Leveraging machine vision in cell-based diagnostics to do more with less

Imaging Flow Cytometry and Convolutional Neural Network-Based Classification Enable Discrimination of Hematopoietic and Leukemic Stem Cells in Acute Myeloid Leukemia

Acute myeloid leukemia (AML) is a heterogenous blood cancer with a dismal prognosis. It emanates from leukemic stem cells (LSCs) arising from the genetic transformation of hematopoietic stem cells (HSCs). LSCs hold prognostic value, but their molecular and immunophenotypic heterogeneity poses challenges: there is no single marker for identifying all LSCs across AML samples. We hypothesized that imaging flow cytometry (IFC) paired with artificial intelligence-driven image analysis could visually distinguish LSCs from HSCs based solely on morphology. Initially, a seven-color IFC panel was employed to immunophenotypically identify LSCs and HSCs in bone marrow samples from five AML patients and ten healthy donors, respectively. Next, we developed convolutional neural network (CNN) models for HSC-LSC discrimination using brightfield (BF), side scatter (SSC), and DNA images. Classification using only BF images achieved 86.96% accuracy, indicating significant morphological differences. Accuracy increased to 93.42% when combining BF with DNA images, highlighting differences in nuclear morphology, although DNA images alone were inadequate for accurate HSC-LSC discrimination. Model development using SSC images revealed minor granularity differences. Performance metrics varied substantially between AML patients, indicating considerable morphologic variations among LSCs. Overall, we demonstrate proof-of-concept results for accurate CNN-based HSC-LSC differentiation, instigating the development of a novel technique within AML monitoring.

Comparative analysis of feature-based ML and CNN for binucleated erythroblast quantification in myelodysplastic syndrome patients using imaging flow cytometry data

Myelodysplastic syndrome is primarily characterized by dysplasia in the bone marrow (BM), presenting a challenge in consistent morphology interpretation. Accurate diagnosis through traditional slide-based analysis is difficult, necessitating a standardized objective technique. Over the past two decades, imaging flow cytometry (IFC) has proven effective in combining image-based morphometric analyses with high-parameter phenotyping. We have previously demonstrated the effectiveness of combining IFC with a feature-based machine learning algorithm to accurately identify and quantify rare binucleated erythroblasts (BNEs) in dyserythropoietic BM cells. However, a feature-based workflow poses challenges requiring software-specific expertise. Here we employ a Convolutional Neural Network (CNN) algorithm for BNE identification and differentiation from doublets and cells with irregular nuclear morphology in IFC data. We demonstrate that this simplified AI workflow, coupled with a powerful CNN algorithm, achieves comparable BNE quantification accuracy to manual and feature-based analysis with substantial time savings, eliminating workflow complexity. This streamlined approach holds significant clinical value, enhancing IFC accessibility for routine diagnostic purposes.

Classification and counting of cells in brightfield microscopy images: an application of convolutional neural networks

Microscopy is integral to medical research, facilitating the exploration of various biological questions, notably cell quantification. However, this process's time-consuming and error-prone nature, attributed to human intervention or automated methods usually applied to fluorescent images, presents challenges. In response, machine learning algorithms have been integrated into microscopy, automating tasks and constructing predictive models from vast datasets. These models adeptly learn representations for object detection, image segmentation, and target classification. An advantageous strategy involves utilizing unstained images, preserving cell integrity and enabling morphology-based classification-something hindered when fluorescent markers are used. The aim is to introduce a model proficient in classifying distinct cell lineages in digital contrast microscopy images. Additionally, the goal is to create a predictive model identifying lineage and determining optimal quantification of cell numbers. Employing a CNN machine learning algorithm, a classification model predicting cellular lineage achieved a remarkable accuracy of 93%, with ROC curve results nearing 1.0, showcasing robust performance. However, some lineages, namely SH-SY5Y (78%), HUH7_mayv (85%), and A549 (88%), exhibited slightly lower accuracies. These outcomes not only underscore the model's quality but also emphasize CNNs' potential in addressing the inherent complexities of microscopic images.

Imaging Flow Cytometry: Development, Present Applications, and Future Challenges

Imaging flow cytometry (ImFC) represents a significant technological advancement in the field of cytometry, effectively merging the high-throughput capabilities of flow analysis with the detailed imaging characteristics of microscopy. In our comprehensive review, we adopt a historical perspective to chart the development of ImFC, highlighting its origins and current state of the art and forecasting potential future advancements. The genesis of ImFC stemmed from merging the hydraulic system of a flow cytometer with advanced camera technology. This synergistic coupling facilitates the morphological analysis of cell populations at a high-throughput scale, effectively evolving the landscape of cytometry. Nevertheless, ImFC's implementation has encountered hurdles, particularly in developing software capable of managing its sophisticated data acquisition and analysis needs. The scale and complexity of the data generated by ImFC necessitate the creation of novel analytical tools that can effectively manage and interpret these data, thus allowing us to unlock the full potential of ImFC. Notably, artificial intelligence (AI) algorithms have begun to be applied to ImFC, offering promise for enhancing its analytical capabilities. The adaptability and learning capacity of AI may prove to be essential in knowledge mining from the high-dimensional data produced by ImFC, potentially enabling more accurate analyses. Looking forward, we project that ImFC may become an indispensable tool, not only in research laboratories, but also in clinical settings. Given the unique combination of high-throughput cytometry and detailed imaging offered by ImFC, we foresee a critical role for this technology in the next generation of scientific research and diagnostics. As such, we encourage both current and future scientists to consider the integration of ImFC as an addition to their research toolkit and clinical diagnostic routine.

Deep learning models for cancer stem cell detection: a brief review

Cancer stem cells (CSCs), also known as tumor-initiating cells (TICs), are a subset of tumor cells that persist within tumors as a distinct population. They drive tumor initiation, relapse, and metastasis through self-renewal and differentiation into multiple cell types, similar to typical stem cell processes. Despite their importance, the morphological features of CSCs have been poorly understood. Recent advances in artificial intelligence (AI) technology have provided automated recognition of biological images of various stem cells, including CSCs, leading to a surge in deep learning research in this field. This mini-review explores the emerging trend of deep learning research in the field of CSCs. It introduces diverse convolutional neural network (CNN)-based deep learning models for stem cell research and discusses the application of deep learning for CSC research. Finally, it provides perspectives and limitations in the field of deep learning-based stem cell research.

A Coal Gangue Identification Method Based on HOG Combined with LBP Features and Improved Support Vector Machine

Identification of coal and gangue is one of the important problems in the coal industry. To improve the accuracy of coal gangue identification in the coal mining process, a coal gangue identification method based on histogram of oriented gradient (HOG) combined with local binary pattern (LBP) features and improved support vector machine (SVM) was proposed. First, according to the actual underground working environment of the mine, a machine vision platform for coal gangue identification was built and the coal gangue image acquisition experiment was carried out. Then, the images of coal and gangue were denoised by median filtering, and the coal and gangue features were extracted by using the HOG combined with LBP feature extraction algorithm, and these features were normalized and principal component analysis (PCA) reduced dimension to remove the correlation and redundancy between the features. Finally, SVM, SVM optimized by genetic algorithm (GA-SVM), SVM optimized by particle swarm optimization (PSO-SVM) algorithm, and SVM optimized by grey wolf optimization (GWO-SVM) algorithm were used as classifiers for identification and classification, respectively. The experimental results show that the GWO-SVM classification model has the highest accuracy, and the average classification accuracies were 96.49% and 94.82% of the training set and test set, respectively, which shows that grey wolf algorithm to optimize support vector machine has a good effect on classification of coal gangue images, which proves the feasibility and accuracy of the proposed method.

Intelligent sort-timing prediction for image-activated cell sorting

Intelligent image-activated cell sorting (iIACS) has enabled high-throughput image-based sorting of single cells with artificial intelligence (AI) algorithms. This AI-on-a-chip technology combines fluorescence microscopy, AI-based image processing, sort-timing prediction, and cell sorting. Sort-timing prediction is particularly essential due to the latency on the order of milliseconds between image acquisition and sort actuation, during which image processing is performed. The long latency amplifies the effects of the fluctuations in the flow speed of cells, leading to fluctuation and uncertainty in the arrival time of cells at the sort point on the microfluidic chip. To compensate for this fluctuation, iIACS measures the flow speed of each cell upstream, predicts the arrival timing of the cell at the sort point, and activates the actuation of the cell sorter appropriately. Here, we propose and demonstrate a machine learning technique to increase the accuracy of the sort-timing prediction that would allow for the improvement of sort event rate, yield, and purity. Specifically, we trained an algorithm to predict the sort timing for morphologically heterogeneous budding yeast cells. The algorithm we developed used cell morphology, position, and flow speed as inputs for prediction and achieved 41.5% lower prediction error compared to the previously employed method based solely on flow speed. As a result, our technique would allow for an increase in the sort event rate of iIACS by a factor of ~2.

Nanoenabled Trainable Systems: From Biointerfaces to Biomimetics

In the dynamic biological system, cells and tissues adapt to diverse environmental conditions and form memories, an essential aspect of training for survival and evolution. An understanding of the biological training principles will inform the design of biomimetic materials whose properties evolve with the environment and offer routes to programmable soft materials, neuromorphic computing, living materials, and biohybrid robotics. In this perspective, we examine the mechanisms by which cells are trained by environmental cues. We outline the artificial platforms that enable biological training and examine the relationship between biological training and biomimetic materials design. We place emphasis on nanoscale material platforms which, given their applicability to chemical, mechanical and electrical stimulation, are critical to bridging natural and synthetic systems.

Deep learning of HIV field-based rapid tests

Although deep learning algorithms show increasing promise for disease diagnosis, their use with rapid diagnostic tests performed in the field has not been extensively tested. Here we use deep learning to classify images of rapid human immunodeficiency virus (HIV) tests acquired in rural South Africa. Using newly developed image capture protocols with the Samsung SM-P585 tablet, 60 fieldworkers routinely collected images of HIV lateral flow tests. From a library of 11,374 images, deep learning algorithms were trained to classify tests as positive or negative. A pilot field study of the algorithms deployed as a mobile application demonstrated high levels of sensitivity (97.8%) and specificity (100%) compared with traditional visual interpretation by humans-experienced nurses and newly trained community health worker staff-and reduced the number of false positives and false negatives. Our findings lay the foundations for a new paradigm of deep learning-enabled diagnostics in low- and middle-income countries, termed REASSURED diagnostics1, an acronym for real-time connectivity, ease of specimen collection, affordable, sensitive, specific, user-friendly, rapid, equipment-free and deliverable. Such diagnostics have the potential to provide a platform for workforce training, quality assurance, decision support and mobile connectivity to inform disease control strategies, strengthen healthcare system efficiency and improve patient outcomes and outbreak management in emerging infections.

AIDeveloper: Deep Learning Image Classification in Life Science and Beyond

Artificial intelligence (AI)-based image analysis has increased drastically in recent years. However, all applications use individual solutions, highly specialized for a particular task. Here, an easy-to-use, adaptable, and open source software, called AIDeveloper (AID) to train neural nets (NN) for image classification without the need for programming is presented. AID provides a variety of NN-architectures, allowing to apply trained models on new data, obtain performance metrics, and export final models to different formats. AID is benchmarked on large image datasets (CIFAR-10 and Fashion-MNIST). Furthermore, models are trained to distinguish areas of differentiated stem cells in images of cell culture. A conventional blood cell count and a blood count obtained using an NN are compared, trained on >1.2 million images, and demonstrated how AID can be used for label-free classification of B- and T-cells. All models are generated by non-programmers on generic computers, allowing for an interdisciplinary use.

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.

Robust Carbonated Structural Color Barcodes with Ultralow Ontology Fluorescence as Biomimic Culture Platform

Photonic crystal (PC) barcodes are a new type of spectrum-encoding microcarriers used in multiplex high-throughput bioassays, such as broad analysis of biomarkers for clinical diagnosis, gene expression, and cell culture. Unfortunately, most of these existing PC barcodes suffered from undesired features, including difficult spectrum-signal acquisition, weak mechanical strength, and high ontology fluorescence, which limited their development to real applications. To address these limitations, we report a new type of structural color-encoded PC barcodes. The barcodes are fabricated by the assembly of monodisperse polydopamine- (PDA-) coated silica (PDA@SiO₂) nanoparticles using a droplet-based microfluidic technique and followed by pyrolysis of PDA@SiO₂ (C@SiO₂) barcodes. Because of the templated carbonization of adhesive PDA, the prepared C@SiO₂ PC beads were endowed with simultaneous easy-to-identify structural color, high mechanical strength, and ultralow ontology fluorescence. We demonstrated that the structural colored C@SiO₂ barcodes not only maintained a high structural stability and good biocompatibility during the coculturing with fibroblasts and tumor cells capture but also achieved an enhanced fluorescent-reading signal-to-noise ratio in the fluorescence-reading detection. These features make the C@SiO₂ PC barcodes versatile for expansive application in fluorescence-reading-based multibioassays.

Critical assessment of AI in drug discovery

Introduction: Artificial Intelligence (AI) has become a component of our everyday lives, with applications ranging from recommendations on what to buy to the analysis of radiology images. Many of the techniques originally developed for other fields such as language translation and computer vision are now being applied in drug discovery. AI has enabled multiple aspects of drug discovery including the analysis of high content screening data, and the design and synthesis of new molecules.Areas covered: This perspective provides an overview of the application of AI in several areas relevant to drug discovery including property prediction, molecule generation, image analysis, and organic synthesis planning.Expert opinion: While a variety of machine learning methods are now being routinely used to predict biological activity and ADME properties, methods of representing molecules continue to evolve. Molecule generation methods are relatively new and unproven but hold the potential to access new, unexplored areas of chemical space. The application of AI in drug discovery will continue to benefit from dedicated research, as well as AI developments in other fields. With this pairing algorithmic advancements and high-quality data, the impact of AI in drug discovery will continue to grow in the coming years.

Machine learning based approach to pH imaging and classification of single cancer cells

The ability to identify different cell populations in a noninvasive manner and without the use of fluorescence labeling remains an important goal in biomedical research. Various techniques have been developed over the last decade, which mainly rely on fluorescent probes or nanoparticles. On the other hand, their applications to single-cell studies have been limited by the lengthy preparation and labeling protocols, as well as issues relating to reproducibility and sensitivity. Furthermore, some of these techniques require the cells to be fixed. Interestingly, it has been shown that different cell types exhibit a unique intracellular environment characterized by specific acidity conditions as a consequence of their distinct functions and metabolism. Here, we leverage a recently developed pH imaging modality and machine learning-based single-cell segmentation and classification to identify different cancer cell lines based on their characteristic intracellular pH. This simple method opens up the potential to perform rapid noninvasive identification of living cancer cells for early cancer diagnosis and further downstream analyses.

Microscopy-based assay for semi-quantitative detection of SARS-CoV-2 specific antibodies in human sera: A semi-quantitative, high throughput, microscopy-based assay expands existing approaches to measure SARS-CoV-2 specific antibody levels in human sera

Emergence of the novel pathogenic coronavirus SARS-CoV-2 and its rapid pandemic spread presents challenges that demand immediate attention. Here, we describe the development of a semi-quantitative high-content microscopy-based assay for detection of three major classes (IgG, IgA, and IgM) of SARS-CoV-2 specific antibodies in human samples. The possibility to detect antibodies against the entire viral proteome together with a robust semi-automated image analysis workflow resulted in specific, sensitive and unbiased assay that complements the portfolio of SARS-CoV-2 serological assays. Sensitive, specific and quantitative serological assays are urgently needed for a better understanding of humoral immune response against the virus as a basis for developing public health strategies to control viral spread. The procedure described here has been used for clinical studies and provides a general framework for the application of quantitative high-throughput microscopy to rapidly develop serological assays for emerging virus infections.

Image-based profiling for drug discovery: due for a machine-learning upgrade?

Image-based profiling is a maturing strategy by which the rich information present in biological images is reduced to a multidimensional profile, a collection of extracted image-based features. These profiles can be mined for relevant patterns, revealing unexpected biological activity that is useful for many steps in the drug discovery process. Such applications include identifying disease-associated screenable phenotypes, understanding disease mechanisms and predicting a drug's activity, toxicity or mechanism of action. Several of these applications have been recently validated and have moved into production mode within academia and the pharmaceutical industry. Some of these have yielded disappointing results in practice but are now of renewed interest due to improved machine-learning strategies that better leverage image-based information. Although challenges remain, novel computational technologies such as deep learning and single-cell methods that better capture the biological information in images hold promise for accelerating drug discovery.

Maternal thyroid profile in first and second trimester of pregnancy is correlated with gestational diabetes mellitus through machine learning

There is evidence about a possible relationship between thyroid abnormalities and gestational diabetes mellitus (GDM). However, there is still no conclusive data on this dependence, since no strong correlation has been proved. In this work, we used machine learning to determine whether there is a correlation between maternal thyroid profile in first and second trimester of pregnancy and GDM. Using principal component analysis, it was possible to find an evident correlation between both, which could be used as a complement for a more sensitive GDM diagnosis.

AI on a chip

Artificial intelligence (AI) has dramatically changed the landscape of science, industry, defence, and medicine in the last several years. Supported by considerably enhanced computational power and cloud storage, the field of AI has shifted from mostly theoretical studies in the discipline of computer science to diverse real-life applications such as drug design, material discovery, speech recognition, self-driving cars, advertising, finance, medical imaging, and astronomical observation, where AI-produced outcomes have been proven to be comparable or even superior to the performance of human experts. In these applications, what is essentially important for the development of AI is the data needed for machine learning. Despite its prominent importance, the very first process of the AI development, namely data collection and data preparation, is typically the most laborious task and is often a limiting factor of constructing functional AI algorithms. Lab-on-a-chip technology, in particular microfluidics, is a powerful platform for both the construction and implementation of AI in a large-scale, cost-effective, high-throughput, automated, and multiplexed manner, thereby overcoming the above bottleneck. On this platform, high-throughput imaging is a critical tool as it can generate high-content information (e.g., size, shape, structure, composition, interaction) of objects on a large scale. High-throughput imaging can also be paired with sorting and DNA/RNA sequencing to conduct a massive survey of phenotype-genotype relations whose data is too complex to analyze with traditional computational tools, but is analyzable with the power of AI. In addition to its function as a data provider, lab-on-a-chip technology can also be employed to implement the developed AI for accurate identification, characterization, classification, and prediction of objects in mixed, heterogeneous, or unknown samples. In this review article, motivated by the excellent synergy between AI and lab-on-a-chip technology, we outline fundamental elements, recent advances, future challenges, and emerging opportunities of AI with lab-on-a-chip technology or "AI on a chip" for short.

Machine learning analyses of methylation profiles uncovers tissue-specific gene expression patterns in wheat

DNA methylation is a mechanism of epigenetic modification in eukaryotic organisms. Generally, methylation within genes promoter inhibits regulatory protein binding and represses transcription, whereas gene body methylation is associated with actively transcribed genes. However, it remains unclear whether there is interaction between methylation levels across genic regions and which site has the biggest impact on gene regulation. We investigated and used the methylation patterns of the bread wheat cultivar Chinese Spring to uncover differentially expressed genes (DEGs) between roots and leaves, using six machine learning algorithms and a deep neural network. As anticipated, genes with higher expression in leaves were mainly involved in photosynthesis and pigment biosynthesis processes whereas genes that were not differentially expressed between roots and leaves were involved in protein processes and membrane structures. Methylation occurred preponderantly (60%) in the CG context, whereas 35 and 5% of methylation occurred in CHG and CHH contexts, respectively. Methylation levels were highly correlated (r = 0.7 to 0.9) between all genic regions, except within the promoter (r = 0.4 to 0.5). Machine learning models gave a high (0.81) prediction accuracy of DEGs. There was a strong correlation (p-value = 9.20×10^-10 ) between all features and gene expression, suggesting that methylation across all genic regions contribute to gene regulation. However, the methylation of the promoter, the CDS and the exon in CG context was the most impactful. Our study provides more insights into the interplay between DNA methylation and gene expression and paves the way for identifying tissue-specific genes using methylation profiles.

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.

Detecting cardiac pathologies via machine learning on heart-rate variability time series and related markers

In this paper we develop statistical algorithms to infer possible cardiac pathologies, based on data collected from 24 h Holter recording over a sample of 2829 labelled patients; labels highlight whether a patient is suffering from cardiac pathologies. In the first part of the work we analyze statistically the heart-beat series associated to each patient and we work them out to get a coarse-grained description of heart variability in terms of 49 markers well established in the reference community. These markers are then used as inputs for a multi-layer feed-forward neural network that we train in order to make it able to classify patients. However, before training the network, preliminary operations are in order to check the effective number of markers (via principal component analysis) and to achieve data augmentation (because of the broadness of the input data). With such groundwork, we finally train the network and show that it can classify with high accuracy (at most ~85% successful identifications) patients that are healthy from those displaying atrial fibrillation or congestive heart failure. In the second part of the work, we still start from raw data and we get a classification of pathologies in terms of their related networks: patients are associated to nodes and links are drawn according to a similarity measure between the related heart-beat series. We study the emergent properties of these networks looking for features (e.g., degree, clustering, clique proliferation) able to robustly discriminate between networks built over healthy patients or over patients suffering from cardiac pathologies. We find overall very good agreement among the two paved routes.

The metamorphosis of analytical chemistry

Defining analytical chemistry as the measurement of isolated compositional features in a selected study object ignores the unique perspective that analytical chemists bring to twenty-first century science and society. In this feature article, we will discuss some of the existing preconceptions and misinterpretations of analytical chemistry that occur at present and will tackle them from the more up-to-date perspective of science in the Big Data Era. This will place their influence in context while simultaneously enlarging the scope of the discipline analytical chemistry to its well-deserved prevalent position in present-day science and technology. Graphical abstract.

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.

DeepMalaria: Artificial Intelligence Driven Discovery of Potent Antiplasmodials

Antimalarial drugs are becoming less effective due to the emergence of drug resistance. Resistance has been reported for all available malaria drugs, including artemisinin, thus creating a perpetual need for alternative drug candidates. The traditional drug discovery approach of high throughput screening (HTS) of large compound libraries for identification of new drug leads is time-consuming and resource intensive. While virtual in silico screening is a solution to this problem, however, the generalization of the models is not ideal. Artificial intelligence (AI), utilizing either structure-based or ligand-based approaches, has demonstrated highly accurate performances in the field of chemical property prediction. Leveraging the existing data, AI would be a suitable alternative to blind-search HTS or fingerprint-based virtual screening. The AI model would learn patterns within the data and help to search for hit compounds efficiently. In this work, we introduce DeepMalaria, a deep-learning based process capable of predicting the anti-Plasmodium falciparum inhibitory properties of compounds using their SMILES. A graph-based model is trained on 13,446 publicly available antiplasmodial hit compounds from GlaxoSmithKline (GSK) dataset that are currently being used to find novel drug candidates for malaria. We validated this model by predicting hit compounds from a macrocyclic compound library and already approved drugs that are used for repurposing. We have chosen macrocyclic compounds as these ligand-binding structures are underexplored in malaria drug discovery. The in silico pipeline for this process also consists of additional validation of an in-house independent dataset consisting mostly of natural product compounds. Transfer learning from a large dataset was leveraged to improve the performance of the deep learning model. To validate the DeepMalaria generated hits, we used a commonly used SYBR Green I fluorescence assay based phenotypic screening. DeepMalaria was able to detect all the compounds with nanomolar activity and 87.5% of the compounds with greater than 50% inhibition. Further experiments to reveal the compounds’ mechanism of action have shown that not only does one of the hit compounds, DC-9237, inhibits all asexual stages of Plasmodium falciparum, but is a fast-acting compound which makes it a strong candidate for further optimization.

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.

Looking beyond the hype: Applied AI and machine learning in translational medicine

Big data problems are becoming more prevalent for laboratory scientists who look to make clinical impact. A large part of this is due to increased computing power, in parallel with new technologies for high quality data generation. Both new and old techniques of artificial intelligence (AI) and machine learning (ML) can now help increase the success of translational studies in three areas: drug discovery, imaging, and genomic medicine. However, ML technologies do not come without their limitations and shortcomings. Current technical limitations and other limitations including governance, reproducibility, and interpretation will be discussed in this article. Overcoming these limitations will enable ML methods to be more powerful for discovery and reduce ambiguity within translational medicine, allowing data-informed decision-making to deliver the next generation of diagnostics and therapeutics to patients quicker, at lowered costs, and at scale.

Omics Meeting Onics: Towards the Next Generation of Spectroscopic-Based Technologies in Personalized Medicine

This article aims to discuss the recent development of integrated point-of-care spectroscopic-based technologies that are paving the way for the next generation of diagnostic monitoring technologies in personalized medicine. Focusing on the nuclear magnetic resonance (NMR) technologies as the leading example, we discuss the emergence of -onics technologies (e.g., photonics and electronics) and how their coexistence with -omics technologies (e.g., genomics, proteomics, and metabolomics) can potentially change the future technological landscape of personalized medicine. The idea of an open-source (e.g., hardware and software) movement is discussed, and we argue that technology democratization will not only promote the dissemination of knowledge and inspire new applications, but it will also increase the speed of field implementation.

Design of Hierarchical Beads for Efficient Label-Free Cell Capture

Defined hierarchical materials promise cell analysis and call for application-driven design in practical use. The further issue is to develop advanced materials and devices for efficient label-free cell capture with minimum instrumentation. Herein, the design of hierarchical beads is reported for efficient label-free cell capture. Silica nanoparticles (size of ≈15 nm) are coated onto silica spheres (size of ≈200 nm) to achieve nanoscale surface roughness, and then the rough silica spheres are combined with microbeads (≈150-1000 µm in diameter) to assemble hierarchical structures. These hierarchical beads are built via electrostatic interaction, covalent bonding, and nanoparticle adherence. Further, after functionalization by hyaluronic acid (HA), the hierarchical beads display desirable surface hydrophilicity, biocompatibility, and chemical/structural stability. Due to the controlled surface topology and chemistry, HA-functionalized hierarchical beads afford high cell capture efficiency up to 98.7% in a facile label-free manner. This work guides the development of label-free cell capture techniques and contributes to the construction of smart interfaces in bio-systems.