Intelligent Image-Activated Cell Sorting

Raman image-activated cell sorting

The advent of image-activated cell sorting and imaging-based cell picking has advanced our knowledge and exploitation of biological systems in the last decade. Unfortunately, they generally rely on fluorescent labeling for cellular phenotyping, an indirect measure of the molecular landscape in the cell, which has critical limitations. Here we demonstrate Raman image-activated cell sorting by directly probing chemically specific intracellular molecular vibrations via ultrafast multicolor stimulated Raman scattering (SRS) microscopy for cellular phenotyping. Specifically, the technology enables real-time SRS-image-based sorting of single live cells with a throughput of up to ~100 events per second without the need for fluorescent labeling. To show the broad utility of the technology, we show its applicability to diverse cell types and sizes. The technology is highly versatile and holds promise for numerous applications that are previously difficult or undesirable with fluorescence-based technologies.

Most current cell sorting methods are based on fluorescence detection with no imaging capability. Here the authors generate and use Raman image-activated cell sorting with a throughput of around 100 events per second, providing molecular images with no need for labeling.

Phenome-Genome Profiling of Single Bacterial Cell by Raman-Activated Gravity-Driven Encapsulation and Sequencing

The small size and low DNA amount of bacterial cells have hindered establishing phenome-genome links in a precisely indexed, one-cell-per-reaction manner. Here, Raman-Activated Gravity-driven single-cell Encapsulation and Sequencing (RAGE-Seq) is presented, where individual cells are phenotypically screened via single-cell Raman spectra (SCRS) in an aquatic, vitality-preserving environment, then the cell with targeted SCRS is precisely packaged in a picoliter microdroplet and readily exported in a precisely indexed, "one-cell-one-tube" manner. Such integration of microdroplet encapsulation to Raman-activated sorting ensures high-coverage one-cell genome sequencing or cultivation that is directly linked to metabolic phenotype. For clinical Escherichia coli isolates, genome assemblies derived from precisely one cell via RAGE-Seq consistently reach >95% coverage. Moreover, directly from a urine sample of urogenital tract infection, metabolic-activity-based antimicrobial susceptibility phenotypes and genome sequence of 99.5% coverage are obtained simultaneously from precisely one cell. This single-cell global mutation map corroborates resistance phenotype and genotype, and unveils epidemiological features with high specificity and sensitivity. The ability to profile and correlate bacterial metabolic phenome and high-quality genome sequences at one-cell resolution suggests broad application of RAGE-Seq.

Intelligent image-activated cell sorting 2.0

The advent of intelligent image-activated cell sorting (iIACS) has enabled high-throughput intelligent image-based sorting of single live cells from heterogeneous populations. iIACS is an on-chip microfluidic technology that builds on a seamless integration of a high-throughput fluorescence microscope, cell focuser, cell sorter, and deep neural network on a hybrid software-hardware data management architecture, thereby providing the combined merits of optical microscopy, fluorescence-activated cell sorting (FACS), and deep learning. Here we report an iIACS machine that far surpasses the state-of-the-art iIACS machine in system performance in order to expand the range of applications and discoveries enabled by the technology. Specifically, it provides a high throughput of ∼2000 events per second and a high sensitivity of ∼50 molecules of equivalent soluble fluorophores (MESFs), both of which are 20 times superior to those achieved in previous reports. This is made possible by employing (i) an image-sensor-based optomechanical flow imaging method known as virtual-freezing fluorescence imaging and (ii) a real-time intelligent image processor on an 8-PC server equipped with 8 multi-core CPUs and GPUs for intelligent decision-making, in order to significantly boost the imaging performance and computational power of the iIACS machine. We characterize the iIACS machine with fluorescent particles and various cell types and show that the performance of the iIACS machine is close to its achievable design specification. Equipped with the improved capabilities, this new generation of the iIACS technology holds promise for diverse applications in immunology, microbiology, stem cell biology, cancer biology, pathology, and synthetic biology.

Cell Type Purification by Single-Cell Transcriptome-Trained Sorting

Much of current molecular and cell biology research relies on the ability to purify cell types by fluorescence-activated cell sorting (FACS). FACS typically relies on the ability to label cell types of interest with antibodies or fluorescent transgenic constructs. However, antibody availability is often limited, and genetic manipulation is labor intensive or impossible in the case of primary human tissue. To date, no systematic method exists to enrich for cell types without a priori knowledge of cell-type markers. Here, we propose GateID, a computational method that combines single-cell transcriptomics with FACS index sorting to purify cell types of choice using only native cellular properties such as cell size, granularity, and mitochondrial content. We validate GateID by purifying various cell types from zebrafish kidney marrow and the human pancreas to high purity without resorting to specific antibodies or transgenes.

Nanoplasmon-enhanced drop-screen for high throughput single-cell nucleocytoplasmic miRNA profiling

Cell nucleocytoplasmic profiles of microRNAs (miRNAs) are critical to determining a single cell's essential functionalities, such as cellular transcription, nucleus export and degradation, which gives a comprehensive view of cellular processes. Despite the importance of addressing nucleocytoplasmic heterogeneity, the challenge of high-throughput screening remains. Although a droplet-based approach was developed for single-cell miRNA assays, the challenge of quantifying miRNA with high sensitivity to indicate nucleocytoplasmic heterogeneity remains. In this study, a nanoplasmon-enhanced droplet screening platform was developed to quantify single-cell nucleocytoplasmic heterogeneity with the high sensitivity of 0.1 nM. Droplet screening and multiplexed plasmonic assays are synergistic: droplet screening is used to isolate single cells for high-throughput screening, while enhanced nanoplasmonic assays are conducted to precisely determine different types of miRNAs, addressing the cell nucleocytoplasmic profile. Here, two nucleic acid-functionalized plasmonic nanosensors, silver nanoparticles functionalized with designed sequences to target miRNAs, are synthesized. After the targets are bound, competitive formation of sensor-target hybrids interferes with plasmonic coupling between the nanoparticles, decreasing a fluorescence signal and thus enabling high-sensitivity single-cell miRNA quantification. Using the fluorescence signal change as a readout allows continuous-flow measurement to provide a single-cell nucleocytoplasmic profile in a high-throughput manner (∼100 cells per minute) for effective quantitative cell biology.

(Photo)convert to pooled visual screening

Pooled genetic screening is a powerful method to systematically link genotype to phenotype and gain insights into biological processes, but applying it to visual phenotypes such as cell morphology or protein localization has remained a challenge. In their recent work, Fowler and colleagues (Hasle et al, 2020) describe an elegant approach for high-throughput cell sorting according to visual phenotypes based on selective photoconversion. This allows combining the advantages of high-content phenotyping by fluorescence microscopy with the efficiency of pooled screening to dissect complex phenotypes.

Fast intelligent cell phenotyping for high-throughput optofluidic time-stretch microscopy based on the XGBoost algorithm

SIGNIFICANCE

The use of optofluidic time-stretch flow cytometry enables extreme-throughput cell imaging but suffers from the difficulties of capturing and processing a large amount of data. As significant amounts of continuous image data are generated, the images require identification with high speed.

AIM

We present an intelligent cell phenotyping framework for high-throughput optofluidic time-stretch microscopy based on the XGBoost algorithm, which is able to classify obtained cell images rapidly and accurately. The applied image recognition consists of density-based spatial clustering of applications with noise outlier detection, histograms of oriented gradients combining gray histogram fused feature, and XGBoost classification.

APPROACH

We tested the ability of this framework against other previously proposed or commonly used algorithms to phenotype two groups of cell images. We quantified their performances with measures of classification ability and computational complexity based on AUC and test runtime. The tested cell image datasets were acquired from high-throughput imaging of over 20,000 drug-treated and untreated cells with an optofluidic time-stretch microscope.

RESULTS

The framework we built beats other methods with an accuracy of over 97% and a classification frequency of 3000  cells  /  s. In addition, we determined the optimal structure of training sets according to model performances under different training set components.

CONCLUSIONS

The proposed XGBoost-based framework acts as a promising solution to processing large flow image data. This work provides a foundation for future cell sorting and clinical practice of high-throughput imaging cytometers.

Three-dimensional localization microscopy in live flowing cells

Capturing the dynamics of live cell populations with nanoscale resolution poses a significant challenge, primarily owing to the speed-resolution trade-off of existing microscopy techniques. Flow cytometry would offer sufficient throughput, but lacks subsample detail. Here we show that imaging flow cytometry, in which the point detectors of flow cytometry are replaced with a camera to record 2D images, is compatible with 3D localization microscopy through point-spread-function engineering, which encodes the depth of the emitter into the emission pattern captured by the camera. The extraction of 3D positions from sub-cellular objects of interest is achieved by calibrating the depth-dependent response of the imaging system using fluorescent beads mixed with the sample buffer. This approach enables 4D imaging of up to tens of thousands of objects per minute and can be applied to characterize chromatin dynamics and the uptake and spatial distribution of nanoparticles in live cancer cells.

Image-Based Single Cell Sorting Automation in Droplet Microfluidics

The recent boom in single-cell omics has brought researchers one step closer to understanding the biological mechanisms associated with cell heterogeneity. Rare cells that have historically been obscured by bulk measurement techniques are being studied by single cell analysis and providing valuable insight into cell function. To support this progress, novel upstream capabilities are required for single cell preparation for analysis. Presented here is a droplet microfluidic, image-based single-cell sorting technique that is flexible and programmable. The automated system performs real-time dual-camera imaging (brightfield & fluorescent), processing, decision making and sorting verification. To demonstrate capabilities, the system was used to overcome the Poisson loading problem by sorting for droplets containing a single red blood cell with 85% purity. Furthermore, fluorescent imaging and machine learning was used to load single K562 cells amongst clusters based on their instantaneous size and circularity. The presented system aspires to replace manual cell handling techniques by translating expert knowledge into cell sorting automation via machine learning algorithms. This powerful technique finds application in the enrichment of single cells based on their micrographs for further downstream processing and analysis.

Intelligent classification of platelet aggregates by agonist type

Platelets are anucleate cells in blood whose principal function is to stop bleeding by forming aggregates for hemostatic reactions. In addition to their participation in physiological hemostasis, platelet aggregates are also involved in pathological thrombosis and play an important role in inflammation, atherosclerosis, and cancer metastasis. The aggregation of platelets is elicited by various agonists, but these platelet aggregates have long been considered indistinguishable and impossible to classify. Here we present an intelligent method for classifying them by agonist type. It is based on a convolutional neural network trained by high-throughput imaging flow cytometry of blood cells to identify and differentiate subtle yet appreciable morphological features of platelet aggregates activated by different types of agonists. The method is a powerful tool for studying the underlying mechanism of platelet aggregation and is expected to open a window on an entirely new class of clinical diagnostics, pharmacometrics, and therapeutics.

Platelets are small cells in the blood that primarily help stop bleeding after an injury by sticking together with other blood cells to form a clot that seals the broken blood vessel. Blood clots, however, can sometimes cause harm. For example, if a clot blocks the blood flow to the heart or the brain, it can result in a heart attack or stroke, respectively. Blood clots have also been linked to harmful inflammation and the spread of cancer, and there are now preliminary reports of remarkably high rates of clotting in COVID-19 patients in intensive care units.

A variety of chemicals can cause platelets to stick together. It has long been assumed that it would be impossible to tell apart the clots formed by different chemicals (which are also known as agonists). This is largely because these aggregates all look very similar under a microscope, making it incredibly time consuming for someone to look at enough microscopy images to reliably identify the subtle differences between them. However, finding a way to distinguish the different types of platelet aggregates could lead to better ways to diagnose or treat blood vessel-clogging diseases.

To make this possible, Zhou, Yasumoto et al. have developed a method called the “intelligent platelet aggregate classifier” or iPAC for short. First, numerous clot-causing chemicals were added to separate samples of platelets taken from healthy human blood. The method then involved using high-throughput techniques to take thousands of images of these samples. Then, a sophisticated computer algorithm called a deep learning model analyzed the resulting image dataset and “learned” to distinguish the chemical causes of the platelet aggregates based on subtle differences in their shapes. Finally, Zhou, Yasumoto et al. verified iPAC method’s accuracy using a new set of human platelet samples.

The iPAC method may help scientists studying the steps that lead to clot formation. It may also help clinicians distinguish which clot-causing chemical led to a patient’s heart attack or stroke. This could help them choose whether aspirin or another anti-platelet drug would be the best treatment. But first more studies are needed to confirm whether this method is a useful tool for drug selection or diagnosis.

High-speed single-pixel imaging by frequency-time-division multiplexing

We propose and experimentally demonstrate high-speed single-pixel imaging by integrating frequency-division multiplexing and time-division multiplexing (techniques used widely in telecommunications) and applying the combined technique, namely, frequency-time-division multiplexing (FTDM), to optical imaging. Specifically, FTDM single-pixel imaging uses an array of broadband, spatially distributed, dual-frequency combs (i.e., spatial dual combs) for multidimensional illumination and detects an image-encoded time-domain signal with a single-pixel photodetector in a FTDM manner. As a proof-of-principle demonstration, we use the method to show ultrafast two-color (bright-field and fluorescence) single-pixel microscopy of breast cancer cells at a high frame rate of 32,000 fps and ultrafast image velocimetry of fluorescent particles flowing at a high speed of ${ \gt }{2}\;{\rm m/s}$>2m/s.

Temporally interleaved optical time-stretch imaging

Optical time-stretch imaging has shown potential in diverse fields for its capability of acquiring images at high speed and high resolution. However, its wide application is hindered by the stringent requirement on the instrumentation hardware caused by the high-speed serial data stream. Here we demonstrate temporally interleaved optical time-stretch imaging that lowers the requirement without sacrificing the frame rate or spatial resolution by interleaving the high-speed data stream into multiple channels in the time domain. Its performance is validated with both a United States Air Force (USAF)-1951 resolution chart and a single-crystal diamond film. We achieve a 101 Mfps 1D scanning rate and 3 µm spatial resolution with only a 2.5 GS/s sampling rate by using a two-channel-interleaved system.

Microfluidic-based linear-optics label-free imager

Linear optics based nanoscopy previously reached resolution beyond the diffraction limit, illuminating samples in the visible light regime while allowing light to interact with freely moving metallic nanoparticles. However, the hydrodynamics governing the nanoparticle motion used to scan the sample is very complex and has low probability of achieving appropriate and fast mapping in practice. Hence, an implementation of the technique on real biological samples has not been demonstrated so far. Moreover, a suitable way to perform controlled nanoparticle scanning of biological samples is required. Here we show a solution where a microfluidic channel is used to flow and trap biological samples inside a water droplet along with suspended nanoparticles surrounded by silicone oil. The evanescent light scattered from the sample and is rescattered by the nanoparticles in the vicinity. This encodes the sub-wavelength features of the sample which can later on be decoded and reconstructed from measurements in the far field. The microfluidic system-controlled flow allows better nanoparticle scanning of the sample and maintains an isolated system for each sample in each droplet. A more localized scan at the droplet water/oil interface is also conducted using amphiphilic nanoparticles where their hydrophilic side is constrained to the droplet and their hydrophobic side is constrained to the oil. This allows higher probability of capturing evanescent fields closer to their origin, yielding better resolution and a higher signal to noise ratio. Using this system, we obtained images of an E. coli sample and demonstrated how the method yield fine resolution of the sample contours. To the best of our knowledge, this is the first time that a linear and label free optics imaging process was performed using a micro-fluidic device.

Label-free imaging flow cytometer for analyzing large cell populations by line-field quantitative phase microscopy with digital refocusing

We propose a line-field quantitative phase-imaging flow cytometer for analyzing large populations of label-free cells. Hydrodynamical focusing brings cells into the focus plane of an optical system while diluting the cell suspension, resulting in decreased throughput rate. To overcome the trade-off between throughput rate and in-focus imaging, our cytometer involves digitally extending the depth-of-focus on loosely hydrodynamically focusing cell suspensions. The cells outside the depth-of-focus range in the 70-µm diameter of the core flow were automatically digitally refocused after image acquisition. We verified that refocusing was successful with our cytometer through statistical analysis of image quality before and after digital refocusing.

Large-scale label-free single-cell analysis of paramylon in Euglena gracilis by high-throughput broadband Raman flow cytometry

Microalga-based biomaterial production has attracted attention as a new source of drugs, foods, and biofuels. For enhancing the production efficiency, it is essential to understand its differences between heterogeneous microalgal subpopulations. However, existing techniques are not adequate to address the need due to the lack of single-cell resolution or the inability to perform large-scale analysis and detect small molecules. Here we demonstrated large-scale single-cell analysis of Euglena gracilis (a unicellular microalgal species that produces paramylon as a potential drug for HIV and colon cancer) with our recently developed high-throughput broadband Raman flow cytometer at a throughput of >1,000 cells/s. Specifically, we characterized the intracellular content of paramylon from single-cell Raman spectra of 10,000 E. gracilis cells cultured under five different conditions and found that paramylon contents in E. gracilis cells cultured in an identical condition is given by a log-normal distribution, which is a good model for describing the number of chemicals in a reaction network. The capability of characterizing distribution functions in a label-free manner is an important basis for isolating specific cell populations for synthetic biology via directed evolution based on the intracellular content of metabolites.

Multiplex Stimulated Raman Scattering Imaging Cytometry Reveals Lipid-Rich Protrusions in Cancer Cells under Stress Condition

In situ measurement of cellular metabolites is still a challenge in biology. Conventional methods, such as mass spectrometry or fluorescence microscopy, would either destroy the sample or introduce strong perturbations to target molecules. Here, we present multiplex stimulated Raman scattering (SRS) imaging cytometry as a label-free single-cell analysis platform with chemical specificity and high-throughput capabilities. Using SRS imaging cytometry, we studied the metabolic responses of human pancreatic cancer cells under stress by starvation and chemotherapeutic drug treatments. We unveiled protrusions containing lipid droplets as a metabolic marker for stress-resistant cancer cells. Furthermore, by spectroscopic SRS mapping, we unveiled that triglyceride in lipid droplets are used for local energy production through lipolysis, autophagy, and β-oxidation. Our findings demonstrate the potential of targeting lipid metabolism for selective treatment of stress-resistant cancers. Collectively, these results highlight SRS imaging cytometry as a powerful label-free tool for biological discoveries with a high-throughput, high-content capacity.

Detection of Rare Objects by Flow Cytometry: Imaging, Cell Sorting, and Deep Learning Approaches

Flow cytometry nowadays is among the main working instruments in modern biology paving the way for clinics to provide early, quick, and reliable diagnostics of many blood-related diseases. The major problem for clinical applications is the detection of rare pathogenic objects in patient blood. These objects can be circulating tumor cells, very rare during the early stages of cancer development, various microorganisms and parasites in the blood during acute blood infections. All of these rare diagnostic objects can be detected and identified very rapidly to save a patient's life. This review outlines the main techniques of visualization of rare objects in the blood flow, methods for extraction of such objects from the blood flow for further investigations and new approaches to identify the objects automatically with the modern deep learning methods.

A neural network approach for real-time particle/cell characterization in microfluidic impedance cytometry

Microfluidic applications such as active particle sorting or selective enrichment require particle classification techniques that are capable of working in real time. In this paper, we explore the use of neural networks for fast label-free particle characterization during microfluidic impedance cytometry. A recurrent neural network is designed to process data from a novel impedance chip layout for enabling real-time multiparametric analysis of the measured impedance data streams. As demonstrated with both synthetic and experimental datasets, the trained network is able to characterize with good accuracy size, velocity, and cross-sectional position of beads, red blood cells, and yeasts, with a unitary prediction time of 0.4 ms. The proposed approach can be extended to other device designs and cell types for electrical parameter extraction. This combination of microfluidic impedance cytometry and machine learning can serve as a stepping stone to real-time single-cell analysis and sorting. Graphical Abstract.

Virtual-freezing fluorescence imaging flow cytometry

By virtue of the combined merits of flow cytometry and fluorescence microscopy, imaging flow cytometry (IFC) has become an established tool for cell analysis in diverse biomedical fields such as cancer biology, microbiology, immunology, hematology, and stem cell biology. However, the performance and utility of IFC are severely limited by the fundamental trade-off between throughput, sensitivity, and spatial resolution. Here we present an optomechanical imaging method that overcomes the trade-off by virtually freezing the motion of flowing cells on the image sensor to effectively achieve 1000 times longer exposure time for microscopy-grade fluorescence image acquisition. Consequently, it enables high-throughput IFC of single cells at >10,000 cells s⁻¹ without sacrificing sensitivity and spatial resolution. The availability of numerous information-rich fluorescence cell images allows high-dimensional statistical analysis and accurate classification with deep learning, as evidenced by our demonstration of unique applications in hematology and microbiology.

High throughput imaging flow cytometry suffers from trade-offs between throughput, sensitivity and spatial resolution. Here the authors introduce a method to virtually freeze cells in the image acquisition window to enable 1000 times longer signal integration time and improve signal-to-noise ratio.

Deep learning guided image-based droplet sorting for on-demand selection and analysis of single cells and 3D cell cultures

Uncovering the heterogeneity of cellular populations and multicellular constructs is a long-standing goal in fields ranging from antimicrobial resistance to cancer research. Emerging technology platforms such as droplet microfluidics hold the promise to decipher such heterogeneities at ultra-high-throughput. However, there is a lack of methods able to rapidly identify and isolate single cells or 3D cell cultures. Here we demonstrate that deep neural networks can accurately classify single droplet images in real-time based on the presence and number of micro-objects including single mammalian cells and multicellular spheroids. This approach also enables the identification of specific objects within mixtures of objects of different types and sizes. The training sets for the neural networks consisted of a few hundred images manually picked and augmented to up to thousands of images per training class. Training required less than 10 minutes using a single GPU, and yielded accuracies of over 90% for single mammalian cell identification. Crucially, the same model could be used to classify different types of objects such as polystyrene spheres, polyacrylamide beads and MCF-7 cells. We applied the developed method for the selection of 3D cell cultures generated with Hek293FT cells encapsulated in agarose gel beads, highlighting the potential of the technology for the selection of objects with a high diversity of visual appearances. The real-time sorting of single droplets was in-line with droplet generation and occurred at rates up to 40 per second independently of image size up to 480 × 480 pixels. The presented microfluidic device also enabled storage of sorted droplets to allow for downstream analyses.

Implementing machine learning methods for imaging flow cytometry

In this review, we focus on the applications of machine learning methods for analyzing image data acquired in imaging flow cytometry technologies. We propose that the analysis approaches can be categorized into two groups based on the type of data, raw imaging signals or features explicitly extracted from images, being analyzed by a trained model. We hope that this categorization is helpful for understanding uniqueness, differences and opportunities when the machine learning-based analysis is implemented in recently developed ‘imaging’ cell sorters.

Classifying T cell activity in autofluorescence intensity images with convolutional neural networks

The importance of T cells in immunotherapy has motivated developing technologies to improve therapeutic efficacy. One objective is assessing antigen-induced T cell activation because only functionally active T cells are capable of killing the desired targets. Autofluorescence imaging can distinguish T cell activity states in a non-destructive manner by detecting endogenous changes in metabolic co-enzymes such as NAD(P)H. However, recognizing robust activity patterns is computationally challenging in the absence of exogenous labels. We demonstrate machine learning methods that can accurately classify T cell activity across human donors from NAD(P)H intensity images. Using 8260 cropped single-cell images from six donors, we evaluate classifiers ranging from traditional models that use previously-extracted image features to convolutional neural networks (CNNs) pre-trained on general non-biological images. Adapting pre-trained CNNs for the T cell activity classification task provides substantially better performance than traditional models or a simple CNN trained with the autofluorescence images alone. Visualizing the images with dimension reduction provides intuition into why the CNNs achieve higher accuracy than other approaches. Our image processing and classifier training software is available at https://github.com/gitter-lab/t-cell-classification.

In vitro monitoring of photoinduced necrosis in HeLa cells using digital holographic microscopy and machine learning

Digital holographic microscopy supplemented with the developed cell segmentation and machine learning and classification algorithms is implemented for quantitative description of the dynamics of cellular necrosis induced by photodynamic treatment in vitro. It is demonstrated that the developed algorithms operating with a set of optical, morphological, and physiological parameters of cells, obtained from their phase images, can be used for automatic distinction between live and necrotic cells. The developed classifier provides high accuracy of about 95.5% and allows for calculation of survival rates in the course of cell death.

Real-time frequency-encoded spatiotemporal focusing through scattering media using a programmable 2D ultrafine optical frequency comb

Optical wavefront shaping is a powerful tool for controlling photons in strongly scattering media. Its speed, however, has been the bottleneck for in vivo applications. Moreover, unlike spatial focusing, temporal focusing from a continuous-wave source has rarely been exploited yet is highly desired for nonlinear photonics. Here, we present a novel real-time frequency-encoded spatiotemporal (FEST) focusing technology. FEST focusing uses a novel programmable two-dimensional optical frequency comb with an ultrafine linewidth to perform single-shot wavefront measurements, with a fast single-pixel detector. This technique enables simultaneous spatial and temporal focusing at microsecond scales through thick dynamic scattering media. This technology also enabled us to discover the large-scale temporal shift, a new phenomenon that, with the conventional spatial memory effect, establishes a space-time duality. FEST focusing opens a new avenue for high-speed wavefront shaping in the field of photonics.

Quantitative scoring of epithelial and mesenchymal qualities of cancer cells using machine learning and quantitative phase imaging

SIGNIFICANCE

We introduce an application of machine learning trained on optical phase features of epithelial and mesenchymal cells to grade cancer cells' morphologies, relevant to evaluation of cancer phenotype in screening assays and clinical biopsies.

AIM

Our objective was to determine quantitative epithelial and mesenchymal qualities of breast cancer cells through an unbiased, generalizable, and linear score covering the range of observed morphologies.

APPROACH

Digital holographic microscopy was used to generate phase height maps of noncancerous epithelial (Gie-No3B11) and fibroblast (human gingival) cell lines, as well as MDA-MB-231 and MCF-7 breast cancer cell lines. Several machine learning algorithms were evaluated as binary classifiers of the noncancerous cells that graded the cancer cells by transfer learning.

RESULTS

Epithelial and mesenchymal cells were classified with 96% to 100% accuracy. Breast cancer cells had scores in between the noncancer scores, indicating both epithelial and mesenchymal morphological qualities. The MCF-7 cells skewed toward epithelial scores, while MDA-MB-231 cells skewed toward mesenchymal scores. Linear support vector machines (SVMs) produced the most distinct score distributions for each cell line.

CONCLUSIONS

The proposed epithelial-mesenchymal score, derived from linear SVM learning, is a sensitive and quantitative approach for detecting epithelial and mesenchymal characteristics of unknown cells based on well-characterized cell lines. We establish a framework for rapid and accurate morphological evaluation of single cells and subtle phenotypic shifts in imaged cell populations.

The Roles of the NLRP3 Inflammasome in Neurodegenerative and Metabolic Diseases and in Relevant Advanced Therapeutic Interventions

Inflammasomes are intracellular multiprotein complexes in the cytoplasm that regulate inflammation activation in the innate immune system in response to pathogens and to host self-derived molecules. Recent advances greatly improved our understanding of the activation of nucleotide-binding oligomerization domain-like receptor (NLR) family pyrin domain containing 3 (NLRP3) inflammasomes at the molecular level. The NLRP3 belongs to the subfamily of NLRP which activates caspase 1, thus causing the production of proinflammatory cytokines (interleukin 1β and interleukin 18) and pyroptosis. This inflammasome is involved in multiple neurodegenerative and metabolic disorders including Alzheimer's disease, multiple sclerosis, type 2 diabetes mellitus, and gout. Therefore, therapeutic targeting to the NLRP3 inflammasome complex is a promising way to treat these diseases. Recent research advances paved the way toward drug research and development using a variety of machine learning-based and artificial intelligence-based approaches. These state-of-the-art approaches will lead to the discovery of better drugs after the training of such a system.

Single-cell dispensing and 'real-time' cell classification using convolutional neural networks for higher efficiency in single-cell cloning

Single-cell dispensing for automated cell isolation of individual cells has gained increased attention in the biopharmaceutical industry, mainly for production of clonal cell lines. Here, machine learning for classification of cell images is applied for ‘real-time’ cell viability sorting on a single-cell printer. We show that an extremely shallow convolutional neural network (CNN) for classification of low-complexity cell images outperforms more complex architectures. Datasets with hundreds of cell images from four different samples were used for training and validation of the CNNs. The clone recovery, i.e. the fraction of single-cells that grow to clonal colonies, is predicted to increase for all the samples investigated. Finally, a trained CNN was deployed on a c.sight single-cell printer for ‘real-time’ sorting of a CHO-K1 cells. On a sample with artificially damaged cells the clone recovery could be increased from 27% to 73%, thereby resulting in a significantly faster and more efficient cloning. Depending on the classification threshold, the frequency at which viable cells are dispensed could be increased by up to 65%. This technology for image-based cell sorting is highly versatile and can be expected to enable cell sorting by computer vision with respect to different criteria in the future.

Deep Learning-Based Single-Cell Optical Image Studies

Optical imaging technology that has the advantages of high sensitivity and cost-effectiveness greatly promotes the progress of nondestructive single-cell studies. Complex cellular image analysis tasks such as three-dimensional reconstruction call for machine-learning technology in cell optical image research. With the rapid developments of high-throughput imaging flow cytometry, big data cell optical images are always obtained that may require machine learning for data analysis. In recent years, deep learning has been prevalent in the field of machine learning for large-scale image processing and analysis, which brings a new dawn for single-cell optical image studies with an explosive growth of data availability. Popular deep learning techniques offer new ideas for multimodal and multitask single-cell optical image research. This article provides an overview of the basic knowledge of deep learning and its applications in single-cell optical image studies. We explore the feasibility of applying deep learning techniques to single-cell optical image analysis, where popular techniques such as transfer learning, multimodal learning, multitask learning, and end-to-end learning have been reviewed. Image preprocessing and deep learning model training methods are then summarized. Applications based on deep learning techniques in the field of single-cell optical image studies are reviewed, which include image segmentation, super-resolution image reconstruction, cell tracking, cell counting, cross-modal image reconstruction, and design and control of cell imaging systems. In addition, deep learning in popular single-cell optical imaging techniques such as label-free cell optical imaging, high-content screening, and high-throughput optical imaging cytometry are also mentioned. Finally, the perspectives of deep learning technology for single-cell optical image analysis are discussed. © 2020 International Society for Advancement of Cytometry.

Engineering Tissue Fabrication With Machine Intelligence: Generating a Blueprint for Regeneration

Regenerating lost or damaged tissue is the primary goal of Tissue Engineering. 3D bioprinting technologies have been widely applied in many research areas of tissue regeneration and disease modeling with unprecedented spatial resolution and tissue-like complexity. However, the extraction of tissue architecture and the generation of high-resolution blueprints are challenging tasks for tissue regeneration. Traditionally, such spatial information is obtained from a collection of microscopic images and then combined together to visualize regions of interest. To fabricate such engineered tissues, rendered microscopic images are transformed to code to inform a 3D bioprinting process. If this process is augmented with data-driven approaches and streamlined with machine intelligence, identification of an optimal blueprint can become an achievable task for functional tissue regeneration. In this review, our perspective is guided by an emerging paradigm to generate a blueprint for regeneration with machine intelligence. First, we reviewed recent articles with respect to our perspective for machine intelligence-driven information retrieval and fabrication. After briefly introducing recent trends in information retrieval methods from publicly available data, our discussion is focused on recent works that use machine intelligence to discover tissue architectures from imaging and spectral data. Then, our focus is on utilizing optimization approaches to increase print fidelity and enhance biomimicry with machine learning (ML) strategies to acquire a blueprint ready for 3D bioprinting.

Focusing of sub-micrometer particles in microfluidic devices

Sub-micrometer particles (0.10-1.0 μm) are of great significance to study, e.g., microvesicles and protein aggregates are targets for therapeutic intervention, and sub-micrometer fluorescent polystyrene (PS) particles are used as probes for diagnostic imaging. Focusing of sub-micrometer particles - precisely control over the position of sub-micrometer particles in a tightly focused stream - has a wide range of applications in the field of biology, chemistry and environment, by acting as a prerequisite step for downstream detection, manipulation and quantification. Microfluidic devices have been attracting great attention as desirable tools for sub-micrometer particle focusing, due to their small size, low reagent consumption, fast analysis and low cost. Recent advancements in fundamental knowledge and fabrication technologies have enabled microfluidic focusing of particles at sub-micrometer scale in a continuous, label-free and high-throughput manner. Microfluidic methods for the focusing of sub-micrometer particles can be classified into two main groups depending on whether an external field is applied: 1) passive methods, which utilize intrinsic fluidic properties without the need of external actuation, such as inertial, deterministic lateral displacement (DLD), viscoelastic and hydrophoretic focusing; and 2) active methods, where external fields are used, such as dielectrophoretic, thermophoretic, acoustophoretic and optical focusing. This article mainly reviews the studies on the focusing of sub-micrometer particles in microfluidic devices over the past 10 years. It aims to bridge the gap between the focusing of micrometer and nanometer scale (1.0-100 nm) particles and to improve the understanding of development progress, current advances and future prospects in microfluidic focusing techniques.

Intelligent frequency-shifted optofluidic time-stretch quantitative phase imaging

Optofluidic time-stretch quantitative phase imaging (OTS-QPI) is a powerful tool as it enables high-throughput (>10,000 cell/s) QPI of single live cells. OTS-QPI is based on decoding temporally stretched spectral interferograms that carry the spatial profiles of cells flowing on a microfluidic chip. However, the utility of OTS-QPI is troubled by difficulties in phase retrieval from the high-frequency region of the temporal interferograms, such as phase-unwrapping errors, high instrumentation cost, and large data volume. To overcome these difficulties, we propose and experimentally demonstrate frequency-shifted OTS-QPI by bringing the phase information to the baseband region. Furthermore, to show its boosted utility, we use it to demonstrate image-based classification of leukemia cells with high accuracy over 96% and evaluation of drug-treated leukemia cells via deep learning.

Amplified piezoelectrically actuated on-chip flow switching for a rapid and stable microfluidic fluorescence activated cell sorter

With the potential to avoid cross-contamination, eliminate bio-aerosols, and minimize device footprints, microfluidic fluorescence-activated cell sorting (μ-FACS) devices could become the platform for the next generation cell sorter. Here, we report an on-chip flow switching based μ-FACS mechanism with piezoelectric actuation as a fast and robust sorting solution. A microfluidic chip with bifurcate configuration and displacement amplified piezoelectric microvalves has been developed to build the μ-FACS system. Rare fluorescent microparticles of different sizes have been significantly enriched from a purity of ∼0.5% to more than 90%. An enrichment of 150-fold from ∼0.6% to ∼91% has also been confirmed for fluorescently labeled MCF-7 breast cancer cells from Jurkat cells, while viability after sorting was maintained. Taking advantage of its simple structure, low cost, fast response, and reliable flow regulation, the proposed μ-FACS system delivers a new option that can meet the requirements of sorting performance, target selectivity, device lifetime, and cost-effectiveness of implementation.

With the potential to avoid cross-contamination, eliminate bio-aerosols, and minimize device footprints, microfluidic fluorescence-activated cell sorting (μ-FACS) devices could become the platform for the next generation cell sorter.

Current strategies and opportunities to manufacture cells for modeling human lungs

Chronic lung diseases remain major healthcare burdens, for which the only curative treatment is lung transplantation. In vitro human models are promising platforms for identifying and testing novel compounds to potentially decrease this burden. Directed differentiation of pluripotent stem cells is an important strategy to generate lung cells to create such models. Current lung directed differentiation protocols are limited as they do not 1) recapitulate the diversity of respiratory epithelium, 2) generate consistent or sufficient cell numbers for drug discovery platforms, and 3) establish the histologic tissue-level organization critical for modeling lung function. In this review, we describe how lung development has formed the basis for directed differentiation protocols, and discuss the utility of available protocols for lung epithelial cell generation and drug development. We further highlight tissue engineering strategies for manipulating biophysical signals during directed differentiation such that future protocols can recapitulate both chemical and physical cues present during lung development.

A Design of Microfluidic Chip with Quasi-Bessel Beam Waveguide for Scattering Detection of Label-Free Cancer Cells

Light scattering detection in microfluidic chips provides an important tool to identify cancer cells without any label processes. However, forward small-angle scattering signals of cells, which are related to their sizes and morphologies, are hard to be detected accurately when scattering angle is less than 11° in microfluidic chips by traditional lighting design due to the influence of incident beam. Therefore, cell's size and morphology being the golden standard for clinical detection may lose their efficacy in recognizing cancer cells from healthy ones. In this article, a novel lighting design in microfluidic chips is put forward in which traditional incident Gaussian beam can be modulated into quasi-Bessel beam by a microprism and waveguide. The quasi-Bessel beam's advantages of nondiffraction theoretically make forward scattering (FS) detection less than 11° possibly. Our experimental results for peripheral blood lymphocytes of human beings and cultured HeLa cells show that the detection rates increase by 47.87% and 46.79%, respectively, by the novel designed microfluidic chip compared to traditional Gaussian lighting method in microfluidic chips. © 2019 International Society for Advancement of Cytometry.

Combining dielectrophoresis and computer vision for precise and fully automated single-cell handling and analysis

With the advent of single-cell technologies comes the necessity for efficient protocols to process single cells. We combine dielectrophoresis with open source computer vision programming to automatically control the trajectories of single cells inside a microfluidic device. Using real-time image analysis, individual cells are automatically selected, isolated and spatially arranged.

Precise Quantitative Analysis of Cell Targeting by Particle-Based Agents Using Imaging Flow Cytometry and Convolutional Neural Network

Understanding the intricacies of particle-cell interactions is essential for many applications such as imaging, phototherapy, and drug/gene delivery, because it is the key to accurate control of the particle properties for the improvement of their therapeutic and diagnostic efficiency. Recently, high-throughput methods have emerged for the detailed investigation of these interactions. For example, imaging flow cytometry (IFC) collects up to 60,000 images of cells per second (in 12 optical channels) and provides information about morphology and organelle localization in combination with fluorescence and side scatter intensity data. However, analysis of IFC data is extremely difficult to perform using conventional methods that calculate integral parameters or use mask-based object recognition. Here, we show application of a convolutional neural network (CNN) for precise quantitative analysis of particle targeting of cells using IFC data. CNN provides high-throughput object detection with almost human precision but avoids the subjective choice of image processing parameters that often leads to incorrect data interpretation. The method allows accurate counting of cell-bound particles with reliable discrimination from the nonbound particles in the field of view. The proposed method expands capabilities of spot counting applications (such as organelle counting, quantification of cell-cell and cell-bacteria interactions) and is going to be useful not only for high-throughput analysis of IFC data but also for other imaging techniques. © 2019 International Society for Advancement of Cytometry.

Deep learning for cellular image analysis

Recent advances in computer vision and machine learning underpin a collection of algorithms with an impressive ability to decipher the content of images. These deep learning algorithms are being applied to biological images and are transforming the analysis and interpretation of imaging data. These advances are positioned to render difficult analyses routine and to enable researchers to carry out new, previously impossible experiments. Here we review the intersection between deep learning and cellular image analysis and provide an overview of both the mathematical mechanics and the programming frameworks of deep learning that are pertinent to life scientists. We survey the field's progress in four key applications: image classification, image segmentation, object tracking, and augmented microscopy. Last, we relay our labs' experience with three key aspects of implementing deep learning in the laboratory: annotating training data, selecting and training a range of neural network architectures, and deploying solutions. We also highlight existing datasets and implementations for each surveyed application.

Ultrafast Simultaneous Raman-Fluorescence Spectroscopy

Raman and fluorescence spectroscopies offer complementary approaches in bioanalytical chemistry, particularly in microbiological assays. The former method is used to detect lipids, metabolites, and nonspecific proteins and nucleic acids in a label-free manner, while the latter is used to investigate targeted proteins, nucleic acids, and their interactions via labeling or transfection. Despite their complementarity, these regimes are seldom used in conjunction due to fluorescent signals overwhelming inherently weak Raman signals by more than several orders of magnitude. Here we report a multimodal spectrometer that simultaneously performs Raman and fluorescence spectroscopies at high speed. It is made possible by Fourier-transform-coherent anti-Stokes Raman scattering (FT-CARS) and Fourier-transform-two-photon excitation (FT-TPE) measurements powered by a femtosecond pulse laser coupled to a homemade rapid-scan Michelson interferometer, operating at 24 000 spectra per second. As a proof-of-principle demonstration, we validate the ultrafast fluoRaman spectrometer by measuring coumarin dyes in organic solvents. To show its potential for applications that require rapid fluoRaman spectroscopy, we also demonstrate fluoRaman flow cytometry of Haematococcus pluvialis cells under varying culture conditions with a high throughput of ∼10 events per second to perform large-scale single-cell analysis of their metabolic stress response.

Using single-cell transcriptomics to understand functional states and interactions in microbial eukaryotes

Understanding the diversity and evolution of eukaryotic microorganisms remains one of the major challenges of modern biology. In recent years, we have advanced in the discovery and phylogenetic placement of new eukaryotic species and lineages, which in turn completely transformed our view on the eukaryotic tree of life. But we remain ignorant of the life cycles, physiology and cellular states of most of these microbial eukaryotes, as well as of their interactions with other organisms. Here, we discuss how high-throughput genome-wide gene expression analysis of eukaryotic single cells can shed light on protist biology. First, we review different single-cell transcriptomics methodologies with particular focus on microbial eukaryote applications. Then, we discuss single-cell gene expression analysis of protists in culture and what can be learnt from these approaches. Finally, we envision the application of single-cell transcriptomics to protist communities to interrogate not only community components, but also the gene expression signatures of distinct cellular and physiological states, as well as the transcriptional dynamics of interspecific interactions. Overall, we argue that single-cell transcriptomics can significantly contribute to our understanding of the biology of microbial eukaryotes. This article is part of a discussion meeting issue 'Single cell ecology'.

Immune cell type, cell activation, and single cell heterogeneity revealed by label-free optical methods

Measurement techniques that allow the global analysis of cellular responses while retaining single-cell sensitivity are increasingly needed in order to understand complex and dynamic biological processes. In this context, compromises between sensitivity, degree of multiplexing, throughput, and invasiveness are often unavoidable. We present here a noninvasive optical approach that can retrieve quantitative biomarkers of both morphological and molecular phenotypes of individual cells, based on a combination of quantitative phase imaging and Raman spectroscopy measurements. We then develop generalized statistical tools to assess the influence of both controlled (cell sub-populations, immune stimulation) and uncontrolled (culturing conditions, animal variations, etc.) experimental parameters on the label-free biomarkers. These indicators can detect different macrophage cell sub-populations originating from different progenitors as well as their activation state, and how these changes are related to specific differences in morphology and molecular content. The molecular indicators also display further sensitivity that allow identification of other experimental conditions, such as differences between cells originating from different animals, allowing the detection of outlier behaviour from given cell sub-populations.

Morpho-Rheological Fingerprinting of Rod Photoreceptors Using Real-Time Deformability Cytometry

Distinct cell-types within the retina are mainly specified by morphological and molecular parameters, however, physical properties are increasingly recognized as a valuable tool to characterize and distinguish cells in diverse tissues. High-throughput analysis of morpho-rheological features has recently been introduced using real-time deformability cytometry (RT-DC) providing new insights into the properties of different cell-types. Rod photoreceptors represent the main light sensing cells in the mouse retina that during development forms apically the densely packed outer nuclear layer. Currently, enrichment and isolation of photoreceptors from retinal primary tissue or pluripotent stem cell-derived organoids for analysis, molecular profiling, or transplantation is achieved using flow cytometry or magnetic activated cell sorting approaches. However, such purification methods require genetic modification or identification of cell surface binding antibody panels. Using primary retina and embryonic stem cell-derived retinal organoids, we characterized the inherent morpho-mechanical properties of mouse rod photoreceptors during development based on RT-DC. We demonstrate that rods become smaller and more compliant throughout development and that these features are suitable to distinguish rods within heterogenous retinal tissues. Hence, physical properties should be considered as additional factors that might affect photoreceptor differentiation and retinal development besides representing potential parameters for label-free sorting of photoreceptors. © 2019 The Authors. Cytometry Part A published by Wiley Periodicals, Inc. on behalf of International Society for Advancement of Cytometry.

Droplet Microfluidics-Enabled High-Throughput Screening for Protein Engineering

Protein engineering—the process of developing useful or valuable proteins—has successfully created a wide range of proteins tailored to specific agricultural, industrial, and biomedical applications. Protein engineering may rely on rational techniques informed by structural models, phylogenic information, or computational methods or it may rely upon random techniques such as chemical mutation, DNA shuffling, error prone polymerase chain reaction (PCR), etc. The increasing capabilities of rational protein design coupled to the rapid production of large variant libraries have seriously challenged the capacity of traditional screening and selection techniques. Similarly, random approaches based on directed evolution, which relies on the Darwinian principles of mutation and selection to steer proteins toward desired traits, also requires the screening of very large libraries of mutants to be truly effective. For either rational or random approaches, the highest possible screening throughput facilitates efficient protein engineering strategies. In the last decade, high-throughput screening (HTS) for protein engineering has been leveraging the emerging technologies of droplet microfluidics. Droplet microfluidics, featuring controlled formation and manipulation of nano- to femtoliter droplets of one fluid phase in another, has presented a new paradigm for screening, providing increased throughput, reduced reagent volume, and scalability. We review here the recent droplet microfluidics-based HTS systems developed for protein engineering, particularly directed evolution. The current review can also serve as a tutorial guide for protein engineers and molecular biologists who need a droplet microfluidics-based HTS system for their specific applications but may not have prior knowledge about microfluidics. In the end, several challenges and opportunities are identified to motivate the continued innovation of microfluidics with implications for protein engineering.

Automatically Controlled Microfluidic System for Continuous Separation of Rare Bacteria from Blood

Bloodstream infection by microorganisms is a major public health concern worldwide. Millions of people per year suffer from microbial infections, and current blood culture-based diagnostic methods are time-consuming because of the low concentration of infectious microorganisms in the bloodstream. In this study, we introduce an efficient automated microfluidic system for the continuous isolation of rare infectious bacteria (Escherichia coli, Staphylococcus aureus, and Pseudomonas aeruginosa) from blood. Bacteria received a balanced force between a fluidic drag force and a periodically controlled dielectrophoretic (DEP) force from tilted electrodes to minimize cell adhesion to the electrodes, which prevented the loss of rare infectious bacteria. Target bacteria were efficiently segregated from the undesired blood cells to ensure that only the bacteria received the DEP force under the hypotonic condition, while the blood cells received no DEP force and exited the channel via a laminar flow. Thus, the bacteria were successfully extracted from the blood with a high recovery yield of 91.3%, and the limit of the bacteria concentration for isolation was 100 cfu/ml. We also developed an automated system that performed every step from blood-sample loading to application of electricity to the microfluidic chip for bacteria separation. It reduced the standard deviation of the bacteria recovery yield from 6.16 to 2.77 compared with the conventional batch process, providing stable bacteria-extraction performance and minimizing errors and bacteria loss caused by user mistakes. © 2019 International Society for Advancement of Cytometry.

Guidelines for the use of flow cytometry and cell sorting in immunological studies (second edition)

These guidelines are a consensus work of a considerable number of members of the immunology and flow cytometry community. They provide the theory and key practical aspects of flow cytometry enabling immunologists to avoid the common errors that often undermine immunological data. Notably, there are comprehensive sections of all major immune cell types with helpful Tables detailing phenotypes in murine and human cells. The latest flow cytometry techniques and applications are also described, featuring examples of the data that can be generated and, importantly, how the data can be analysed. Furthermore, there are sections detailing tips, tricks and pitfalls to avoid, all written and peer-reviewed by leading experts in the field, making this an essential research companion.

Unravelling tumour heterogeneity by single-cell profiling of circulating tumour cells

Single-cell technologies have contributed to unravelling tumour heterogeneity, now considered a hallmark of cancer and one of the main causes of tumour resistance to cancer therapies. Liquid biopsy (LB), defined as the detection and analysis of cells or cell products released by tumours into the blood, offers an appealing minimally invasive approach that allows the characterization and monitoring of tumour heterogeneity in individual patients. Here, we will review and discuss how circulating tumour cell (CTC) analysis at single-cell resolution provides unique insights into tumour heterogeneity that are not revealed by analysis of circulating tumour DNA (ctDNA) derived from LBs. The molecular analysis of CTCs provides complementary information to that of genomic aberrations determined using ctDNA to fully describe many different cellular components (for example, DNA, RNA, proteins and metabolites) that can influence tumour heterogeneity.