Expert-level detection of M-proteins in serum protein electrophoresis using machine learning.

OBJECTIVES: Serum protein electrophoresis (SPE) in combination with immunotyping (IMT) is the diagnostic standard for detecting monoclonal proteins (M-proteins). However, interpretation of SPE and IMT is weakly standardized, time consuming and investigator dependent. Here, we present five machine learning (ML) approaches for automated detection of M-proteins on SPE on an unprecedented large and well-curated data set and compare the performance with that of laboratory experts. METHODS: SPE and IMT were performed in serum samples from 69,722 individuals from Norway. IMT results were used to label the samples as M-protein present (positive, n=4,273) or absent (negative n=65,449). Four feature-based ML algorithms and one convolutional neural network (CNN) were trained on 68,722 randomly selected SPE patterns to detect M-proteins. Algorithm performance was compared to that of an expert group of clinical pathologists and laboratory technicians (n=10) on a test set of 1,000 samples. RESULTS: The random forest classifier showed the best performance (F1-Score 93.2 %, accuracy 99.1 %, sensitivity 89.9 %, specificity 99.8 %, positive predictive value 96.9 %, negative predictive value 99.3 %) and outperformed the experts (F1-Score 61.2 ± 16.0 %, accuracy 89.2 ± 10.2 %, sensitivity 94.3 ± 2.8 %, specificity 88.9 ± 10.9 %, positive predictive value 47.3 ± 16.2 %, negative predictive value 99.5 ± 0.2 %) on the test set. Interestingly the performance of the RFC saturated, the CNN performance increased steadily within our training set (n=68,722). CONCLUSIONS: Feature-based ML systems are capable of automated detection of M-proteins on SPE beyond expert-level and show potential for use in the clinical laboratory.

CD37 is a safe chimeric antigen receptor target to treat acute myeloid leukemia.

Acute myeloid leukemia (AML) is characterized by the accumulation of immature myeloid cells in the bone marrow and the peripheral blood. Nearly half of the AML patients relapse after standard induction therapy, and new forms of therapy are urgently needed. Chimeric antigen receptor (CAR) T therapy has so far not been successful in AML due to lack of efficacy and safety. Indeed, the most attractive antigen targets are stem cell markers such as CD33 or CD123. We demonstrate that CD37, a mature B cell marker, is expressed in AML samples, and its presence correlates with the European LeukemiaNet (ELN) 2017 risk stratification. We repurpose the anti-lymphoma CD37CAR for the treatment of AML and show that CD37CAR T cells specifically kill AML cells, secrete proinflammatory cytokines, and control cancer progression in vivo. Importantly, CD37CAR T cells display no toxicity toward hematopoietic stem cells. Thus, CD37 is a promising and safe CAR T cell AML target.

Spatial proteomics in neurons at single-protein resolution.

To understand biological processes, it is necessary to reveal the molecular heterogeneity of cells by gaining access to the location and interaction of all biomolecules. Significant advances were achieved by super-resolution microscopy, but such methods are still far from reaching the multiplexing capacity of proteomics. Here, we introduce secondary label-based unlimited multiplexed DNA-PAINT (SUM-PAINT), a high-throughput imaging method that is capable of achieving virtually unlimited multiplexing at better than 15 nm resolution. Using SUM-PAINT, we generated 30-plex single-molecule resolved datasets in neurons and adapted omics-inspired analysis for data exploration. This allowed us to reveal the complexity of synaptic heterogeneity, leading to the discovery of a distinct synapse type. We not only provide a resource for researchers, but also an integrated acquisition and analysis workflow for comprehensive spatial proteomics at single-protein resolution.

Generation of complex bone marrow organoids from human induced pluripotent stem cells.

The human bone marrow (BM) niche sustains hematopoiesis throughout life. We present a method for generating complex BM-like organoids (BMOs) from human induced pluripotent stem cells (iPSCs). BMOs consist of key cell types that self-organize into spatially defined three-dimensional structures mimicking cellular, structural and molecular characteristics of the hematopoietic microenvironment. Functional properties of BMOs include the presence of an in vivo-like vascular network, the presence of multipotent mesenchymal stem/progenitor cells, the support of neutrophil differentiation and responsiveness to inflammatory stimuli. Single-cell RNA sequencing revealed a heterocellular composition including the presence of a hematopoietic stem/progenitor (HSPC) cluster expressing genes of fetal HSCs. BMO-derived HSPCs also exhibited lymphoid potential and a subset demonstrated transient engraftment potential upon xenotransplantation in mice. We show that the BMOs could enable the modeling of hematopoietic developmental aspects and inborn errors of hematopoiesis, as shown for human VPS45 deficiency. Thus, iPSC-derived BMOs serve as a physiologically relevant in vitro model of the human BM microenvironment to study hematopoietic development and BM diseases.

PXPermute reveals staining importance in multichannel imaging flow cytometry.

Imaging flow cytometry (IFC) allows rapid acquisition of numerous single-cell images per second, capturing information from multiple fluorescent channels. However, the traditional process of staining cells with fluorescently labeled conjugated antibodies for IFC analysis is time consuming, expensive, and potentially harmful to cell viability. To streamline experimental workflows and reduce costs, it is crucial to identify the most relevant channels for downstream analysis. In this study, we introduce PXPermute, a user-friendly and powerful method for assessing the significance of IFC channels, particularly for cell profiling. Our approach evaluates channel importance by permuting pixel values within each channel and analyzing the resulting impact on machine learning or deep learning models. Through rigorous evaluation of three multichannel IFC image datasets, we demonstrate PXPermute's potential in accurately identifying the most informative channels, aligning with established biological knowledge. PXPermute can assist biologists with systematic channel analysis, experimental design optimization, and biomarker identification.

Built to Last? Reproducibility and Reusability of Deep Learning Algorithms in Computational Pathology.

Recent progress in computational pathology has been driven by deep learning. While code and data availability are essential to reproduce findings from preceding publications, ensuring a deep learning model's reusability is more challenging. For that, the codebase should be well-documented and easy to integrate into existing workflows and models should be robust toward noise and generalizable toward data from different sources. Strikingly, only a few computational pathology algorithms have been reused by other researchers so far, let alone employed in a clinical setting. To assess the current state of reproducibility and reusability of computational pathology algorithms, we evaluated peer-reviewed articles available in PubMed, published between January 2019 and March 2021, in 5 use cases: stain normalization; tissue type segmentation; evaluation of cell-level features; genetic alteration prediction; and inference of grading, staging, and prognostic information. We compiled criteria for data and code availability and statistical result analysis and assessed them in 160 publications. We found that only one-quarter (41 of 160 publications) made code publicly available. Among these 41 studies, three-quarters (30 of 41) analyzed their results statistically, half of them (20 of 41) released their trained model weights, and approximately a third (16 of 41) used an independent cohort for evaluation. Our review is intended for both pathologists interested in deep learning and researchers applying algorithms to computational pathology challenges. We provide a detailed overview of publications with published code in the field, list reusable data handling tools, and provide criteria for reproducibility and reusability.

Modeling early treatment response in AML from cell-free tumor DNA.

Monitoring disease response after intensive chemotherapy for acute myeloid leukemia (AML) currently requires invasive bone marrow biopsies, imposing a significant burden on patients. In contrast, cell-free tumor DNA (ctDNA) in peripheral blood, carrying tumor-specific mutations, offers a less-invasive assessment of residual disease. However, the relationship between ctDNA levels and bone marrow blast kinetics remains unclear. We explored this in 10 AML patients with NPM1 and IDH2 mutations undergoing initial chemotherapy. Comparison of mathematical mixed-effect models showed that (1) inclusion of blast cell death in the bone marrow, (2) transition of ctDNA to peripheral blood, and (3) ctDNA decay in peripheral blood describes kinetics of blast cells and ctDNA best. The fitted model allows prediction of residual bone marrow blast content from ctDNA, and its scaling factor, representing clonal heterogeneity, correlates with relapse risk. Our study provides precise insights into blast and ctDNA kinetics, offering novel avenues for AML disease monitoring.

Explainable machine learning for profiling the immunological synapse and functional characterization of therapeutic antibodies.

Therapeutic antibodies are widely used to treat severe diseases. Most of them alter immune cells and act within the immunological synapse; an essential cell-to-cell interaction to direct the humoral immune response. Although many antibody designs are generated and evaluated, a high-throughput tool for systematic antibody characterization and prediction of function is lacking. Here, we introduce the first comprehensive open-source framework, scifAI (single-cell imaging flow cytometry AI), for preprocessing, feature engineering, and explainable, predictive machine learning on imaging flow cytometry (IFC) data. Additionally, we generate the largest publicly available IFC dataset of the human immunological synapse containing over 2.8 million images. Using scifAI, we analyze class frequency and morphological changes under different immune stimulation. T cell cytokine production across multiple donors and therapeutic antibodies is quantitatively predicted in vitro, linking morphological features with function and demonstrating the potential to significantly impact antibody design. scifAI is universally applicable to IFC data. Given its modular architecture, it is straightforward to incorporate into existing workflows and analysis pipelines, e.g., for rapid antibody screening and functional characterization.

Label-free imaging of 3D pluripotent stem cell differentiation dynamics on chip.

Massive, parallelized 3D stem cell cultures for engineering in vitro human cell types require imaging methods with high time and spatial resolution to fully exploit technological advances in cell culture technologies. Here, we introduce a large-scale integrated microfluidic chip platform for automated 3D stem cell differentiation. To fully enable dynamic high-content imaging on the chip platform, we developed a label-free deep learning method called Bright2Nuc to predict in silico nuclear staining in 3D from confocal microscopy bright-field images. Bright2Nuc was trained and applied to hundreds of 3D human induced pluripotent stem cell cultures differentiating toward definitive endoderm on a microfluidic platform. Combined with existing image analysis tools, Bright2Nuc segmented individual nuclei from bright-field images, quantified their morphological properties, predicted stem cell differentiation state, and tracked the cells over time. Our methods are available in an open-source pipeline, enabling researchers to upscale image acquisition and phenotyping of 3D cell culture.

[Artificial Intelligence for computer-aided leukemia diagnostics]. / Künstliche Intelligenz für die computerunterstützte Leukämiediagnostik.

The manual examination of blood and bone marrow specimens for leukemia patients is time-consuming and limited by intra- and inter-observer variance. The development of AI algorithms for leukemia diagnostics requires high-quality sample digitization and reliable annotation of large datasets. Deep learning-based algorithms using these datasets attain human-level performance for some well-defined, clinically relevant questions such as the blast character of cells. Methods such as multiple - instance - learning allow predicting diagnoses from a collection of leukocytes, but are more data-intensive. Using "explainable AI" methods can make the prediction process more transparent and allow users to verify the algorithm's predictions. Stability and robustness analyses are necessary for routine application of these algorithms, and regulatory institutions are developing standards for this purpose. Integrated diagnostics, which link different diagnostic modalities, offer the promise of even greater accuracy but require more extensive and diverse datasets.

Progressive disruption of hematopoietic architecture from clonal hematopoiesis to MDS.

Clonal hematopoiesis of indeterminate potential (CHIP) describes the age-related acquisition of somatic mutations in hematopoietic stem/progenitor cells (HSPC) leading to clonal blood cell expansion. Although CHIP mutations drive myeloid malignancies like myelodysplastic syndromes (MDS) it is unknown if clonal expansion is attributable to changes in cell type kinetics, or involves reorganization of the hematopoietic hierarchy. Using computational modeling we analyzed differentiation and proliferation kinetics of cultured hematopoietic stem cells (HSC) from 8 healthy individuals, 7 CHIP, and 10 MDS patients. While the standard hematopoietic hierarchy explained HSPC kinetics in healthy samples, 57% of CHIP and 70% of MDS samples were best described with alternative hierarchies. Deregulated kinetics were found at various HSPC compartments with high inter-individual heterogeneity in CHIP and MDS, while altered HSC rates were most relevant in MDS. Quantifying kinetic heterogeneity in detail, we show that reorganization of the HSPC compartment is already detectable in the premalignant CHIP state.

RedTell: an AI tool for interpretable analysis of red blood cell morphology.

Introduction: Hematologists analyze microscopic images of red blood cells to study their morphology and functionality, detect disorders and search for drugs. However, accurate analysis of a large number of red blood cells needs automated computational approaches that rely on annotated datasets, expensive computational resources, and computer science expertise. We introduce RedTell, an AI tool for the interpretable analysis of red blood cell morphology comprising four single-cell modules: segmentation, feature extraction, assistance in data annotation, and classification. Methods: Cell segmentation is performed by a trained Mask R-CNN working robustly on a wide range of datasets requiring no or minimum fine-tuning. Over 130 features that are regularly used in research are extracted for every detected red blood cell. If required, users can train task-specific, highly accurate decision tree-based classifiers to categorize cells, requiring a minimal number of annotations and providing interpretable feature importance. Results: We demonstrate RedTell's applicability and power in three case studies. In the first case study we analyze the difference of the extracted features between the cells coming from patients suffering from different diseases, in the second study we use RedTell to analyze the control samples and use the extracted features to classify cells into echinocytes, discocytes and stomatocytes and finally in the last use case we distinguish sickle cells in sickle cell disease patients. Discussion: We believe that RedTell can accelerate and standardize red blood cell research and help gain new insights into mechanisms, diagnosis, and treatment of red blood cell associated disorders.

Bispecific antibodies redirect synthetic agonistic receptor modified T cells against melanoma.

BACKGROUND: Melanoma is an immune sensitive disease, as demonstrated by the activity of immune check point blockade (ICB), but many patients will either not respond or relapse. More recently, tumor infiltrating lymphocyte (TIL) therapy has shown promising efficacy in melanoma treatment after ICB failure, indicating the potential of cellular therapies. However, TIL treatment comes with manufacturing limitations, product heterogeneity, as well as toxicity problems, due to the transfer of a large number of phenotypically diverse T cells. To overcome said limitations, we propose a controlled adoptive cell therapy approach, where T cells are armed with synthetic agonistic receptors (SAR) that are selectively activated by bispecific antibodies (BiAb) targeting SAR and melanoma-associated antigens. METHODS: Human as well as murine SAR constructs were generated and transduced into primary T cells. The approach was validated in murine, human and patient-derived cancer models expressing the melanoma-associated target antigens tyrosinase-related protein 1 (TYRP1) and melanoma-associated chondroitin sulfate proteoglycan (MCSP) (CSPG4). SAR T cells were functionally characterized by assessing their specific stimulation and proliferation, as well as their tumor-directed cytotoxicity, in vitro and in vivo. RESULTS: MCSP and TYRP1 expression was conserved in samples of patients with treated as well as untreated melanoma, supporting their use as melanoma-target antigens. The presence of target cells and anti-TYRP1 × anti-SAR or anti-MCSP × anti-SAR BiAb induced conditional antigen-dependent activation, proliferation of SAR T cells and targeted tumor cell lysis in all tested models. In vivo, antitumoral activity and long-term survival was mediated by the co-administration of SAR T cells and BiAb in a syngeneic tumor model and was further validated in several xenograft models, including a patient-derived xenograft model. CONCLUSION: The SAR T cell-BiAb approach delivers specific and conditional T cell activation as well as targeted tumor cell lysis in melanoma models. Modularity is a key feature for targeting melanoma and is fundamental towards personalized immunotherapies encompassing cancer heterogeneity. Because antigen expression may vary in primary melanoma tissues, we propose that a dual approach targeting two tumor-associated antigens, either simultaneously or sequentially, could avoid issues of antigen heterogeneity and deliver therapeutic benefit to patients.

Wound infiltrating adipocytes are not myofibroblasts.

The origins of wound myofibroblasts and scar tissue remains unclear, but it is assumed to involve conversion of adipocytes into myofibroblasts. Here, we directly explore the potential plasticity of adipocytes and fibroblasts after skin injury. Using genetic lineage tracing and live imaging in explants and in wounded animals, we observe that injury induces a transient migratory state in adipocytes with vastly distinct cell migration patterns and behaviours from fibroblasts. Furthermore, migratory adipocytes, do not contribute to scar formation and remain non-fibrogenic in vitro, in vivo and upon transplantation into wounds in animals. Using single-cell and bulk transcriptomics we confirm that wound adipocytes do not convert into fibrogenic myofibroblasts. In summary, the injury-induced migratory adipocytes remain lineage-restricted and do not converge or reprogram into a fibrosing phenotype. These findings broadly impact basic and translational strategies in the regenerative medicine field, including clinical interventions for wound repair, diabetes, and fibrotic pathologies.

Single-cell transcriptomic atlas-guided development of CAR-T cells for the treatment of acute myeloid leukemia.

Chimeric antigen receptor T cells (CAR-T cells) have emerged as a powerful treatment option for individuals with B cell malignancies but have yet to achieve success in treating acute myeloid leukemia (AML) due to a lack of safe targets. Here we leveraged an atlas of publicly available RNA-sequencing data of over 500,000 single cells from 15 individuals with AML and tissue from 9 healthy individuals for prediction of target antigens that are expressed on malignant cells but lacking on healthy cells, including T cells. Aided by this high-resolution, single-cell expression approach, we computationally identify colony-stimulating factor 1 receptor and cluster of differentiation 86 as targets for CAR-T cell therapy in AML. Functional validation of these established CAR-T cells shows robust in vitro and in vivo efficacy in cell line- and human-derived AML models with minimal off-target toxicity toward relevant healthy human tissues. This provides a strong rationale for further clinical development.

Explainable AI identifies diagnostic cells of genetic AML subtypes.

Explainable AI is deemed essential for clinical applications as it allows rationalizing model predictions, helping to build trust between clinicians and automated decision support tools. We developed an inherently explainable AI model for the classification of acute myeloid leukemia subtypes from blood smears and found that high-attention cells identified by the model coincide with those labeled as diagnostically relevant by human experts. Based on over 80,000 single white blood cell images from digitized blood smears of 129 patients diagnosed with one of four WHO-defined genetic AML subtypes and 60 healthy controls, we trained SCEMILA, a single-cell based explainable multiple instance learning algorithm. SCEMILA could perfectly discriminate between AML patients and healthy controls and detected the APL subtype with an F1 score of 0.86±0.05 (mean±s.d., 5-fold cross-validation). Analyzing a novel multi-attention module, we confirmed that our algorithm focused with high concordance on the same AML-specific cells as human experts do. Applied to classify single cells, it is able to highlight subtype specific cells and deconvolve the composition of a patient's blood smear without the need of single-cell annotation of the training data. Our large AML genetic subtype dataset is publicly available, and an interactive online tool facilitates the exploration of data and predictions. SCEMILA enables a comparison of algorithmic and expert decision criteria and can present a detailed analysis of individual patient data, paving the way to deploy AI in the routine diagnostics for identifying hematopoietic neoplasms.

A generalizable brain extraction net (BEN) for multimodal MRI data from rodents, nonhuman primates, and humans.

Accurate brain tissue extraction on magnetic resonance imaging (MRI) data is crucial for analyzing brain structure and function. While several conventional tools have been optimized to handle human brain data, there have been no generalizable methods to extract brain tissues for multimodal MRI data from rodents, nonhuman primates, and humans. Therefore, developing a flexible and generalizable method for extracting whole brain tissue across species would allow researchers to analyze and compare experiment results more efficiently. Here, we propose a domain-adaptive and semi-supervised deep neural network, named the Brain Extraction Net (BEN), to extract brain tissues across species, MRI modalities, and MR scanners. We have evaluated BEN on 18 independent datasets, including 783 rodent MRI scans, 246 nonhuman primate MRI scans, and 4601 human MRI scans, covering five species, four modalities, and six MR scanners with various magnetic field strengths. Compared to conventional toolboxes, the superiority of BEN is illustrated by its robustness, accuracy, and generalizability. Our proposed method not only provides a generalized solution for extracting brain tissue across species but also significantly improves the accuracy of atlas registration, thereby benefiting the downstream processing tasks. As a novel fully automated deep-learning method, BEN is designed as an open-source software to enable high-throughput processing of neuroimaging data across species in preclinical and clinical applications.

Magnetic resonance imaging (MRI) is an ideal way to obtain high-resolution images of the whole brain of rodents and primates (including humans) non-invasively. A critical step in processing MRI data is brain tissue extraction, which consists on removing the signal from the non-neural tissues around the brain, such as the skull or fat, from the images. If this step is done incorrectly, it can lead to images with signals that do not correspond to the brain, which can compromise downstream analysis, and lead to errors when comparing samples from similar species. Although several traditional toolboxes to perform brain extraction are available, most of them focus on human brains, and no standardized methods are available for other mammals, such as rodents and monkeys. To bridge this gap, Yu et al. developed a computational method based on deep learning (a type of machine learning that imitates how humans learn certain types of information) named the Brain Extraction Net (BEN). BEN can extract brain tissues across species, MRI modalities, and scanners to provide a generalizable toolbox for neuroimaging using MRI. Next, Yu et al. demonstrated BEN's functionality in a large-scale experiment involving brain tissue extraction in eighteen different MRI datasets from different species. In these experiments, BEN was shown to improve the robustness and accuracy of processing brain magnetic resonance imaging data. Brain tissue extraction is essential for MRI-based neuroimaging studies, so BEN can benefit both the neuroimaging and the neuroscience communities. Importantly, the tool is an open-source software, allowing other researchers to use it freely. Additionally, it is an extensible tool that allows users to provide their own data and pre-trained networks to further improve BEN's generalization. Yu et al. have also designed interfaces to support other popular neuroimaging processing pipelines and to directly deal with external datasets, enabling scientists to use it to extract brain tissue in their own experiments.

Altered expression response upon repeated gene repression in single yeast cells.

Cells must continuously adjust to changing environments and, thus, have evolved mechanisms allowing them to respond to repeated stimuli. While faster gene induction upon a repeated stimulus is known as reinduction memory, responses to repeated repression have been less studied so far. Here, we studied gene repression across repeated carbon source shifts in over 1,500 single Saccharomyces cerevisiae cells. By monitoring the expression of a carbon source-responsive gene, galactokinase 1 (Gal1), and fitting a mathematical model to the single-cell data, we observed a faster response upon repeated repressions at the population level. Exploiting our single-cell data and quantitative modeling approach, we discovered that the faster response is mediated by a shortened repression response delay, the estimated time between carbon source shift and Gal1 protein production termination. Interestingly, we can exclude two alternative hypotheses, i) stronger dilution because of e.g., increased proliferation, and ii) a larger fraction of repressing cells upon repeated repressions. Collectively, our study provides a quantitative description of repression kinetics in single cells and allows us to pinpoint potential mechanisms underlying a faster response upon repeated repression. The computational results of our study can serve as the starting point for experimental follow-up studies.

SHAPR predicts 3D cell shapes from 2D microscopic images.

Reconstruction of shapes and sizes of three-dimensional (3D) objects from two- dimensional (2D) information is an intensely studied subject in computer vision. We here consider the level of single cells and nuclei and present a neural network-based SHApe PRediction autoencoder. For proof-of-concept, SHAPR reconstructs 3D shapes of red blood cells from single view 2D confocal microscopy images more accurately than naïve stereological models and significantly increases the feature-based prediction of red blood cell types from F1 = 79% to F1 = 87.4%. Applied to 2D images containing spheroidal aggregates of densely grown human induced pluripotent stem cells, we find that SHAPR learns fundamental shape properties of cell nuclei and allows for prediction-based morphometry. Reducing imaging time and data storage, SHAPR will help to optimize and up-scale image-based high-throughput applications for biomedicine.