DAFi: A directed recursive data filtering and clustering approach for improving and interpreting data clustering identification of cell populations from polychromatic flow cytometry data

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.

A cell-level discriminative neural network model for diagnosis of blood cancers

MOTIVATION

Precise identification of cancer cells in patient samples is essential for accurate diagnosis and clinical monitoring but has been a significant challenge in machine learning approaches for cancer precision medicine. In most scenarios, training data are only available with disease annotation at the subject or sample level. Traditional approaches separate the classification process into multiple steps that are optimized independently. Recent methods either focus on predicting sample-level diagnosis without identifying individual pathologic cells or are less effective for identifying heterogeneous cancer cell phenotypes.

RESULTS

We developed a generalized end-to-end differentiable model, the Cell Scoring Neural Network (CSNN), which takes sample-level training data and predicts the diagnosis of the testing samples and the identity of the diagnostic cells in the sample, simultaneously. The cell-level density differences between samples are linked to the sample diagnosis, which allows the probabilities of individual cells being diagnostic to be calculated using backpropagation. We applied CSNN to two independent clinical flow cytometry datasets for leukemia diagnosis. In both qualitative and quantitative assessments, CSNN outperformed preexisting neural network modeling approaches for both cancer diagnosis and cell-level classification. Post hoc decision trees and 2D dot plots were generated for interpretation of the identified cancer cells, showing that the identified cell phenotypes match the cancer endotypes observed clinically in patient cohorts. Independent data clustering analysis confirmed the identified cancer cell populations.

AVAILABILITY AND IMPLEMENTATION

The source code of CSNN and datasets used in the experiments are publicly available on GitHub (http://github.com/erobl/csnn). Raw FCS files can be downloaded from FlowRepository (ID: FR-FCM-Z6YK).

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 cell-level discriminative neural network model for diagnosis of blood cancers

Motivation

Precise identification of cancer cells in patient samples is essential for accurate diagnosis and clinical monitoring but has been a significant challenge in machine learning approaches for cancer precision medicine. In most scenarios, training data are only available with disease annotation at the subject or sample level. Traditional approaches separate the classification process into multiple steps that are optimized independently. Recent methods either focus on predicting sample-level diagnosis without identifying individual pathologic cells or are less effective for identifying heterogeneous cancer cell phenotypes.

Results

We developed a generalized end-to-end differentiable model, the Cell Scoring Neural Network (CSNN), which takes the available sample-level training data and predicts both the diagnosis of the testing samples and the identity of the diagnostic cells in the sample, simultaneously. The cell-level density differences between samples are linked to the sample diagnosis, which allows the probabilities of individual cells being diagnostic to be calculated using backpropagation. We applied CSNN to two independent clinical flow cytometry datasets for leukemia diagnosis. In both qualitative and quantitative assessments, CSNN outperformed preexisting neural network modeling approaches for both cancer diagnosis and cell-level classification. Post hoc decision trees and 2D dot plots were generated for interpretation of the identified cancer cells, showing that the identified cell phenotypes match the cancer endotypes observed clinically in patient cohorts. Independent data clustering analysis confirmed the identified cancer cell populations.

Availability

The source code of CSNN and datasets used in the experiments are publicly available on GitHub and FlowRepository.

Contact

Edgar E. Robles: roblesee@uci.edu and Yu Qian: mqian@jcvi.org.

Supplementary information

Supplementary data are available on GitHub and at Bioinformatics online.

Explaining the polarized macrophage pool during murine allergic lung inflammation

Introduction

Differentially polarized macrophages, especially YM1+ and MHCII+ macrophages, play an important role in asthma development. The origin of these polarized macrophages has not been elucidated yet. We therefore aimed to investigate how proliferation, monocyte recruitment, and/or switching of polarization states contribute to this specific pool of polarized interstitial and alveolar macrophages during development of house dust mite (HDM)-induced allergic lung inflammation in mice.

Methods

Male and female mice were first treated intranasally with PKH26 to label lung-resident macrophages and were then exposed to either HDM or phosphate-buffered saline (PBS) for two weeks. Different myeloid immune cell types were quantified in lung tissue and blood using flow cytometry.

Results

We found that macrophage polarization only starts up in the second week of HDM exposures. Before this happened, unpolarized alveolar and interstitial macrophages transiently increased in HDM-exposed mice. This transient increase was mostly local proliferation of alveolar macrophages, while interstitial macrophages also contained unlabeled macrophages suggesting monocyte contribution. After two weeks of exposures, the number of interstitial and alveolar macrophages was similar between HDM and PBS-exposed mice, but the distribution of polarization states was remarkably different. HDM-exposed mice selectively developed YM1+ alveolar macrophages and MHCII-hi interstitial macrophages while nonpolarized macrophages were lost compared to PBS-exposed mice.

Discussion

In this HDM model we have shown that development of a polarized macrophage pool during allergic inflammation is first dependent on proliferation of nonpolarized tissue-resident macrophages with some help of infiltrating unlabeled cells, presumably circulating monocytes. These nonpolarized macrophages then acquire their polarized phenotype by upregulating YM1 on alveolar macrophages and MHCII on interstitial macrophages. This novel information will help us to better understand the role of macrophages in asthma and designing therapeutic strategies targeting macrophage functions.

FastMix: a versatile data integration pipeline for cell type-specific biomarker inference

MOTIVATION

Flow cytometry (FCM) and transcription profiling are the two widely used assays in translational immunology research. However, there is no data integration pipeline for analyzing these two types of assays together with experiment variables for biomarker inference. Current FCM data analysis mainly relies on subjective manual gating analysis, which is difficult to be directly integrated with other automated computational methods. Existing deconvolutional analysis of bulk transcriptomics relies on predefined marker genes in the transcriptomics data, which are unavailable for novel cell types and does not utilize the FCM data that provide canonical phenotypic definitions of the cell types.

RESULTS

We developed a novel analytics pipeline-FastMix-for computational immunology, which integrates flow cytometry, bulk transcriptomics and clinical covariates for identifying cell type-specific gene expression signatures and biomarker genes. FastMix addresses the 'large p, small n' problem in the gene expression and flow cytometry integration analysis via a linear mixed effects model (LMER) for both cross-sectional and longitudinal studies. Its novel moment-based estimator not only reduces bias in parameter estimation but also is more efficient than iterative optimization. The FastMix pipeline also includes a cutting-edge flow cytometry data analysis method-DAFi-for identifying cell populations of interest and their characteristics. Simulation studies showed that FastMix produced smaller type I/II errors than competing methods. Validation using real data of two vaccine studies showed that FastMix identified a consistent set of signature genes as in independent single-cell RNA-seq analysis, producing additional interesting findings.

AVAILABILITY AND IMPLEMENTATION

Source code of FastMix is publicly available at https://github.com/terrysun0302/FastMix.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

A system-view of Bordetella pertussis booster vaccine responses in adults primed with whole-cell versus acellular vaccine in infancy

The increased incidence of whooping cough worldwide suggests that current vaccination against Bordetella pertussis infection has limitations in quality and duration of protection. The resurgence of infection has been linked to the introduction of acellular vaccines (aP), which have an improved safety profile compared with the previously used whole-cell (wP) vaccines. To determine immunological differences between aP and wP priming in infancy, we performed a systems approach of the immune response to booster vaccination. Transcriptomic, proteomic, cytometric, and serologic profiling revealed multiple shared immune responses with different kinetics across cohorts, including an increase of blood monocyte frequencies and strong antigen-specific IgG responses. Additionally, we found a prominent subset of aP-primed individuals (30%) with a strong differential signature, including higher levels of expression for CCL3, NFKBIA, and ICAM1. Contrary to the wP individuals, this subset displayed increased PT-specific IgE responses after boost and higher antigen-specific IgG4 and IgG3 antibodies against FHA and FIM2/3 at baseline and after boost. Overall, the results show that, while broad immune response patterns to Tdap boost overlap between aP- and wP-primed individuals, a subset of aP-primed individuals present a divergent response. These findings provide candidate targets to study the causes and correlates of waning immunity after aP vaccination.

Current trends in flow cytometry automated data analysis software

Automated flow cytometry (FC) data analysis tools for cell population identification and characterization are increasingly being used in academic, biotechnology, pharmaceutical, and clinical laboratories. The development of these computational methods is designed to overcome reproducibility and process bottleneck issues in manual gating, however, the take-up of these tools remains (anecdotally) low. Here, we performed a comprehensive literature survey of state-of-the-art computational tools typically published by research, clinical, and biomanufacturing laboratories for automated FC data analysis and identified popular tools based on literature citation counts. Dimensionality reduction methods ranked highly, such as generic t-distributed stochastic neighbor embedding (t-SNE) and its initial Matlab-based implementation for cytometry data viSNE. Software with graphical user interfaces also ranked highly, including PhenoGraph, SPADE1, FlowSOM, and Citrus, with unsupervised learning methods outnumbering supervised learning methods, and algorithm type popularity spread across K-Means, hierarchical, density-based, model-based, and other classes of clustering algorithms. Additionally, to illustrate the actual use typically within clinical spaces alongside frequent citations, a survey issued by UK NEQAS Leucocyte Immunophenotyping to identify software usage trends among clinical laboratories was completed. The survey revealed 53% of laboratories have not yet taken up automated cell population identification methods, though among those that have, Infinicyt software is the most frequently identified. Survey respondents considered data output quality to be the most important factor when using automated FC data analysis software, followed by software speed and level of technical support. This review found differences in software usage between biomedical institutions, with tools for discovery, data exploration, and visualization more popular in academia, whereas automated tools for specialized targeted analysis that apply supervised learning methods were more used in clinical settings.

Artificial intelligence and the hunt for immunological disorders

PURPOSE OF REVIEW

Artificial intelligence has pervasively transformed many industries and is beginning to shape medical practice. New use cases are being identified in subspecialty domains of medicine and, in particular, application of artificial intelligence has found its way to the practice of allergy-immunology. Here, we summarize recent developments, emerging applications and obstacles to realizing full potential.

RECENT FINDINGS

Artificial/augmented intelligence and machine learning are being used to reduce dimensional complexity, understand cellular interactions and advance vaccine work in the basic sciences. In genomics, bioinformatic methods are critical for variant calling and classification. For clinical work, artificial intelligence is enabling disease detection, risk profiling and decision support. These approaches are just beginning to have impact upon the field of clinical immunology and much opportunity exists for further advancement.

SUMMARY

This review highlights use of computational methods for analysis of large datasets across the spectrum of research and clinical care for patients with immunological disorders. Here, we discuss how big data methods are presently being used across the field clinical immunology.

Validation of a hybrid approach to standardize immunophenotyping analysis in large population studies: The Health and Retirement Study

Traditional manual gating strategies are often time-intensive, place a high burden on the analyzer, and are susceptible to bias between analyzers. Several automated gating methods have shown to exceed performance of manual gating for a limited number of cell subsets. However, many of the automated algorithms still require significant manual interventions or have yet to demonstrate their utility in large datasets. Therefore, we developed an approach that utilizes a previously published automated algorithm (OpenCyto framework) with a manually created hierarchically cell gating template implemented, along with a custom developed visualization software (FlowAnnotator) to rapidly and efficiently analyze immunophenotyping data in large population studies. This approach allows pre-defining populations that can be analyzed solely by automated analysis and incorporating manual refinement for smaller downstream populations. We validated this method with traditional manual gating strategies for 24 subsets of T cells, B cells, NK cells, monocytes and dendritic cells in 931 participants from the Health and Retirement Study (HRS). Our results show a high degree of correlation (r ≥ 0.80) for 18 (78%) of the 24 cell subsets. For the remaining subsets, the correlation was low (<0.80) primarily because of the low numbers of events recorded in these subsets. The mean difference in the absolute counts between the hybrid method and manual gating strategy of these cell subsets showed results that were very similar to the traditional manual gating method. We describe a practical method for standardization of immunophenotyping methods in large scale population studies that provides a rapid, accurate and reproducible alternative to labor intensive manual gating strategies.

Unbiased analysis of peripheral blood mononuclear cells reveals CD4 T cell response to RSV matrix protein

Respiratory syncytial virus (RSV) is the most important cause of respiratory tract illness especially in young infants that develop severe disease requiring hospitalization, and accounting for 74,000–126,000 admissions in the United States (Rezaee et al., 2017; Resch, 2017). Observations of neonatal and infant T cells suggest that they may express different immune markers compared to T-cells from older children. Flow cytometry analysis of cellular responses using “conventional” anti-viral markers (IL2, IFN-γ, TNF, IL10 and IL4) upon RSV-peptide stimulation detected an overall low RSV response in peripheral blood. Therefore we sought an unbiased approach to identify RSV-specific immune markers using RNA-sequencing upon stimulation of infant PBMCs with overlapping peptides representing RSV antigens. To understand the cellular response using transcriptional signatures, transcription factors and cell-type specific signatures were used to investigate breadth of response across peptides. Unexpected from the ICS data, M peptide induced a response equivalent to the F-peptide and was characterized by activation of GATA2, 3, STAT3 and IRF1. This along with upregulation of several unconventional T cell signatures was only observed upon M-peptide stimulation. Moreover, signatures of natural RSV infections were identified from the data available in the public domain to investigate similarities between transcriptional signatures from PBMCs and upon peptide stimulation. This analysis also suggested activation of T cell response upon M-peptide stimulation. Hence, based on transcriptional response, markers were chosen to validate the role of M-peptide in activation of T cells. Indeed, CD4+CXCL9+ cells were identified upon M-peptide stimulation by flow cytometry. Future work using additional markers identified in this study could reveal additional unconventional T cells responding to RSV infections in infants. In conclusion, T cell responses to RSV in infants may not follow the canonical Th1/Th2 patterns of effector responses but include additional functions that may be unique to the neonatal period and correlate with clinical outcomes.

Machine Learning of Discriminative Gate Locations for Clinical Diagnosis

High-throughput single-cell cytometry technologies have significantly improved our understanding of cellular phenotypes to support translational research and the clinical diagnosis of hematological and immunological diseases. However, subjective and ad hoc manual gating analysis does not adequately handle the increasing volume and heterogeneity of cytometry data for optimal diagnosis. Prior work has shown that machine learning can be applied to classify cytometry samples effectively. However, many of the machine learning classification results are either difficult to interpret without using characteristics of cell populations to make the classification, or suboptimal due to the use of inaccurate cell population characteristics derived from gating boundaries. To date, little has been done to optimize both the gating boundaries and the diagnostic accuracy simultaneously. In this work, we describe a fully discriminative machine learning approach that can simultaneously learn feature representations (e.g., combinations of coordinates of gating boundaries) and classifier parameters for optimizing clinical diagnosis from cytometry measurements. The approach starts from an initial gating position and then refines the position of the gating boundaries by gradient descent until a set of globally-optimized gates across different samples are achieved. The learning procedure is constrained by regularization terms encoding domain knowledge that encourage the algorithm to seek interpretable results. We evaluate the proposed approach using both simulated and real data, producing classification results on par with those generated via human expertise, in terms of both the positions of the gating boundaries and the diagnostic accuracy. © 2019 The Authors. Cytometry Part A published by Wiley Periodicals, Inc. on behalf of International Society for Advancement of Cytometry.

High-Throughput Analysis of Clinical Flow Cytometry Data by Automated Gating

Advancements in flow cytometers with capability to measure 15 or more parameters have enabled us to characterize cell populations at unprecedented levels of detail. Beyond discovery research, there is now a growing demand to dive deeper into evaluating the immune response in clinical trials for immune modulating compounds. However, for high-volume, complex flow cytometry data generated in clinical trials, conventional manual gating remains the standard of practice. Traditional manual gating is resource intense and becomes a bottleneck and an impractical method to complete high volumes of flow cytometry data analysis. Current efforts to automate “manual gating” have shown that computational algorithms can facilitate the analysis of daunting multi-parameter data; however, a greater degree of precision in comparison with traditional manual gating is needed for wide-scale adoption of automated gating methods. In an effort to more closely follow the manual gating process, our automated gating pipeline was created to include negative controls (Fluorescence Minus One [FMO]) to enhance the reliability of gate placement. We demonstrate that use of an automated pipeline, heavily relying on FMO controls for population discrimination, can analyze multi-parameter, large-scale clinical datasets with comparable precision and accuracy to traditional manual gating.