectivity to GSK-3β. In addition, Compound 4d induced apoptosis to some extent and possessed modest PK properties.

Quantitative single cell analysis uncovers the life/death decision in CD95 network

CD95/Fas/APO-1 is a member of the death receptor family that triggers apoptotic and anti-apoptotic responses in particular, NF-κB. These responses are characterized by a strong heterogeneity within a population of cells. To determine how the cell decides between life and death we developed a computational model supported by imaging flow cytometry analysis of CD95 signaling. Here we show that CD95 stimulation leads to the induction of caspase and NF-κB pathways simultaneously in one cell. The related life/death decision strictly depends on cell-to-cell variability in the formation of the death-inducing complex (DISC) on one side (extrinsic noise) vs. stochastic gene expression of the NF-κB pathway on the other side (intrinsic noise). Moreover, our analysis has uncovered that the stochasticity in apoptosis and NF-kB pathways leads not only to survival or death of a cell, but also causes a third type of response to CD95 stimulation that we termed ambivalent response. Cells in the ambivalent state can undergo cell death or survive which was subsequently validated by experiments. Taken together, we have uncovered how these two competing pathways control the fate of a cell, which in turn plays an important role for development of anti-cancer therapies.

Activation of death receptor (DR) family has been reported to activate both apoptotic as well as anti-apoptotic responses. Molecular mechanisms underlying the intricate details of this crosstalk have not been established yet. Here we show that these pathways are triggered simultaneously in one cell. Furthermore, using stochastic computational modeling we uncovered how an individual cell undergoes apoptosis, while other cells survive upon the same DR activation conditions. This was only possible by combination of computational modeling supported by experimental validation based on the state of the art single cell analysis. The latter included cutting edge technology of imaging flow cytometry, which combines microscopy and flow cytometry in one measurement circuit enabling quantitative analysis of endogenous cellular protein levels estimated from a large number of cells simultaneously. This allowed to shed the light on the question how a single cell possibly avoids apoptosis, which is a highly actual topic in the field of cancer research and development of efficient anti-cancer therapies.