Cytometry Part A

Inflammatory activation remodels the Golgi apparatus to meet increased secretory demand, yet whether these structural changes carry computationally accessible information about immune cell state has not been explored. Here we show that machine learning applied to imaging flow cytometry images of the Golgi can distinguish lipopolysaccharide (LPS) treated from control cells. We trained models on Golgi images from human THP-1 monocytes before and 16 h after LPS stimulation in vitro, and from circulating myeloid cells of mice 24 h after intratracheal LPS or saline in vivo. In each dataset, the best-performing model was a deep learning model trained directly on images rather than a classifier using predefined morphometric features. Cross-domain performance varied with the model, transfer direction and use of labelled target data: several deep learning models trained on mouse images classified THP-1 cells above chance without changing model parameters. Grad-CAM highlighted regions within or adjacent to the GM130 fluorescence pattern. These findings indicate that GM130 images carry information associated with LPS treatment that supports classification within and across the two datasets. To our knowledge, this is the first application of supervised deep learning to imaging flow cytometry images of a subcellular organelle for inflammatory phenotyping, establishing organelle level image analysis as a potential complement to molecular assays for immune cell classification.

Platelet-leukocyte aggregates (PLAs) are a proposed interface between coagulation and immune regulation, but their distribution across leukocyte subsets beyond monocytes and neutrophils, and their behavior in acute disorders of immune regulation, such as sepsis and severe trauma, remain largely undefined. The study of thromboimmune mechanisms in these acute conditions has relied heavily on murine sepsis models, whose species differences in platelet and leukocyte biology limit translation to human disease. Direct measurement in human whole blood is needed yet reported PLA frequencies vary widely because quantification is highly sensitive to sample handling. Here we present a robust, minimally manipulative 27-color spectral flow cytometry protocol that allows simultaneous deep immunophenotyping and classification of PLAs across >40 leukocyte subpopulations. In healthy donors, PLA frequency ranged from 1.7% on memory CD4 T cells to over 50% on monocyte subsets, with monocytes contributing 25% of all PLAs. We also found novel platelet-binding leukocyte populations, including Th9 and Th22 CD4+ T cells. Optimization identified anticoagulant choice, centrifugation conditions, dilution, and sample processing time as key determinants of reproducible measurement; PLA quantification was validated by imaging flow cytometry. In a small validation cohort of sepsis and trauma patients, the assay recapitulated established immunophenotypic features of critical illness, including neutrophilia and myeloid-derived suppressor cells (MDSC) expansion, and quantified PLAs within each subset. This protocol provides a reference framework for studying thromboinflammation and other dysregulated immune response diseases directly in human blood, and a foundation for further studies, defining the mechanisms and clinical relevance of platelet-leukocyte interactions in disease.

Chimeric antigen receptor (CAR) T cells are patient-derived T cells engineered to recognize specific antigens on malignant cells, representing a major breakthrough in personalized cancer immunotherapy. While CAR-T cell therapy is an established treatment for relapsed or refractory hematologic malignancies, understanding the rationale and methodology behind its development is essential for training the next generation of oncology researchers. Here, we describe a novel, hands-on small-enrollment laboratory course designed to teach upper-level undergraduate and graduate students about immunotherapies and CAR-T cell technology by paralleling a typical bench-scale development process. Students isolated T cells from porcine peripheral blood mononuclear cells (PBMCs) via immunomagnetic selection, followed by flow cytometry to assess purity, viability, and yield. Students then used pre-engineered B7H3 CAR-T cells to perform co-culture assays with U87 glioblastoma cells to evaluate tumor cell killing efficacy. Cytotoxicity was qualitatively evaluated using immunofluorescence microscopy, while IFN-gamma release was quantified using Enzyme-linked Immunosorbent Assay (ELISA). Student performance was evaluated through electronic laboratory notebooks, discussion questions, a capstone project, and student-generated data. Our results demonstrate students high academic performance across assignments and the successful execution of complex laboratory workflows. Collectively, these findings establish the feasibility and implementation of a research-integrated curriculum providing foundational exposure to immuno-oncology research tools and CAR-T cell production techniques.

Lenalidomide (Revlimid), bortezomib (Velcade), and dexamethasone, are used alone or in combination (RVd therapy) as first-line therapies for hematologic malignancies including the plasma cell dyscrasia, Multiple Myeloma (MM). The effects of RVd treatment on tumor cells have been documented, but little is known about their impacts on "healthy" immune cells. New therapeutics, including chimeric antigen receptor T cell (CAR-T) and bispecific T-cell engagers (BiTEs) depend on robust T cell function but these are often harvested for cellular therapies after or in tandem with RVd therapy. Understanding the molecular effects of these drugs on healthy T cells is therefore of particular importance. Since the molecular effects of each drug includes regulation of key transcription factors, we used a tri-modal, single-cell assay (TEA-seq), simultaneously profiling mRNA transcripts, cell surface proteins, and chromatin accessibility in primary human peripheral blood T cells treated for 4, 24, or 72 hours in vitro. Synergies and conflicts potentially arising from combinatorial therapy were identified and validated by flow cytometry. Doublet and triplet drug combinations were used to assess effects on cell-surface marker expression and on T cell activation. Our results suggest that T cell function can be optimized by the administration of these drugs individually and that sequential administration may offer an opportunity to enhance T cell function by affecting localization and altering T cell states. This work provides those interested in immunology, oncology, and cell therapies an opportunity to explore molecular pathways that could be manipulated by these commonly used drugs to modify T cell function.

Flow cytometry is central to clinical hematology, generating extensive archives comprising billions of single-cell profiles linked to expert-derived diagnostic summaries. While these records represent a largely untapped repository of collective expert knowledge, the underlying single-cell annotations required for supervised machine learning are typically not recorded in a standardized, accessible format. We present IMPGAT (implicit gating), a weakly supervised multiple-instance learning framework that reconstructs single-cell gating strategies directly from existing sample-level cell-type frequency distributions. The model utilizes an induced set attention mechanism to map single-cell marker profiles to specific cell populations, requiring neither explicit cell-level labels nor unsupervised clustering during training. We evaluate the framework on acute lymphoblastic leukemia (ALL) and acute myeloid leukemia (AML) cohorts, totaling 711 measurements from 268 individuals and 240 million single cells. In ALL, the model's quantification of cell-type abundances shows no statistically significant difference from human inter-expert variability. In AML, the framework achieves blast quantification on par with a recently established supervised state-of-the-art model that relies on explicit single-cell annotations for training. Error analysis shows that mismatches between model predictions and expert gating primarily involve expert-labeled non-cellular events, reflecting the non-incorporation of any explicit physical prior knowledge (such as the geometric relationships traditionally used to identify doublets and debris in scatter cytograms) in model training. Conversely, model certainty correlates with phenotypic borderline cases where manual bisection is inherently difficult. Our approach enables the systematic utilization of retrospective clinical records for the development of automated, standardized gating logic and is applicable to broader high-throughput contexts, such as large-scale immune monitoring or phenotypic drug screening.

Natural killer (NK) cells display striking variability in their cytotoxic responses, but whether this variation reflects random events, stable differences between cells, or effects of previous encounters remains unclear. We developed a Bayesian framework that uses single-cell interaction histories to disentangle these sources of variability. The framework models target encounters and killing decisions to quantify population heterogeneity, determine the sample sizes needed to distinguish competing mechanisms, and separate stable cell-to-cell differences from history-dependent behaviour. Synthetic data established when these mechanisms can be reliably distinguished in practice. We tested the framework using time-lapse imaging of NK cells exposed to rituximab or CC-96673, an antibody co-targeting CD20 and CD47. Despite similar overall killing, the framework identified distinct underlying responses: rituximab mainly increased mean killing rate, whereas CC-96673 reduced cell-to-cell variation. Event-count analysis supported continuous population heterogeneity, while ordered interaction histories revealed that both stable differences in killing propensity and previous encounters shape cytotoxic decisions. To make the framework directly usable, we introduce BARRACUDA, an open-source web platform and Python package implementing these analyses, including donor-aware extensions, for single-cell cytotoxicity datasets.

The field of microglial research has evolved throughout the years. Microglia, the immune cells of the central nervous system, are recognized as highly heterogeneous and dynamic cells, known for modifying their structure and function based on the local context. Investigating microglial density, spatial distribution, and morphological states is important for uncovering their distinct functional states in health and pathology. However, quantifying these features accurately is often a methodological challenge. Fully automated computational approaches often fail to capture subtle biological nuances and complex structural variations. Also, the high diversity of image sets makes it difficult to maintain consistent reliability. In contrast, entirely manual quantification is labor-intensive and prone to observer bias. To bridge this gap, we propose a semi-automated framework using the open-source software CellProfiler. Our workflow is divided into two distinct pipelines designed to combine automation of batch analysis with targeted user oversight, allowing for manual intervention when necessary to ensure maximum accuracy. Both pipelines are capable of recognizing microglial soma and tracing their processes. In the density workflow, it automatically calculates cell density and provides spatial distribution measurements, such as closest-neighbor distance and spacing index. For morphological profiling, it yields extensive structural data, including area, perimeter, convex area, form factor, and various shape descriptors. Furthermore, we demonstrate how researchers can optimize the pipeline settings to accommodate varied image datasets and experimental conditions. We hope this open-source framework can standardize microglial density, distribution, and morphological analysis and reduce systematic bias, providing researchers with a robust tool to better characterize their heterogeneity.

Background: The clinical course of acute leukemias and related hematologic neoplasms is defined by aggressive clonal proliferation, severe hematopoietic disruption, and recurrent molecular alterations. Although serial bone marrow biopsies, multiparameter flow cytometry, and next-generation sequencing remain standard surveillance modalities, procedural invasiveness, high costs, and operational turnaround times limit their frequency. Minimally invasive, scalable biomarkers integrating routine hematologic indices, targeted gene expression, circulating oncoprotein levels, and patient compliance metrics may provide an accessible framework for dynamic monitoring. Methods: In this longitudinal cohort study of 66 patients across 272 serial encounters (discrete follow-up intervals: days 0, 14, 41, 71, and 78), we assessed the prognostic value of peripheral complete blood counts (white blood cell count [WBC], hemoglobin [Hb]), molecular indicators (FLT3, NPM1, and DNMT3A transcript levels; targeted soluble FLT3 quantification), and medication adherence. The primary clinical endpoint was longitudinal progression to critical deterioration or disease-related mortality. Generalized linear mixed-effects models (GLMM) with patient-specific random intercepts were constructed to account for intra-subject repeated measures. Predictors were standardized per 1-SD increment. Model performance was assessed via the Akaike Information Criterion (AIC) and the Concordance index (C-index). Results: Leukocyte expansion correlated inversely with hemoglobin concentration (r=-0.877, p<0.001), reflecting bone marrow infiltration and secondary erythroid suppression. Multivariable mixed-effects modeling confirmed that elevated WBC count (adjusted odds ratio [aOR] = 1.52 per 1-SD increase; 95% CI: 1.24-1.86; p<0.001) and reduced medication adherence (aOR = 0.58; 95% CI: 0.44-0.76; p<0.001) independently predicted adverse clinical transition. Integrating targeted molecular markers (FLT3 expression and soluble protein levels) with routine hematologic indices and adherence demonstrated superior calibration and discrimination over single-domain models ({Delta}AIC[&ge;]116; Harrells C-index = 0.81). Conclusions: Readily accessible peripheral hematologic indices, targeted molecular quantification, and medication adherence provide complementary prognostic information regarding disease activity. Integrating these low-burden parameters into clinical workflows offers an efficient, scalable paradigm for early risk stratification in hematologic malignancies.

Venetoclax and azacitidine (ven-aza) is a standard of care therapy for newly diagnosed acute myeloid leukemia (AML) patients unfit to receive intensive therapy, and may also be appropriate for certain fit patients. Models predicting response to ven-aza currently focus predominantly on genetics. Here, we present two multimodal fusion models: a custom ResNet-34-based model and a pathology foundation model fine-tuned for bone marrow smear (BMS) images that combine clinical and genetic variables with whole slide images. Training on 193 newly diagnosed AML patients who received ven-aza, we obtained an area-under-the-receiver-operating-characteristic (AUROC) of 0.79 and 0.82 for the ResNet-based and fine-tuned foundation models in a heldout test set, and 0.76 and 0.73 in an external validation set, predicting best response to this therapy. Sensitivity analysis showed that fusing image data with clinical and genetic variables outperformed training on either modality alone. In univariable and multivariable analyses, image-based classification was an independent predictive marker, second only in effect size to IDH1/2 mutation status, outperforming other genetic alterations. Image-based explainability showed high model attention on myeloblasts, suggesting previously unrecognized cell-specific patterns associated with response. Our findings suggest BMS images complement genetic biomarkers to refine outcome prediction in ven-aza treatment and incentivize AI-supported outcome prediction, including bone marrow morphology.

Inverse design has advanced the discovery of molecules and materials. Yet it remains largely unexplored for steering cell fate, where inputs are continuous, combinatorial culture conditions and outputs are distributions of cell states. Human hematopoiesis, in which combinations and doses of growth factors steer stem cells toward each blood lineage, is a demanding test case. While forward models can evaluate discrete conditions, the vast combinatorial space renders searching for a specific, target-producing design an intractable inverse problem. Here, we introduce LabCompass, an inverse-modeling framework that optimizes experimental designs toward candidates expected to produce specified target cell states, using a flow-matching generative model guided by cellular phenotypes predicted by a forward surrogate. We applied LabCompass to primary human CD34+ in vitro cultures, where continuous cytokine and small-molecule parameters govern hematopoietic cell fate. In a lab-in-the-loop setting, we experimentally validated model-driven designs and used these measurements to update the model across four successive loops. LabCompass recovered established lineage-inducing designs, improved predictions with new data, and enriched target populations across lineages. Incorporating new parameters expanded the design space and enriched rare populations beyond initial reach. Across loops, we generated a 78-million-cell spectral flow cytometry dataset and identified distinct culture conditions converging on the same target cell states. Our results establish generative inverse modeling as a compelling paradigm for navigating high-dimensional, continuous experimental spaces, and demonstrate that virtual cell models should be judged not only by how accurately they predict cellular responses, but also by how effectively they guide experiments toward desired biological outcomes.

Traditional cell tracking methods focus on fully automated tracking. The quality of the generated tracks, however, is heavily influenced by factors such as cell speed and density. In complex scenarios where track correctness is essential, an efficient and reliable tool for manual track correction remains a key component of the cell tracking process. Most tracking tools that allow for such manual correction do so only as a post-processing step, using human feedback to correct one track error at a time -- without improving the quality of other tracks in the dataset. This highlights the need for a more efficient track correction method that iteratively integrates human feedback into the automated tracking process. In this paper we propose a human-in-the-loop approach to cell tracking and investigate the extent to which a tracking algorithm can learn from human input during the tracking process. We combine a graph representation of cell detections, Dijkstra's shortest path algorithm, and a neural network that predicts cell displacement to generate initial track suggestions. We introduce a tool that enables human feedback on individual tracks suggested by the algorithm; this feedback is then propagated to improve subsequent track generation. Compared to the traditional approach of fully automated tracking with correction as a post-processing step, our human-in-the-loop tracking framework reduces the number of corrections required. Finally, we show how this approach can be integrated with existing state-of-the-art tracking algorithms by using pre-generated tracks as a prior, improving the quality of tracks suggested to the human annotator.

In this paper, we introduce Nagini3D, a 3D biological image segmentation method that hybridizes two high-performing yet highly complementary segmentation paradigms: deep learning-based approaches and snake-based methods. Our approach leverages both the high efficiency of data-driven techniques and the convenient shape representation provided by active surfaces, which proves highly practical for incorporating a priori knowledge as well as for the post-analysis of segmented objects. By considering a complete 3D volume, our method ensures segmentation consistency across all three dimensions, unlike many approaches that handle volumes in a slice-by-slice manner. Additionally, it theoretically enables the representation of any object with spherical topology, overcoming the limitations of common 3D methods that rely on object convexity assumptions. Furthermore, the continuous representation of objects allows for a resolution-independent description, facilitating the extraction of various geometric features of interest (e.g., local curvature, principal deformations). We demonstrate both the quality of the segmentation produced by our method and the richness of the accessible geometric features through an extensive set of experiments conducted on multiple real and simulated datasets, including objects with challenging geometries.

Nuclear segmentation in 3D microscopy remains challenging, particularly for low signal-to-noise ratio (SNR) data from timelapse imaging, in vivo experiments, or dense tissue samples. Yet accurate 3D nuclear segmentation is a prerequisite for quantitative single-cell analysis, making this a key bottleneck for high-throughput study of challenging datasets. We present NucLogic, a fast and robust 3D nuclear segmentation algorithm that combines the maturity of 2D segmentation with geometric stitching rules based on nuclear shape, orientation, and intensity, to reconstruct accurate 3D volumes. NucLogic reliably segments challenging datasets including long-term timelapse imaging of organoids, and large dense structures such as the zebrafish brain. Benchmarked against other state-of-the-art segmentation tools, NucLogic matches F1 scores at high SNR, with increasing outperformance as SNR decreases. Importantly, segmentation completes at 20-50% of the computation time, with greater speed gains on larger images. Beyond segmentation, NucLogic includes an intuitive graphical user interface allowing non-experts to segment, quantify, and visualize 3D and 4D data. This enables easy quantification of cell numbers and integration of a variety of both cell-intrinsic properties, such as phenotype, morphology, and local environment metrics, including density and spatial interactions. Together, NucLogic makes quantitative 3D nuclear analysis of previously unmanageable datasets accessible to a broad research community.

Background: Epigenetic deregulation is a defining feature of leukemia, and DNA methylation and chromatin accessibility profiles encode the cell of origin, lineage and clinical behaviour of the disease. Artificial intelligence (AI) and machine learning (ML) can extract predictive patterns from these high-dimensional data, but the published models have not been systematically appraised. We systematically reviewed AI models built on epigenomic data in leukemia for diagnosis, prognosis, relapse and treatment-response prediction, and measurable residual disease (MRD) detection. Methods: This review followed PRISMA 2020 and the SWiM guideline. PubMed was searched on 7 October 2026 with three structured queries, supplemented by a broader PubMed query, citation searching and web searching. Eligible studies were peer-reviewed primary studies that applied an ML or deep-learning algorithm to DNA methylation, chromatin-accessibility or histone-modification data from human leukemia samples and reported a quantitative diagnostic, prognostic, response or MRD outcome. Risk of bias and applicability were assessed with PROBAST, informed by PROBAST+AI. Owing to heterogeneity, results were synthesized narratively and in structured tables, without meta-analysis. Results: Of 68 unique database records and 32 reports from other sources, 30 studies (2010-2026; 22 since 2020) were included: 16 in acute myeloid leukemia, 4 in acute lymphoblastic leukemia, 2 spanning acute leukemia lineages, 3 in juvenile myelomonocytic leukemia and 5 in chronic lymphocytic leukemia; 10 were pediatric. DNA methylation was the input in 28 studies and chromatin accessibility in 2; no eligible study modelled histone marks. Tree ensembles (n = 9) and support vector machines (n = 5) were the most frequent algorithms. Diagnostic classifiers reported accuracy, concordance or F1 scores of 0.87-1.00, and two classifiers were applied to nanopore sequencing data, one returning acute leukemia subtype calls within about 2 hours. Prognostic epigenomic scores were associated with survival (reported hazard ratios 2.36-10.82), but discrimination fell on transport to independent cohorts (C-index 0.677 internally vs 0.529 in one external cohort). Fifteen studies validated models on an external epigenomic cohort, one prospectively. Overall risk of bias was high in 21 studies, unclear in 8 and low in 1, driven by the analysis domain (small samples, absent calibration, possible data leakage). Calibration was reported in 3 studies and code was available for 11. Conclusions: Epigenomic AI models classify leukemia subtypes with high reported accuracy and can deliver same-day diagnoses, and methylation-based scores add prognostic information. However, the evidence is dominated by retrospective, high-risk-of-bias development studies with limited external validation and almost no prospective or impact evaluation. Prospective, multi-center validation with calibrated, transparently reported models is required before clinical adoption.

Extracellular vesicles (EVs) are nanosized, lipid bilayer-enclosed particles that mediate intercellular communication and hold considerable promise as biomarkers and therapeutic agents. However, their functional heterogeneity remains incompletely understood, largely due to the absence of reliable methods for isolating specific EV subpopulations. Here, we established a Nanoscale Flow sorting (NanoFACS) workflow and evaluated its potential for EV detection, sorting, and molecular characterization. We assessed critical parameters, including fluorescent staining and labeling approaches, background signal discrimination, dilution and flow-rate effects, and scatter triggering. We achieved high-purity sorting of CFSE-stained and antibody-labeled EVs, preserving vesicle integrity and sufficient RNA yields for small RNA sequencing of sorted populations. We identified EV subtype-specific small RNAs despite partial cargo overlap in single-marker sorted populations. Our results establish a reproducible antibody-based NanoFACS workflow that defines key operational parameters for reliable EV detection and sorting, with potential adaptability across conventional and spectral flow cytometry platforms. By reducing background and non-EV-associated events, the workflow enables the isolation of phenotypically defined EV subpopulations suitable for downstream molecular analysis, providing a practical approach to investigate EV heterogeneity.

Machine learning benchmarks often treat image files as independent observations, although multiple files may represent repeated views or other related samples. Prior work has shown that non-independent partitioning can inflate model performance, but the sensitivity of a biomedical benchmark to progressively increasing train-test relatedness is less often quantified. Here, we quantified how apparent classification performance changes when recoverable sample groups are progressively allowed to cross training, validation, and test partitions. Using source structure and filenames, we reconstructed analysis groups in a microscopy corpus compiled from multiple sources and generated five class stratified partitioning conditions, ranging from an intact group reference to random assignment of individual files. We applied the same training recipe within each model family to 129,173 images spanning 14 classes of blood cells and hematopoietic cell states. For a pretrained Vision Transformer, random assignment of individual files increased the mean test macro F1 from 0.853 to 0.977 and accuracy from 0.851 to 0.990 relative to the intact group reference. Apparent performance increased progressively across the intermediate conditions. The endpoint pattern also appeared with a ResNet-50 backbone, and the largest apparent gains occurred in immature granulocytic and blast classes. A descriptive analysis within the random assignment condition further showed higher scores among test images that had another member of the same group in the training set, although the exposed and unexposed subsets were not exchangeable. The grouping workflow, exact split definitions, code, and compact result files are released as HSD-Bench to support reproducible evaluation of hidden sample dependence.

Sepsis is life-threatening, yet diagnosis remains a major global challenge because existing approaches lack speed and accuracy. Here we show that label-free imaging cytometry of 10 L whole-blood samples by Remoscope rapidly distinguishes patients with sepsis from those with non-infectious critical illness and healthy controls. In a prospective study of 29 critically ill adults, multi-physician adjudication identified sepsis (n=13), non-infectious critical illness (n=12), and indeterminate status (n=4); these patients were compared to healthy controls (n=22). A multiple instance learning (MIL) model pooled unbiased features from thousands of blood images per patient. Optimized for rule-out, the three-class model detected sepsis with 100% sensitivity and 85.3% specificity. Class activation heatmaps, unsupervised single cell embeddings, and morphometrics converged on abnormal leukocyte and erythrocyte morphology, including immature neutrophil-like cells. Label-free whole-blood imaging with MIL detects sepsis-associated hematologic signatures without stains or cold chain, establishing a foundation for rapid critical care diagnostics.

Context: Cytological specimens allow minimally invasive, repeated sampling for diagnosis and molecular testing. However, cytology biobanking protocols have primarily been optimized for morphology, and the effects of preanalytical handling and storage on intracellular proteins remain unclear. Objective: To assess how fixation, staining, storage temperature, and duration affect intracellular protein preservation in cytological specimens and to identify conditions suitable for in situ proximity ligation assay (isPLA). Design: Human cancer cell lines were processed under different preanalytical conditions. Intracellular proteins and protein protein interactions were assessed by isPLA, fluorescence microscopy, and quantitative image analysis. Slides were stored at room temperature or minus 20 Celsius, with or without MayGrunwaldGiemsa (MGG) staining. Results: Storage temperature had the greatest effect on protein signal. Unstained slides stored at minus 20 Celsius retained strong signals for up to 24 months, whereas room temperature storage reduced detectable protein interactions by approximately 95%. MGG staining further reduced signal intensity during prolonged storage. Nevertheless, stained slides remained suitable for isPLA when staining, microscopic evaluation, destaining, and antibody labeling were completed on the same day. Prolonged room temperature storage of stained slides caused loss of antigenicity, increased autofluorescence, and false negative findings. Conclusions: Low temperature storage and standardized preanalytical handling preserve intracellular protein signals in cytological specimens. These conditions support reliable single cell protein profiling of archived samples and their use in biomarker research and translational pathology.

VEXAS syndrome is an adult-onset severe autoinflammatory disease caused by somatic mutations in UBA1, yet the cascade mechanisms linking primitive hematopoietic abnormalities to mature myeloid dysfunctions remain largely unknown. Identifying master regulators of a progressive disease, a black-box process, from complex transcriptomic data also remains challenging. To address this challenge, we developed CauNagi, a computational framework for prioritizing cascade candidate regulators (CCRs). CauNagi integrates a causal representation learning module derived from CausCell with an iterative deep learning backbone adapted from UNAGI; in addition, CauNagi extends these two components with a unique downstream module for CCRs analysis designed to characterize regulatory propagation across hierarchical cellular states. Mechanistically, CauNagi iteratively integrates causal disentangled representation learning with (1) disease-stage cell-state trajectory reconstruction and (2) dynamic regulatory analysis. Benchmarking on single-cell transcriptomic datasets showed that CauNagi preserved cell-type structure in idiopathic pulmonary fibrosis (IPF) and enriched known acute myeloid leukemia(AML)-associated genes among its top-ranked global regulators. When applied to VEXAS syndrome, CauNagi readily revealed inflammatory responses, endoplasmic reticulum stress, and myeloid bias, consistent with the disease features. Furthermore, the CCRs analysis module of CauNagi assisted us in identifying 36 causal drivers, with SPI1, NFKB1, STAT3, and FOS prioritized as high-confidence regulatory hubs linking aberrant myeloid differentiation and inflammatory programs. These findings were further supported by an independent single-cell transcriptomic dataset from a murine VEXAS model. Overall, CauNagi provides a computationally efficient and systematic framework for identifying candidate causal regulators. Beyond hematopoietic diseases, CauNagi may also be applicable to other progressive disorders for which multistage single-cell transcriptomic datasets are available. CauNagi is available at https://github.com/steamed-stuffed-bun/CauNagi.

Automated triage of whole-slide cervical cytology images remains constrained by the heavy dependence on single-cell bounding boxes or pixel-level annotations, which introduce significant bottlenecks, high expert overhead, and observer variability. To address these challenges, we present a weakly-supervised, detection-free Multiple Instance Learning (MIL) framework powered by a Gated Attention pooling engine that operates exclusively on slide-level predictions. By treating whole-slide images as bags of local instance patches, the dual-branch gated network dynamically assigns non-linear attention weights to highlight isolated dysplastic cells while suppressing benign background and debris, successfully resolving the "needle-in-a-haystack" problem inherent to high-grade lesions. Evaluated across multi-center cohorts including internal datasets (SIPaKMeD, Herlev, and CRIC) and the unannotated, out-of-distribution Mendeley LBC validation cohort processed via an unsupervised marker-controlled watershed pipeline our approach demonstrates robust generalization without requiring dense instance labels. Furthermore, our architectural comparison reveals a key trade-off: lightweight backbones like MobileNetV2 optimize in-distribution multi-center accuracy (90.96% Accuracy, 0.9800 ROC-AUC), whereas higher-capacity models like Xception ensure superior out-of-distribution robustness (80.43% Balanced Accuracy) under domain shifts. Ultimately, this detection-less pipeline provides a scalable and clinically viable solution to automate slide triage and alleviate cytopathologist shortages in resource-constrained environments.