Critical assessment of automated flow cytometry data analysis techniques

Amino Acid Stress Response Genes Contribute to a 25-Fold Increased Risk of L-Asparaginase-Induced Hypersensitivity

BACKGROUND

L-asparaginase is essential in treating pediatric acute lymphoblastic leukemia (ALL) but is limited by hypersensitivity reactions in up to 70% of patients, leading to severe, dose-limiting complications and compromised event-free survival.

PROCEDURE

This study conducted a genome-wide association study (GWAS) in a discovery cohort of 221 pediatric cancer patients who experienced l-asparaginase-induced hypersensitivity reactions (≥CTCAE grade 2) and 705 controls without hypersensitivity despite equivalent exposure. Results were replicated in an independent cohort of 41 cases and 139 controls.

RESULTS

Significant associations were identified between hypersensitivity and four genes crucial for amino acid stress response: CYP1B1 (rs59569490; odds ratio [OR]  =  8.5; 95% confidence interval [CI], 3.9-18.5; p  =  1.5 × 10-10), SEC16B (rs115461320; OR  =  4.2; 95% CI, 2.5-7.9; p  =  1.2 × 10-6), OPLAH (rs11993268; OR  =  4.8; 95% CI, 2.4-9.9; p  =  2.0 × 10-6), and SORCS2 (rs11940340; OR  =  6.7; 95% CI, 2.8-15.7; p  =  5.7 × 10-7). Variants in SEC16B, OPLAH, and SORCS2 remained significant in the analysis of the replication cohort (p < 0.05). Patients who carried risk alleles in two or more of these genes experienced an 86.4% increased incidence of hypersensitivity reactions in the discovery cohort (OR  =  25.2; 95% CI, 7.4-86.2; p  =  1.0 × 10-10), which was replicated in the independent cohort with a 100% incidence in carriers (p  =  0.04).

CONCLUSIONS

The cumulative incidence of these large effect variants highlights their significance for the identification of patients at high risk of l-asparaginase-induced hypersensitivity. Successfully identifying patients at increased risk of hypersensitivity reactions can inform personalized treatment strategies and limit these harmful dose-limiting reactions in pediatric ALL.

Raman spectroscopy for cell analysis: Retrospect and prospect

Cell analysis is crucial to contemporary biomedical research, as it plays a pivotal role in elucidating life processes and advancing disease diagnosis and treatment. Raman spectroscopy, harnessing distinctive molecular vibrational data, provides a non-destructive method for cell analysis. This review surveys the progress of Raman spectroscopy in cellular analysis, emphasizing its utility in identifying individual cells, monitoring biomolecules, and assessing intracellular environments. A significant focus is placed on the novel application of triple-bond molecules as Raman tags, which enhance imaging capabilities by creating a distinctive signature with minimal background noise. The summary of Raman spectroscopy studies provides a forward-looking perspective on its applications.

Single-cell omics technologies - Fundamentals on how to create single-cell looking glasses for reproductive health

Over the last decade, in line with the goals of precision medicine to offer individualized patient care, various single-cell technologies measuring gene and proteomic expression in various tissues have rapidly advanced to study health and disease at the single cell level. Precisely understanding cell composition, position within tissues, signaling pathways, and communication can reveal insights into disease mechanisms and systemic changes during development, pregnancy, and gynecologic disorders across the lifespan. Single-cell technologies dissect the complex cellular compositions of reproductive tract tissues, providing insights into mechanisms behind reproductive tract dysfunction which impact wellness and quality of life. These technologies aim to understand basic tissue and organ functions and, clinically, to develop novel diagnostics, early disease biomarkers, and cell-targeted therapies for currently suboptimally-treated disorders. Increasingly, they are applied to pregnancy and pregnancy disorders, gynecologic malignancies, and uterine and ovarian physiology and aging, which are discussed in more detail in manuscripts in this special issue of AJOG. Here, we review recent applications of single-cell technologies to the study of gynecologic disorders and systemic biological adaptations during fetal development, pregnancy, and across a woman's lifespan. We discuss sequencing- and proteomic-based single-cell methods, as well as spatial transcriptomics and high-dimensional proteomic imaging, describing each technology's mechanism, workflow, quality control, and highlighting specific benefits, drawbacks, and utility in the context of reproductive medicine. We consider analytical methods for the high-dimensional single-cell data generated, highlighting statistical constraints and recent computational techniques for downstream clinical translation. Overall, current and evolving single-cell "looking glasses", or perspectives, have the potential to transform fundamental understanding of women's health and reproductive disorders and alter the trajectory of clinical practice and patient outcomes in the future.

Computational flow cytometry immunophenotyping at diagnosis is unable to predict relapse in childhood B-cell Acute Lymphoblastic Leukemia

B-cell Acute Lymphoblastic Leukemia is the most prevalent form of childhood cancer, with approximately 15% of patients undergoing relapse after initial treatment. Further advancements depend on novel therapies and more precise risk stratification criteria. In the context of computational flow cytometry and machine learning, this paper aims to explore the potential prognostic value of flow cytometry data at diagnosis, a relatively unexplored direction for relapse prediction in this disease. To this end, we collected a dataset of 252 patients from three hospitals and implemented a comprehensive pipeline for multicenter data integration, feature extraction, and patient classification, comparing the results with existing algorithms from the literature. The analysis revealed no significant differences in immunophenotypic patterns between relapse and non-relapse patients and suggests the need for alternative approaches to handle flow cytometry data in relapse prediction.

Advanced sperm preservation techniques in yellow spotted mountain newts Neurergus derjugini enhance genetic management and conservation efforts

Advances in cold storage and cryopreservation of amphibian sperm are critical for the genetic management and conservation of threatened species. This study represents the first investigation into the sperm of the yellow spotted mountain newt (Neurergus derjugini), focusing on both short-term and long-term storage for future reproductive efforts. We examined the effects of seven extenders on sperm motility over time at three storage temperatures (4 ± 1 °C, 9 ± 1 °C, and 20 ± 1 °C). Additionally, we assessed the impact of 16 cryoprotectants on sperm motility and morphology post-thawing. Following the identification of the most effective freezing medium, we evaluated sperm DNA fragmentation to ensure viability. Our results indicate that 10% Holtfreter's solution is the optimal extender for short-term storage at all three temperatures, maintaining sperm motility for up to 15 days at 4 °C. For long-term storage, a combination of 10% Holtfreter's solution and 10% DMSO was found to best preserve sperm motility, morphology, and minimize DNA fragmentation after thawing. These findings underscore the importance of specific extenders and temperature treatments in enhancing sperm functionality, thereby supporting successful assisted reproductive technologies (ART) for endangered species.

A User-Centric Approach to Reliable Automated Flow Cytometry Data Analysis for Biomedical Applications

Automation and the increased number of measurable parameters in flow cytometry (FCM) have strongly increased the volume and complexity of phenotyping immune cell populations. Despite numerous automated gating methods for FCM analysis, their adoption in routine practice remains challenging due to accessibility barriers for users and potential model failures. Here, we propose a user-centered solution that combines elements of supervised machine learning (SML), rapid application development (RAD), systematic quality assurance guided by structured argumentation, and uncertainty estimation to address these challenges. We implement a data-driven model for event classification and use RAD to generate software prototypes, allowing FCM users to apply the model for automated gating. Considering concepts for structured argumentation from assurance cases (ACs), we derived and justified quality analyses that inform users about the quality of the model. We propose guiding the model operation phase using uncertainty estimation to provide users with a clear understanding of the model's confidence in its predictions. We aim to overcome barriers to the routine application of automated gating and contribute to more reliable and efficient FCM data analysis. Our approach is based on the application of phenotyping for human immune cells. We encourage future research to investigate the potential of SML, ACs, and uncertainty estimation to address dependability of data-driven models (DDMs) supporting diagnostic decision making in the medical domain, including FCM in clinical applications and highly regulated areas such as pharmaceutical research.

Machine Learning Methods in Clinical Flow Cytometry

This review will explore the integration of machine learning (ML) techniques to enhance the analysis of increasingly complex and voluminous flow cytometry data, as traditional manual methods are insufficient for handling this data. We attempt to provide a comprehensive introduction to ML in flow cytometry, detailing the transition from manual gating to computational methods and emphasizing the importance of data quality. Key ML techniques are discussed, including supervised learning methods like logistic regression, support vector machines, and neural networks, which rely on labeled data to classify disease states. Unsupervised methods, such as k-means clustering, FlowSOM, UMAP, and t-SNE, are highlighted for their ability to identify novel cell populations without predefined labels. We also delve into newer semi-supervised and weakly supervised methods, which leverage partial labeling to improve model performance. Practical aspects of implementing ML in clinical settings are addressed, including regulatory considerations, data preprocessing, model training, validation, and the importance of generalizability, and we underscore the collaborative effort required among pathologists, data scientists, and laboratory professionals to ensure robust model development and deployment. Finally, we show the transformative potential of ML in flow cytometry in uncovering new biological insights through advanced computational techniques.

Deciphering cellular complexity: advances and future directions in single-cell protein analysis

Single-cell protein analysis has emerged as a powerful tool for understanding cellular heterogeneity and deciphering the complex mechanisms governing cellular function and fate. This review provides a comprehensive examination of the latest methodologies, including sophisticated cell isolation techniques (Fluorescence-Activated Cell Sorting (FACS), Magnetic-Activated Cell Sorting (MACS), Laser Capture Microdissection (LCM), manual cell picking, and microfluidics) and advanced approaches for protein profiling and protein-protein interaction analysis. The unique strengths, limitations, and opportunities of each method are discussed, along with their contributions to unraveling gene regulatory networks, cellular states, and disease mechanisms. The importance of data analysis and computational methods in extracting meaningful biological insights from the complex data generated by these technologies is also highlighted. By discussing recent progress, technological innovations, and potential future directions, this review emphasizes the critical role of single-cell protein analysis in advancing life science research and its promising applications in precision medicine, biomarker discovery, and targeted therapeutics. Deciphering cellular complexity at the single-cell level holds immense potential for transforming our understanding of biological processes and ultimately improving human health.

Evaluating Strategies to Assess the Differentiation Potential of Human Pluripotent Stem Cells: A Review, Analysis and Call for Innovation

Pluripotent stem cells have the ability to differentiate into all cells and tissues within the human body, and as a result they are attractive resources for use in basic research, drug discovery and regenerative medicine. In order to successfully achieve this application, starting cell sources ideally require in-depth characterisation to confirm their pluripotent status and their ability to differentiate into tissues representative of the three developmental germ layers. Many different methods to assess potency are employed, each having its own distinct advantages and limitations. Some aspects of this characterisation process are not always well standardised, particularly techniques used to assess pluripotency as a function. In this article, we consider the methods used to establish cellular pluripotency and subsequently analyse characterisation data for over 1590 human pluripotent cell lines from publicly available repositories in the UK and USA. In particular, we focus on the teratoma xenograft assay, its use and protocols, demonstrating the level of variation and the frequency with which it is used. Finally, we reflect on the implications of the findings, and suggest in vitro alternatives using modern innovative technology as a way forward.

Unveiling the power of high-dimensional cytometry data with cyCONDOR

High-dimensional cytometry (HDC) is a powerful technology for studying single-cell phenotypes in complex biological systems. Although technological developments and affordability have made HDC broadly available in recent years, technological advances were not coupled with an adequate development of analytical methods that can take full advantage of the complex data generated. While several analytical platforms and bioinformatics tools have become available for the analysis of HDC data, these are either web-hosted with limited scalability or designed for expert computational biologists, making their use unapproachable for wet lab scientists. Additionally, end-to-end HDC data analysis is further hampered due to missing unified analytical ecosystems, requiring researchers to navigate multiple platforms and software packages to complete the analysis. To bridge this data analysis gap in HDC we develop cyCONDOR, an easy-to-use computational framework covering not only all essential steps of cytometry data analysis but also including an array of downstream functions and tools to expand the biological interpretation of the data. The comprehensive suite of features of cyCONDOR, including guided pre-processing, clustering, dimensionality reduction, and machine learning algorithms, facilitates the seamless integration of cyCONDOR into clinically relevant settings, where scalability and disease classification are paramount for the widespread adoption of HDC in clinical practice. Additionally, the advanced analytical features of cyCONDOR, such as pseudotime analysis and batch integration, provide researchers with the tools to extract deeper insights from their data. We use cyCONDOR on a variety of data from different tissues and technologies demonstrating its versatility to assist the analysis of high-dimensional data from preprocessing to biological interpretation.

A beginner's guide to supervised analysis for mass cytometry data in cancer biology

Mass cytometry enables deep profiling of biological samples at single-cell resolution. This technology is more than relevant in cancer research due to high cellular heterogeneity and complexity. Downstream analysis of high-dimensional datasets increasingly relies on machine learning (ML) to extract clinically relevant information, including supervised algorithms for classification and regression purposes. In cancer research, they are used to develop predictive models that will guide clinical decision making. However, the development of supervised algorithms faces major challenges, such as sufficient validation, before being translated into the clinics. In this work, we provide a framework for the analysis of mass cytometry data with a specific focus on supervised algorithms and practical examples of their applications. We also raise awareness on key issues regarding good practices for researchers curious to implement supervised ML on their mass cytometry data. Finally, we discuss the challenges of supervised ML application to cancer research.

SingletSeeker: an unsupervised clustering approach for automated singlet discrimination in cytometry

Flow cytometry is a high-throughput, high-dimensional technique that generates large sets of single-cell data. Prior to analyzing this data, it is common to exclude any events that contain two or more cells, multiplets, to ensure downstream analysis and quantification is of single-cell events, singlets, only. The process of singlet discrimination is critical yet fundamentally subjective and time-consuming; it is performed manually by the user, where the proper exclusion of multiplets depends on the user's expertise and often varies from experiment to experiment. To address this problem, we have developed an algorithm to automatically discriminate singlets from other unwanted events such as multiplets and debris. Using parameters derived from imaging, the algorithm first identifies high-density clusters of events using a density-based clustering algorithm, and then classifies the clusters based on their properties. Multiplets are discarded in the first step, while singlets are distinguished from debris in the second step. The algorithm can use different strategies on imaging feature selection-based user's preferences and imaging features available. In addition, the relative importance of singlets precision vs. sensitivity can be further tweaked via a density coefficient adjustment. Twenty-two datasets from various sites and of various cell types acquired on the BD FACSDiscover™ S8 Cell Sorter with CellView™ Image Technology were used to develop and validate the algorithm across multiple imaging feature sets. A consistent singlets precision >97% with a solid >88% sensitivity has been demonstrated with a LightLoss feature set and the default density coefficient. This work yields a high-precision, high-sensitivity algorithm capable of objective and automated singlet discrimination across multiple cell types using various imaging-derived parameters. A free FlowJo™ Software plugin implementation is available for simple and reproducible singlet discrimination for use at the beginning of any user's workflow.

Artificial intelligence in Andrological flow cytometry: The next step?

Since its introduction in animal andrology, flow cytometry (FC) has dramatically evolved. Nowadays, many compartments and functions of the spermatozoa can be analyzed in thousands of spermatozoa, including, but not limited to DNA, acrosome, membrane integrity, membrane symmetry, permeability, and polarity; mitochondrial mass and mitochondrial membrane potential, identification of reactive oxygen species, ion dynamics, and cellular signaling among many others. Improved machines, many more probes, and new software are greatly expanding the amount of information that can be obtained from each flow cytometry analysis. Modern flow cytometers permit the simultaneous investigation of many different sperm compartments and functions and their interactions, allowing the identification of sperm phenotypes, helping to disclose different sperm populations within the ejaculate. Complex flow cytometry panels require a careful design of the experiment, including selecting probes (fully understanding the characteristics and properties of them) and adequate controls (technical and biological). Ideally, compensation and management of data ("cleaning", transformations, the establishment of gates) are better performed post-acquisition using specific software. Data can be expressed as a percentage of positive cells (typically viability assays), intensity of fluorescence (arbitrary fluorescence units, i.e. changes in intracellular Ca2+) or dim and bright populations (typically assays of membrane permeability or antigen expression). Furthermore, artificial intelligence/self-learning algorithms are improving visualization and management of data generated by modern flow cytometers. In this paper, recent developments in flow cytometry for animal andrology will be briefly reviewed; moreover, a small flow cytometry experiment will be used to illustrate how these techniques can improve data analysis.

High-Performance Suspension Bead Sensor Based on Optical Tweezers and Immuno-Rolling Circle Amplification

In recent years, optical tweezers have become an effective bioassay tool due to their unique advantages, especially in combination with suspension beads, which can be applied to develop a high-performance analysis platform capable of high-quality imaging and stable signal output. However, the optical tweezer-assisted bead analysis is still at the early stage, and further development of different favorable methods is in need. Herein, we have first developed the optical tweezer-assisted immuno-rolling circle amplification (immuno-RCA) on beads for protein detection. Prostate-specific antigen was selected as the model analyte, and the immunosandwich structure on beads was built by the high affinity of "antibody-antigen". The "protein-nucleic acid" signals were effectively converted through the covalent coupling procedure of antibodies and oligonucleotides, further initiating the RCA reaction to achieve signal amplification. The individual beads with the strong irregular Brownian motion in a fluid environment were eventually trapped by the optical tweezers to acquire the accurate and high-quality signal. Compared with the conventional immunoassay on beads, the sensitivity of the developed strategy was increased by 587 times with a limit of detection of 4.29 pg/mL (0.13 pM), as well as excellent specificity, stability, and reproducibility. This study developed the new optical tweezer-assisted beads imaging strategy for protein targets, which has great potential for being applied to clinical serology research and expands the application of optical tweezers in the bioassays.

Recommendations for using artificial intelligence in clinical flow cytometry

Flow cytometry is a key clinical tool in the diagnosis of many hematologic malignancies and traditionally requires close inspection of digital data by hematopathologists with expert domain knowledge. Advances in artificial intelligence (AI) are transferable to flow cytometry and have the potential to improve efficiency and prioritization of cases, reduce errors, and highlight fundamental, previously unrecognized associations with underlying biological processes. As a multidisciplinary group of stakeholders, we review a range of critical considerations for appropriately applying AI to clinical flow cytometry, including use case identification, low and high risk use cases, validation, revalidation, computational considerations, and the present regulatory frameworks surrounding AI in clinical medicine. In particular, we provide practical guidance for the development, implementation, and suggestions for potential regulation of AI-based methods in the clinical flow cytometry laboratory. We expect these recommendations to be a helpful initial framework of reference, which will also require additional updates as the field matures.

Comparison of three machine learning algorithms for classification of B-cell neoplasms using clinical flow cytometry data

Multiparameter flow cytometry data is visually inspected by expert personnel as part of standard clinical disease diagnosis practice. This is a demanding and costly process, and recent research has demonstrated that it is possible to utilize artificial intelligence (AI) algorithms to assist in the interpretive process. Here we report our examination of three previously published machine learning methods for classification of flow cytometry data and apply these to a B-cell neoplasm dataset to obtain predicted disease subtypes. Each of the examined methods classifies samples according to specific disease categories using ungated flow cytometry data. We compare and contrast the three algorithms with respect to their architectures, and we report the multiclass classification accuracies and relative required computation times. Despite different architectures, two of the methods, flowCat and EnsembleCNN, had similarly good accuracies with relatively fast computational times. We note a speed advantage for EnsembleCNN, particularly in the case of addition of training data and retraining of the classifier.

Tracking single hiPSC-derived cardiomyocyte contractile function using CONTRAX an efficient pipeline for traction force measurement

Cardiomyocytes derived from human induced pluripotent stem cells (hiPSC-CMs) are powerful in vitro models to study the mechanisms underlying cardiomyopathies and cardiotoxicity. Quantification of the contractile function in single hiPSC-CMs at high-throughput and over time is essential to disentangle how cellular mechanisms affect heart function. Here, we present CONTRAX, an open-access, versatile, and streamlined pipeline for quantitative tracking of the contractile dynamics of single hiPSC-CMs over time. Three software modules enable: parameter-based identification of single hiPSC-CMs; automated video acquisition of >200 cells/hour; and contractility measurements via traction force microscopy. We analyze >4,500 hiPSC-CMs over time in the same cells under orthogonal conditions of culture media and substrate stiffnesses; +/- drug treatment; +/- cardiac mutations. Using undirected clustering, we reveal converging maturation patterns, quantifiable drug response to Mavacamten and significant deficiencies in hiPSC-CMs with disease mutations. CONTRAX empowers researchers with a potent quantitative approach to develop cardiac therapies.

An automatic analysis and quality assurance method for lymphocyte subset identification

OBJECTIVES

Lymphocyte subsets are the predictors of disease diagnosis, treatment, and prognosis. Determination of lymphocyte subsets is usually carried out by flow cytometry. Despite recent advances in flow cytometry analysis, most flow cytometry data can be challenging with manual gating, which is labor-intensive, time-consuming, and error-prone. This study aimed to develop an automated method to identify lymphocyte subsets.

METHODS

We propose a knowledge-driven combined with data-driven method which can gate automatically to achieve subset identification. To improve accuracy and stability, we have implemented a Loop Adjustment Gating to optimize the gating result of the lymphocyte population. Furthermore, we have incorporated an anomaly detection mechanism to issue warnings for samples that might not have been successfully analyzed, ensuring the quality of the results.

RESULTS

The evaluation showed a 99.2 % correlation between our method results and manual analysis with a dataset of 2,000 individual cases from lymphocyte subset assays. Our proposed method attained 97.7 % accuracy for all cases and 100 % for the high-confidence cases. With our automated method, 99.1 % of manual labor can be saved when reviewing only the low-confidence cases, while the average turnaround time required is only 29 s, reducing by 83.7 %.

CONCLUSIONS

Our proposed method can achieve high accuracy in flow cytometry data from lymphocyte subset assays. Additionally, it can save manual labor and reduce the turnaround time, making it have the potential for application in the laboratory.

GammaGateR: semi-automated marker gating for single-cell multiplexed imaging

MOTIVATION

Multiplexed immunofluorescence (mIF) is an emerging assay for multichannel protein imaging that can decipher cell-level spatial features in tissues. However, existing automated cell phenotyping methods, such as clustering, face challenges in achieving consistency across experiments and often require subjective evaluation. As a result, mIF analyses often revert to marker gating based on manual thresholding of raw imaging data.

RESULTS

To address the need for an evaluable semi-automated algorithm, we developed GammaGateR, an R package for interactive marker gating designed specifically for segmented cell-level data from mIF images. Based on a novel closed-form gamma mixture model, GammaGateR provides estimates of marker-positive cell proportions and soft clustering of marker-positive cells. The model incorporates user-specified constraints that provide a consistent but slide-specific model fit. We compared GammaGateR against the newest unsupervised approach for annotating mIF data, employing two colon datasets and one ovarian cancer dataset for the evaluation. We showed that GammaGateR produces highly similar results to a silver standard established through manual annotation. Furthermore, we demonstrated its effectiveness in identifying biological signals, achieved by mapping known spatial interactions between CD68 and MUC5AC cells in the colon and by accurately predicting survival in ovarian cancer patients using the phenotype probabilities as input for machine learning methods. GammaGateR is a highly efficient tool that can improve the replicability of marker gating results, while reducing the time of manual segmentation.

AVAILABILITY AND IMPLEMENTATION

The R package is available at https://github.com/JiangmeiRubyXiong/GammaGateR.

iGATE analysis improves the interpretability of single-cell immune landscape of influenza infection

Influenza poses a persistent health burden worldwide. To design equitable vaccines effective across all demographics, it is essential to better understand how host factors such as genetic background and aging affect the single-cell immune landscape of influenza infection. Cytometry by time-of-flight (CyTOF) represents a promising technique in this pursuit, but interpreting its large, high-dimensional data remains difficult. We have developed a new analytical approach, in silico gating annotating training elucidating (iGATE), based on probabilistic support vector machine classification. By rapidly and accurately "gating" tens of millions of cells in silico into user-defined types, iGATE enabled us to track 25 canonical immune cell types in mouse lung over the course of influenza infection. Applying iGATE to study effects of host genetic background, we show that the lower survival of C57BL/6 mice compared with BALB/c was associated with a more rapid accumulation of inflammatory cell types and decreased IL-10 expression. Furthermore, we demonstrate that the most prominent effect of aging is a defective T cell response, reducing survival of aged mice. Finally, iGATE reveals that the 25 canonical immune cell types exhibited differential influenza infection susceptibility and replication permissiveness in vivo, but neither property varied with host genotype or aging. The software is available at https://github.com/UmichWenLab/iGATE.

Immunophenotyping with (phospho)protein profiling and fluorescent cell barcoding for single-cell signaling analysis and biomarker discovery

The microenvironment of hematologic cancers contributes to tumor cell survival and proliferation, as well as treatment resistance. Understanding tumor- and drug-induced changes to the immune cell composition and functionality is therefore critical for implementing optimal treatment strategies and for the development of novel cancer therapies. The liquid nature of peripheral blood makes this organ uniquely suited for single-cell studies by flow cytometry. (Phospho)protein profiles detected by flow cytometry analyses have been shown to correlate with ex vivo drug sensitivity and to predict treatment outcomes in hematologic cancers, demonstrating that this method is suitable for pre-clinical studies. Here, we present a flow cytometry protocol that combines multi-parameter immunophenotyping with single-cell (phospho)protein profiling. The protocol makes use of fluorescent cell barcoding, which means that multiple cell samples, either collected from different donors or exposed to different treatment conditions, can be combined and analyzed as one experiment. This reduces variability between samples, increases the throughput of the experiment, and lowers experimental costs. This protocol may serve as a guide for the use and further development of assays to study immunophenotype and cell signaling at single-cell resolution in normal and malignant cells. The read-outs may provide biological insight into cancer pathogenesis, identify novel drug targets, and ultimately serve as a biomarker to guide clinical decision-making.

A multi-omics systems vaccinology resource to develop and test computational models of immunity

Systems vaccinology studies have identified factors affecting individual vaccine responses, but comparing these findings is challenging due to varying study designs. To address this lack of reproducibility, we established a community resource for comparing Bordetella pertussis booster responses and to host annual contests for predicting patients' vaccination outcomes. We report here on our experiences with the "dry-run" prediction contest. We found that, among 20+ models adopted from the literature, the most successful model predicting vaccination outcome was based on age alone. This confirms our concerns about the reproducibility of conclusions between different vaccinology studies. Further, we found that, for newly trained models, handling of baseline information on the target variables was crucial. Overall, multiple co-inertia analysis gave the best results of the tested modeling approaches. Our goal is to engage community in these prediction challenges by making data and models available and opening a public contest in August 2024.

Ex vivo discovery of synergistic drug combinations for hematologic malignancies

Combination therapies have improved outcomes for patients with acute myeloid leukemia (AML). However, these patients still have poor overall survival. Although many combination therapies are identified with high-throughput screening (HTS), these approaches are constrained to disease models that can be grown in large volumes (e.g., immortalized cell lines), which have limited translational utility. To identify more effective and personalized treatments, we need better strategies for screening and exploring potential combination therapies. Our objective was to develop an HTS platform for identifying effective combination therapies with highly translatable ex vivo disease models that use size-limited, primary samples from patients with leukemia (AML and myelodysplastic syndrome). We developed a system, ComboFlow, that comprises three main components: MiniFlow, ComboPooler, and AutoGater. MiniFlow conducts ex vivo drug screening with a miniaturized flow-cytometry assay that uses minimal amounts of patient sample to maximize throughput. ComboPooler incorporates computational methods to design efficient screens of pooled drug combinations. AutoGater is an automated gating classifier for flow cytometry that uses machine learning to rapidly analyze the large datasets generated by the assay. We used ComboFlow to efficiently screen more than 3000 drug combinations across 20 patient samples using only 6 million cells per patient sample. In this screen, ComboFlow identified the known synergistic combination of bortezomib and panobinostat. ComboFlow also identified a novel drug combination, dactinomycin and fludarabine, that synergistically killed leukemic cells in 35 % of AML samples. This combination also had limited effects in normal, hematopoietic progenitors. In conclusion, ComboFlow enables exploration of massive landscapes of drug combinations that were previously inaccessible in ex vivo models. We envision that ComboFlow can be used to discover more effective and personalized combination therapies for cancers amenable to ex vivo models.

Using Artificial Intelligence to Interpret Clinical Flow Cytometry Datasets for Automated Disease Diagnosis and/or Monitoring

Flow cytometry (FC) is routinely used for hematological disease diagnosis and monitoring. Advancement in this technology allows us to measure an increasing number of markers simultaneously, generating complex high-dimensional datasets. However, current analytic software and methods rely on experienced analysts to perform labor-intensive manual inspection and interpretation on a series of 2-dimensional plots via a complex, sequential gating process. With an aggravating shortage of professionals and growing demands, it is very challenging to provide the FC analysis results in a fast, accurate, and reproducible way. Artificial intelligence has been widely used in many sectors to develop automated detection or classification tools. Here we describe a type of machine learning method for developing automated disease classification and residual disease monitoring on clinical flow datasets.

Trellis tree-based analysis reveals stromal regulation of patient-derived organoid drug responses

Patient-derived organoids (PDOs) can model personalized therapy responses; however, current screening technologies cannot reveal drug response mechanisms or how tumor microenvironment cells alter therapeutic performance. To address this, we developed a highly multiplexed mass cytometry platform to measure post-translational modification (PTM) signaling, DNA damage, cell-cycle activity, and apoptosis in >2,500 colorectal cancer (CRC) PDOs and cancer-associated fibroblasts (CAFs) in response to clinical therapies at single-cell resolution. To compare patient- and microenvironment-specific drug responses in thousands of single-cell datasets, we developed "Trellis"-a highly scalable, tree-based treatment effect analysis method. Trellis single-cell screening revealed that on-target cell-cycle blockage and DNA-damage drug effects are common, even in chemorefractory PDOs. However, drug-induced apoptosis is rarer, patient-specific, and aligns with cancer cell PTM signaling. We find that CAFs can regulate PDO plasticity-shifting proliferative colonic stem cells (proCSCs) to slow-cycling revival colonic stem cells (revCSCs) to protect cancer cells from chemotherapy.

Proficiency tests to evaluate the impact on assay outcomes of harmonized influenza-specific Intracellular Cytokine Staining (ICS) and IFN-ɣ Enzyme-Linked ImmunoSpot (ELISpot) protocols

The magnitude and quality of cell-mediated immune responses elicited by natural infection or vaccination are commonly measured by Interferon-ɣ (IFN-ɣ) Enzyme-Linked ImmunoSpot (ELISpot) and Intracellular Cytokine Staining (ICS). To date, laboratories apply a variety of in-house procedures which leads to diverging results, complicates interlaboratory comparisons and hampers vaccine evaluations. During the FLUCOP project, efforts have been made to develop harmonized Standard Operating Procedures (SOPs) for influenza-specific IFN-ɣ ELISpot and ICS assays. Exploratory pilot studies provided information about the interlaboratory variation before harmonization efforts were initiated. Here we report the results of two proficiency tests organized to evaluate the impact of the harmonization effort on assay results and the performance of participating FLUCOP partners. The introduction of the IFN-ɣ ELISpot SOP reduced variation of both background and stimulated responses. Post-harmonization background responses were all lower than an arbitrary threshold of 50 SFU/million cells. When stimulated with A/California and B/Phuket, a statistically significant reduction in variation (p < 0.0001) was observed and CV values were strongly reduced, from 148% to 77% for A/California and from 126% to 73% for B/Phuket. The harmonizing effect of applying an ICS SOP was also confirmed by an increased homogeneity of data obtained by the individual labs. The application of acceptance criteria on cell viability and background responses further enhanced the data homogeneity. Finally, as the same set of samples was analyzed by both the IFN-ɣ ELISpot and the ICS assays, a method comparison was performed. A clear correlation between the two methods was observed, but they cannot be considered interchangeable. In conclusion, proficiency tests show that a limited harmonization effort consisting of the introduction of SOPs and the use of the same in vitro stimulating antigens leads to a reduction of the interlaboratory variation of IFN-ɣ ELISpot data and demonstrate that substantial improvements for the ICS assay are achieved as comparable laboratory datasets could be generated. Additional steps to further reduce the interlaboratory variation of ICS data can consist of standardized gating templates and detailed data reporting instructions as well as further efforts to harmonize reagent and instrument use.

Identifying dynamical persistent biomarker structures for rare events using modern integrative machine learning approach

The evolution of omics and computational competency has accelerated discoveries of the underlying biological processes in an unprecedented way. High throughput methodologies, such as flow cytometry, can reveal deeper insights into cell processes, thereby allowing opportunities for scientific discoveries related to health and diseases. However, working with cytometry data often imposes complex computational challenges due to high-dimensionality, large size, and nonlinearity of the data structure. In addition, cytometry data frequently exhibit diverse patterns across biomarkers and suffer from substantial class imbalances which can further complicate the problem. The existing methods of cytometry data analysis either predict cell population or perform feature selection. Through this study, we propose a "wisdom of the crowd" approach to simultaneously predict rare cell populations and perform feature selection by integrating a pool of modern machine learning (ML) algorithms. Given that our approach integrates superior performing ML models across different normalization techniques based on entropy and rank, our method can detect diverse patterns existing across the model features. Furthermore, the method identifies a dynamic biomarker structure that divides the features into persistently selected, unselected, and fluctuating assemblies indicating the role of each biomarker in rare cell prediction, which can subsequently aid in studies of disease progression.

Advances in automated and reactive flow cytometry for synthetic biotechnology

Automated flow cytometry (FC) has been initially considered for bioprocess monitoring and optimization. More recently, new physical and software interfaces have been made available, facilitating the access to this technology for labs and industries. It also comes with new capabilities, such as being able to act on the cultivation conditions based on population data. This approach, known as reactive FC, extended the range of applications of automated FC to bioprocess control and the stabilization of cocultures, but also to the broad field of synthetic and systems biology for the characterization of gene circuits. However, several issues must be addressed before automated and reactive FC can be considered standard and modular technologies.

GammaGateR: semi-automated marker gating for single-cell multiplexed imaging

Motivation

Multiplexed immunofluorescence (mIF) is an emerging assay for multichannel protein imaging that can decipher cell-level spatial features in tissues. However, existing automated cell phenotyping methods, such as clustering, face challenges in achieving consistency across experiments and often require subjective evaluation. As a result, mIF analyses often revert to marker gating based on manual thresholding of raw imaging data.

Results

To address the need for an evaluable semi-automated algorithm, we developed GammaGateR, an R package for interactive marker gating designed specifically for segmented cell-level data from mIF images. Based on a novel closed-form gamma mixture model, GammaGateR provides estimates of marker-positive cell proportions and soft clustering of marker-positive cells. The model incorporates user-specified constraints that provide a consistent but slide-specific model fit. We compared GammaGateR against the newest unsupervised approach for annotating mIF data, employing two colon datasets and one ovarian cancer dataset for the evaluation. We showed that GammaGateR produces highly similar results to a silver standard established through manual annotation. Furthermore, we demonstrated its effectiveness in identifying biological signals, achieved by mapping known spatial interactions between CD68 and MUC5AC cells in the colon and by accurately predicting survival in ovarian cancer patients using the phenotype probabilities as input for machine learning methods. GammaGateR is a highly efficient tool that can improve the replicability of marker gating results, while reducing the time of manual segmentation.

Availability and Implementation

The R package is available at https://github.com/JiangmeiRubyXiong/GammaGateR.

A biology-driven deep generative model for cell-type annotation in cytometry

Cytometry enables precise single-cell phenotyping within heterogeneous populations. These cell types are traditionally annotated via manual gating, but this method lacks reproducibility and sensitivity to batch effect. Also, the most recent cytometers-spectral flow or mass cytometers-create rich and high-dimensional data whose analysis via manual gating becomes challenging and time-consuming. To tackle these limitations, we introduce Scyan https://github.com/MICS-Lab/scyan, a Single-cell Cytometry Annotation Network that automatically annotates cell types using only prior expert knowledge about the cytometry panel. For this, it uses a normalizing flow-a type of deep generative model-that maps protein expressions into a biologically relevant latent space. We demonstrate that Scyan significantly outperforms the related state-of-the-art models on multiple public datasets while being faster and interpretable. In addition, Scyan overcomes several complementary tasks, such as batch-effect correction, debarcoding and population discovery. Overall, this model accelerates and eases cell population characterization, quantification and discovery in cytometry.

Artificial Intelligence for Clinical Flow Cytometry

In this review, the authors discuss the fundamental principles of machine learning. They explore recent studies and approaches in implementing machine learning into flow cytometry workflows. These applications are promising but not without their shortcomings. Explainability may be the biggest barrier to adoption, as they contain "black boxes" in which a complex network of mathematical processes learns features of data that are not translatable into real language. The authors discuss the current limitations of machine learning models and the possibility that, without a multiinstitutional development process, these applications could have poor generalizability. They also discuss widespread deployment of augmented decision-making.

A systems vaccinology resource to develop and test computational models of immunity

Computational models that predict an individual's response to a vaccine offer the potential for mechanistic insights and personalized vaccination strategies. These models are increasingly derived from systems vaccinology studies that generate immune profiles from human cohorts pre- and post-vaccination. Most of these studies involve relatively small cohorts and profile the response to a single vaccine. The ability to assess the performance of the resulting models would be improved by comparing their performance on independent datasets, as has been done with great success in other areas of biology such as protein structure predictions. To transfer this approach to system vaccinology studies, we established a prototype platform that focuses on the evaluation of Computational Models of Immunity to Pertussis Booster vaccinations (CMI-PB). A community resource, CMI-PB generates experimental data for the explicit purpose of model evaluation, which is performed through a series of annual data releases and associated contests. We here report on our experience with the first such 'dry run' for a contest where the goal was to predict individual immune responses based on pre-vaccination multi-omic profiles. Over 30 models adopted from the literature were tested, but only one was predictive, and was based on age alone. The performance of new models built using CMI-PB training data was much better, but varied significantly based on the choice of pre-vaccination features used and the model building strategy. This suggests that previously published models developed for other vaccines do not generalize well to Pertussis Booster vaccination. Overall, these results reinforced the need for comparative analysis across models and datasets that CMI-PB aims to achieve. We are seeking wider community engagement for our first public prediction contest, which will open in early 2024.

A topic modeling approach reveals the dynamic T cell composition of peripheral blood during cancer immunotherapy

We present TopicFlow, a computational framework for flow cytometry data analysis of patient blood samples for the identification of functional and dynamic topics in circulating T cell population. This framework applies a Latent Dirichlet Allocation (LDA) model, adapting the concept of topic modeling in text mining to flow cytometry. To demonstrate the utility of our method, we conducted an analysis of ∼17 million T cells collected from 138 peripheral blood samples in 51 patients with melanoma undergoing treatment with immune checkpoint inhibitors (ICIs). Our study highlights three latent dynamic topics identified by LDA: a T cell exhaustion topic that independently recapitulates the previously identified LAG-3+ immunotype associated with ICI resistance, a naive topic and its association with immune-related toxicity, and a T cell activation topic that emerges upon ICI treatment. Our approach can be broadly applied to mine high-parameter flow cytometry data for insights into mechanisms of treatment response and toxicity.

Classifying flow cytometry data using Bayesian analysis helps to distinguish ALS patients from healthy controls

Introduction

Given its wide availability and cost-effectiveness, multidimensional flow cytometry (mFC) became a core method in the field of immunology allowing for the analysis of a broad range of individual cells providing insights into cell subset composition, cellular behavior, and cell-to-cell interactions. Formerly, the analysis of mFC data solely relied on manual gating strategies. With the advent of novel computational approaches, (semi-)automated gating strategies and analysis tools complemented manual approaches.

Methods

Using Bayesian network analysis, we developed a mathematical model for the dependencies of different obtained mFC markers. The algorithm creates a Bayesian network that is a HC tree when including raw, ungated mFC data of a randomly selected healthy control cohort (HC). The HC tree is used to classify whether the observed marker distribution (either patients with amyotrophic lateral sclerosis (ALS) or HC) is predicted. The relative number of cells where the probability q is equal to zero is calculated reflecting the similarity in the marker distribution between a randomly chosen mFC file (ALS or HC) and the HC tree.

Results

Including peripheral blood mFC data from 68 ALS and 35 HC, the algorithm could correctly identify 64/68 ALS cases. Tuning of parameters revealed that the combination of 7 markers, 200 bins, and 20 patients achieved the highest AUC on a significance level of p < 0.0001. The markers CD4 and CD38 showed the highest zero probability. We successfully validated our approach by including a second, independent ALS and HC cohort (55 ALS and 30 HC). In this case, all ALS were correctly identified and side scatter and CD20 yielded the highest zero probability. Finally, both datasets were analyzed by the commercially available algorithm 'Citrus', which indicated superior ability of Bayesian network analysis when including raw, ungated mFC data.

Discussion

Bayesian network analysis might present a novel approach for classifying mFC data, which does not rely on reduction techniques, thus, allowing to retain information on the entire dataset. Future studies will have to assess the performance when discriminating clinically relevant differential diagnoses to evaluate the complementary diagnostic benefit of Bayesian network analysis to the clinical routine workup.

Computational flow cytometry provides accurate assessment of measurable residual disease in chronic lymphocytic leukaemia

Undetectable measurable residual disease (MRD) is associated with favourable clinical outcomes in chronic lymphocytic leukaemia (CLL). While assessment is commonly performed using multiparameter flow cytometry (MFC), this approach is associated with limitations including user bias and expertise that may not be widely available. Implementation of unsupervised clustering algorithms in the laboratory can address these limitations and have not been previously reported in a systematic quantitative manner. We developed a computational pipeline to assess CLL MRD using FlowSOM. In the training step, a self-organising map was generated with nodes representing the full breadth of normal immature and mature B cells along with disease immunophenotypes. This map was used to detect MRD in multiple validation cohorts containing a total of 456 samples. This included an evaluation of atypical CLL cases and samples collected from two different laboratories. Computational MRD showed high correlation with expert analysis (Pearson's r > 0.99 for typical CLL). Binary classification of typical CLL samples as either MRD positive or negative demonstrated high concordance (>98%). Interestingly, computational MRD detected disease in a small number of atypical CLL cases in which MRD was not detected by expert analysis. These results demonstrate the feasibility and value of automated MFC analysis in a diagnostic laboratory.

Development of a fast and precise potency test for BCG vaccine viability using flow cytometry compared to MTT and colony-forming unit assays

In a precarious world of rapidly growing pandemics, the field of vaccine production has witnessed considerable growth. Bacillus Calmette-Guérin (BCG) is a live-attenuated vaccine and a part of the immunization program in 157 countries. The quality control is based on a potency test through viable cell enumeration. The colony-forming unit (CFU) assay is the official method, however, it often yields fluctuating results, suffers from medium cracking, and requires lengthy analysis (~ 28 days). Flow cytometric analysis was proposed earlier, but it was coupled with a Coulter counter for measuring the entire bacterial population (live/dead). In the present study, thiazole orange/propidium iodide dyes supplemented with fluorogenic reference beads were employed for viable counting, eliminating the need for a Coulter counter. Both the flow cytometry and the colorimetric technique employing tetrazolium salt were validated and compared to the CFU assay. The colorimetric assay displayed high precision, accuracy, and a strong positive correlation with the CFU assay. The flow cytometry assay demonstrated high precision and a notable ability to distinguish different forms of BCG cells (live, injured, and dead). It also exhibited a perfect positive correlation with the CFU assay. Both methods reduced the analysis time by > 26 days and eliminated the need for human intervention by automating the test.

Flow Cytometry: The Next Revolution

Unmasking the subtleties of the immune system requires both a comprehensive knowledge base and the ability to interrogate that system with intimate sensitivity. That task, to a considerable extent, has been handled by an iterative expansion in flow cytometry methods, both in technological capability and also in accompanying advances in informatics. As the field of fluorescence-based cytomics matured, it reached a technological barrier at around 30 parameter analyses, which stalled the field until spectral flow cytometry created a fundamental transformation that will likely lead to the potential of 100 simultaneous parameter analyses within a few years. The simultaneous advance in informatics has now become a watershed moment for the field as it competes with mature systematic approaches such as genomics and proteomics, allowing cytomics to take a seat at the multi-omics table. In addition, recent technological advances try to combine the speed of flow systems with other detection methods, in addition to fluorescence alone, which will make flow-based instruments even more indispensable in any biological laboratory. This paper outlines current approaches in cell analysis and detection methods, discusses traditional and microfluidic sorting approaches as well as next-generation instruments, and provides an early look at future opportunities that are likely to arise.

Single-cell analysis reveals inflammatory interactions driving macular degeneration

Due to commonalities in pathophysiology, age-related macular degeneration (AMD) represents a uniquely accessible model to investigate therapies for neurodegenerative diseases, leading us to examine whether pathways of disease progression are shared across neurodegenerative conditions. Here we use single-nucleus RNA sequencing to profile lesions from 11 postmortem human retinas with age-related macular degeneration and 6 control retinas with no history of retinal disease. We create a machine-learning pipeline based on recent advances in data geometry and topology and identify activated glial populations enriched in the early phase of disease. Examining single-cell data from Alzheimer's disease and progressive multiple sclerosis with our pipeline, we find a similar glial activation profile enriched in the early phase of these neurodegenerative diseases. In late-stage age-related macular degeneration, we identify a microglia-to-astrocyte signaling axis mediated by interleukin-1β which drives angiogenesis characteristic of disease pathogenesis. We validated this mechanism using in vitro and in vivo assays in mouse, identifying a possible new therapeutic target for AMD and possibly other neurodegenerative conditions. Thus, due to shared glial states, the retina provides a potential system for investigating therapeutic approaches in neurodegenerative diseases.

ANPELA: Significantly Enhanced Quantification Tool for Cytometry-Based Single-Cell Proteomics

ANPELA is widely used for quantifying traditional bulk proteomic data. Recently, there is a clear shift from bulk proteomics to the single-cell ones (SCP), for which powerful cytometry techniques demonstrate the fantastic capacity of capturing cellular heterogeneity that is completely overlooked by traditional bulk profiling. However, the in-depth and high-quality quantification of SCP data is still challenging and severely affected by the large numbers of quantification workflows and extreme performance dependence on the studied datasets. In other words, the proper selection of well-performing workflow(s) for any studied dataset is elusory, and it is urgently needed to have a significantly enhanced and accelerated tool to address this issue. However, no such tool is developed yet. Herein, ANPELA is therefore updated to its 2.0 version (https://idrblab.org/anpela/), which is unique in providing the most comprehensive set of quantification alternatives (>1000 workflows) among all existing tools, enabling systematic performance evaluation from multiple perspectives based on machine learning, and identifying the optimal workflow(s) using overall performance ranking together with the parallel computation. Extensive validation on different benchmark datasets and representative application scenarios suggest the great application potential of ANPELA in current SCP research for gaining more accurate and reliable biological insights.

Uncovering the hidden structure of dynamic T cell composition in peripheral blood during cancer immunotherapy: a topic modeling approach

Immune checkpoint inhibitors (ICIs), now mainstays in the treatment of cancer treatment, show great potential but only benefit a subset of patients. A more complete understanding of the immunological mechanisms and pharmacodynamics of ICI in cancer patients will help identify the patients most likely to benefit and will generate knowledge for the development of next-generation ICI regimens. We set out to interrogate the early temporal evolution of T cell populations from longitudinal single-cell flow cytometry data. We developed an innovative statistical and computational approach using a Latent Dirichlet Allocation (LDA) model that extends the concept of topic modeling used in text mining. This powerful unsupervised learning tool allows us to discover compositional topics within immune cell populations that have distinct functional and differentiation states and are biologically and clinically relevant. To illustrate the model's utility, we analyzed ∼17 million T cells obtained from 138 pre- and on-treatment peripheral blood samples from a cohort of melanoma patients treated with ICIs. We identified three latent dynamic topics: a T-cell exhaustion topic that recapitulates a LAG3+ predominant patient subgroup with poor clinical outcome; a naive topic that shows association with immune-related toxicity; and an immune activation topic that emerges upon ICI treatment. We identified that a patient subgroup with a high baseline of the naïve topic has a higher toxicity grade. While the current application is demonstrated using flow cytometry data, our approach has broader utility and creates a new direction for translating single-cell data into biological and clinical insights.

Global sphingosine-1-phosphate receptor 2 deficiency attenuates neuroinflammation and ischemic-reperfusion injury after neonatal stroke

Arterial ischemic stroke is common in neonates-1 per 2,300-5,000 births-and therapeutic targets remain insufficiently defined. Sphingosine-1-phosphate receptor 2 (S1PR2), a major regulator of the CNS and immune systems, is injurious in adult stroke. Here, we assessed whether S1PR2 contributes to stroke induced by 3 h transient middle cerebral artery occlusion (tMCAO) in S1PR2 heterozygous (HET), knockout (KO), and wild type (WT) postnatal day 9 pups. HET and WT of both sexes displayed functional deficits in Open Field test whereas injured KO at 24 h reperfusion performed similarly to naives. S1PR2 deficiency protected neurons, attenuated infiltration of inflammatory monocytes, and altered vessel-microglia interactions without reducing increased cytokine levels in injured regions at 72 h. Pharmacologic inhibition of S1PR2 after tMCAO by JTE-013 attenuated injury 72 h after tMCAO. Importantly, the lack of S1PR2 alleviated anxiety and brain atrophy during chronic injury. Altogether, we identify S1PR2 as a potential new target for mitigating neonatal stroke.

Artificial intelligence in clinical multiparameter flow cytometry and mass cytometry-key tools and progress

There are many research studies and emerging tools using artificial intelligence (AI) and machine learning to augment flow and mass cytometry workflows. Emerging AI tools can quickly identify common cell populations with continuous improvement of accuracy, uncover patterns in high-dimensional cytometric data that are undetectable by human analysis, facilitate the discovery of cell subpopulations, perform semi-automated immune cell profiling, and demonstrate potential to automate aspects of clinical multiparameter flow cytometric (MFC) diagnostic workflow. Utilizing AI in the analysis of cytometry samples can reduce subjective variability and assist in breakthroughs in understanding diseases. Here we review the diverse types of AI that are being applied to clinical cytometry data and how AI is driving advances in data analysis to improve diagnostic sensitivity and accuracy. We review supervised and unsupervised clustering algorithms for cell population identification, various dimensionality reduction techniques, and their utilities in visualization and machine learning pipelines, and supervised learning approaches for classifying entire cytometry samples.Understanding the AI landscape will enable pathologists to better utilize open source and commercially available tools, plan exploratory research projects to characterize diseases, and work with machine learning and data scientists to implement clinical data analysis pipelines.

Latent dirichlet allocation for double clustering (LDA-DC): discovering patients phenotypes and cell populations within a single Bayesian framework

BACKGROUND

Current clinical routines rely more and more on "omics" data such as flow cytometry data from host and microbiota. Cohorts variability in addition to patients' heterogeneity and huge dimensions make it difficult to understand underlying structure of the data and decipher pathologies. Patients stratification and diagnostics from such complex data are extremely challenging. There is an acute need to develop novel statistical machine learning methods that are robust with respect to the data heterogeneity, efficient from the computational viewpoint, and can be understood by human experts.

RESULTS

We propose a novel approach to stratify cell-based observations within a single probabilistic framework, i.e., to extract meaningful phenotypes from both patients and cells data simultaneously. We define this problem as a double clustering problem that we tackle with the proposed approach. Our method is a practical extension of the Latent Dirichlet Allocation and is used for the Double Clustering task (LDA-DC). We first validate the method on artificial datasets, then we apply our method to two real problems of patients stratification based on cytometry and microbiota data. We observe that the LDA-DC returns clusters of patients and also clusters of cells related to patients' conditions. We also construct a graphical representation of the results that can be easily understood by humans and are, therefore, of a big help for experts involved in pre-clinical research.

Tracking defined microbial communities by multicolor flow cytometry reveals tradeoffs between productivity and diversity

Cross feeding between microbes is ubiquitous, but its impact on the diversity and productivity of microbial communities is incompletely understood. A reductionist approach using simple microbial communities has the potential to detect cross feeding interactions and their impact on ecosystem properties. However, quantifying abundance of more than two microbes in a community in a high throughput fashion requires rapid, inexpensive assays. Here, we show that multicolor flow cytometry combined with a machine learning-based classifier can rapidly quantify species abundances in simple, synthetic microbial communities. Our approach measures community structure over time and detects the exchange of metabolites in a four-member community of fluorescent Bacteroides species. Notably, we quantified species abundances in co-cultures and detected evidence of cooperation in polysaccharide processing and competition for monosaccharide utilization. We also observed that co-culturing on simple sugars, but not complex sugars, reduced microbial productivity, although less productive communities maintained higher community diversity. In summary, our multicolor flow cytometric approach presents an economical, tractable model system for microbial ecology using well-studied human bacteria. It can be extended to include additional species, evaluate more complex environments, and assay response of communities to a variety of disturbances.

GeoWaVe: geometric median clustering with weighted voting for ensemble clustering of cytometry data

MOTIVATION

Clustering is an unsupervised method for identifying structure in unlabelled data. In the context of cytometry, it is typically used to categorize cells into subpopulations of similar phenotypes. However, clustering is greatly dependent on hyperparameters and the data to which it is applied as each algorithm makes different assumptions and generates a different 'view' of the dataset. As such, the choice of clustering algorithm can significantly influence results, and there is often not one preferred method but different insights to be obtained from different methods. To overcome these limitations, consensus approaches are needed that directly address the effect of competing algorithms. To the best of our knowledge, consensus clustering algorithms designed specifically for the analysis of cytometry data are lacking.

RESULTS

We present a novel ensemble clustering methodology based on geometric median clustering with weighted voting (GeoWaVe). Compared to graph ensemble clustering methods that have gained popularity in single-cell RNA sequencing analysis, GeoWaVe performed favourably on different sets of high-dimensional mass and flow cytometry data. Our findings provide proof of concept for the power of consensus methods to make the analysis, visualization and interpretation of cytometry data more robust and reproducible. The wide availability of ensemble clustering methods is likely to have a profound impact on our understanding of cellular responses, clinical conditions and therapeutic and diagnostic options.

AVAILABILITY AND IMPLEMENTATION

GeoWaVe is available as part of the CytoCluster package https://github.com/burtonrj/CytoCluster and published on the Python Package Index https://pypi.org/project/cytocluster. Benchmarking data described are available from https://doi.org/10.5281/zenodo.7134723.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Cell Viability Multiplexing: Quantification of Cellular Viability by Barcode Flow Cytometry and Computational Analysis

Fluorescent cell barcoding (FCB) is a useful flow cytometric technique for high-throughput multiplexed analyses and can minimize technical variations after preliminary optimization and validation of protocols. To date, FCB is widely used for measurement of phosphorylation status of certain proteins, while it can be also employed for cellular viability assessment. In this chapter, we describe the protocol to perform FCB combined with viability assessment on lymphocytes and monocytes using manual and computational analysis. We also provide recommendations for FCB protocol optimization and validation for clinical sample analysis.

Microbial Response to Increased Temperatures Within a Lava-Induced Hydrothermal System in Iceland: An Analogue for the Habitability of Volcanic Terrains on Mars

Fossil hydrothermal systems on Mars are important exploration targets because they may have once been habitable and could still preserve evidence of microbial life. We investigated microbial communities within an active lava-induced hydrothermal system associated with the 2014-2015 eruption of Holuhraun in Iceland as a Mars analogue. In 2016, the microbial composition in the lava-heated water differed substantially from that of the glacial river and spring water sources that fed into the system. Several taxonomic and metabolic groups were confined to the water emerging from the lava and some showed the highest sequence similarities to subsurface ecosystems, including to the predicted thermophilic and deeply branching Candidatus Acetothermum autotrophicum. Measurements show that the communities were affected by temperature and other environmental factors. In particular, comparing glacial river water incubated in situ (5.7°C, control) with glacial water incubated within a lava-heated stream (17.5°C, warm) showed that microbial abundance, richness, and diversity increased in the warm treatment compared with the control, with the predicted major metabolism shifting from lithotrophy toward organotrophy and possibly phototrophy. In addition, thermophilic bacteria isolated from the lava-heated water and a nearby acidic hydrothermal system included the known endospore-formers Geobacillus stearothermophilus and Paenibacillus cisolokensis as well as a potentially novel taxon within the order Hyphomicrobiales. Similar lava-water interactions on Mars could therefore have generated habitable environments for microbial communities.

On clustering for cell-phenotyping in multiplex immunohistochemistry (mIHC) and multiplexed ion beam imaging (MIBI) data

OBJECTIVE

Multiplex immunohistochemistry (mIHC) and multiplexed ion beam imaging (MIBI) images are usually phenotyped using a manual thresholding process. The thresholding is prone to biases, especially when examining multiple images with high cellularity.

RESULTS

Unsupervised cell-phenotyping methods including PhenoGraph, flowMeans, and SamSPECTRAL, primarily used in flow cytometry data, often perform poorly or need elaborate tuning to perform well in the context of mIHC and MIBI data. We show that, instead, semi-supervised cell clustering using Random Forests, linear and quadratic discriminant analysis are superior. We test the performance of the methods on two mIHC datasets from the University of Colorado School of Medicine and a publicly available MIBI dataset. Each dataset contains a bunch of highly complex images.

PRIMAL-GMM: PaRametrIc MAnifold Learning of Gaussian Mixture Models

We propose a ParametRIc MAnifold Learning (PRIMAL) algorithm for Gaussian mixtures models (GMM), assuming that GMMs lie on or near to a manifold of probability distributions that is generated from a low-dimensional hierarchical latent space through parametric mappings. Inspired by principal component analysis (PCA), the generative processes for priors, means and covariance matrices are modeled by their respective latent space and parametric mapping. Then, the dependencies between latent spaces are captured by a hierarchical latent space by a linear or kernelized mapping. The function parameters and hierarchical latent space are learned by minimizing the reconstruction error between ground-truth GMMs and manifold-generated GMMs, measured by Kullback-Leibler Divergence (KLD). Variational approximation is employed to handle the intractable KLD between GMMs and a variational EM algorithm is derived to optimize the objective function. Experiments on synthetic data, flow cytometry analysis, eye-fixation analysis and topic models show that PRIMAL learns a continuous and interpretable manifold of GMM distributions and achieves a minimum reconstruction error.