Integration of mechanistic immunological knowledge into a machine learning pipeline improves predictions

New horizons at the interface of artificial intelligence and translational cancer research

Artificial intelligence (AI) is increasingly being utilized in cancer research as a computational strategy for analyzing multiomics datasets. Advances in single-cell and spatial profiling technologies have contributed significantly to our understanding of tumor biology, and AI methodologies are now being applied to accelerate translational efforts, including target discovery, biomarker identification, patient stratification, and therapeutic response prediction. Despite these advancements, the integration of AI into clinical workflows remains limited, presenting both challenges and opportunities. This review discusses AI applications in multiomics analysis and translational oncology, emphasizing their role in advancing biological discoveries and informing clinical decision-making. Key areas of focus include cellular heterogeneity, tumor microenvironment interactions, and AI-aided diagnostics. Challenges such as reproducibility, interpretability of AI models, and clinical integration are explored, with attention to strategies for addressing these hurdles. Together, these developments underscore the potential of AI and multiomics to enhance precision oncology and contribute to advancements in cancer care.

Opportunities and challenges with artificial intelligence in allergy and immunology: a bibliometric study

Introduction

The fields of allergy and immunology are increasingly recognizing the transformative potential of artificial intelligence (AI). Its adoption is reshaping research directions, clinical practices, and healthcare systems. However, a systematic overview identifying current statuses, emerging trends, and future research hotspots is lacking.

Methods

This study applied bibliometric analysis methods to systematically evaluate the global research landscape of AI applications in allergy and immunology. Data from 3,883 articles published by 21,552 authors across 1,247 journals were collected and analyzed to identify leading contributors, prevalent research themes, and collaboration patterns.

Results

Analysis revealed that the USA and China are currently leading in research output and scientific impact in this domain. AI methodologies, especially machine learning (ML) and deep learning (DL), are predominantly applied in drug discovery and development, disease classification and prediction, immune response modeling, clinical decision support, diagnostics, healthcare system digitalization, and medical education. Emerging trends indicate significant movement toward personalized medical systems integration.

Discussion

The findings demonstrate the dynamic evolution of AI in allergy and immunology, highlighting the broadening scope from basic diagnostics to comprehensive personalized healthcare systems. Despite advancements, critical challenges persist, including technological limitations, ethical concerns, and regulatory frameworks that could potentially hinder further implementation and integration.

Conclusion

AI holds considerable promise for advancing allergy and immunology globally by enhancing healthcare precision, efficiency, and accessibility. Addressing existing technological, ethical, and regulatory challenges will be crucial to fully realizing its potential, ultimately improving global health outcomes and patient well-being.

Machine Learning Reveals Distinct Immunogenic Signatures of Th1 Imprinting in ART-Treated Individuals with HIV Following Repeated SARS-CoV-2 Vaccination

The human immune system is intrinsically variable and remarkably diverse across a population. The immune response to antigens is driven by a complex interplay of time-dependent interdependencies across components of the immune system. After repeated vaccination, the humoral and cellular arms of the immune response display highly heterogeneous dynamics, further complicating the attribution of a phenotypic outcome to specific immune system components. We employ a random forest (RF) approach to classify informative differences in immunogenicity between older people living with HIV (PLWH) on ART and an age-matched control group who received up to five SARS-CoV-2 vaccinations over 104 weeks. RFs identify immunological variables of importance, interpreted as evidence for Th1 imprinting, and suggest novel distinguishing immune features, such as saliva-based antibody screening, as promising diagnostic features towards classifying responses (whereas serum IgG is not). Additionally, we implement supervised and unsupervised Machine Learning methods to produce physiologically accurate synthetic datasets that conform to the statistical distribution of the original immunological data, thus enabling further data-driven hypothesis testing and model validation. Our results highlight the effectiveness of RFs in utilizing informative immune feature interdependencies for classification tasks and suggests broad impacts of ML applications for personalized vaccination strategies among high-risk populations.

A machine learning approach to leveraging electronic health records for enhanced omics analysis

Omics studies produce a large number of measurements, enabling the development, validation and interpretation of systems-level biological models. Large cohorts are required to power these complex models; yet, the cohort size remains limited due to clinical and budgetary constraints. We introduce clinical and omics multimodal analysis enhanced with transfer learning (COMET), a machine learning framework that incorporates large, observational electronic health record databases and transfer learning to improve the analysis of small datasets from omics studies. By pretraining on electronic health record data and adaptively blending both early and late fusion strategies, COMET overcomes the limitations of existing multimodal machine learning methods. Using two independent datasets, we showed that COMET improved the predictive modelling performance and biological discovery compared with the analysis of omics data with traditional methods. By incorporating electronic health record data into omics analyses, COMET enables more precise patient classifications, beyond the simplistic binary reduction to cases and controls. This framework can be broadly applied to the analysis of multimodal omics studies and reveals more powerful biological insights from limited cohort sizes.

An immune signature of postoperative cognitive decline: a prospective cohort study

BACKGROUND

Postoperative cognitive decline (POCD) is the predominant complication affecting patients over 60 years old following major surgery, yet its prediction and prevention remain challenging. Understanding the biological processes underlying the pathogenesis of POCD is essential for identifying mechanistic biomarkers to advance diagnostics and therapeutics. This study aimed to provide a comprehensive analysis of immune cell trajectories differentiating patients with and without POCD and to derive a predictive score enabling the identification of high-risk patients during the preoperative period.

MATERIAL AND METHODS

Twenty-six patients aged 60 years old and older undergoing elective major orthopedic surgery were enrolled in a prospective longitudinal study, and the occurrence of POCD was assessed 7 days after surgery. Serial samples collected before surgery, and 1, 7, and 90 days after surgery were analyzed using a combined single-cell mass cytometry and plasma proteomic approach. Unsupervised clustering of the high-dimensional mass cytometry data was employed to characterize time-dependent trajectories of all major innate and adaptive immune cell frequencies and signaling responses. Sparse machine learning coupled with data-driven feature selection was applied to the presurgery immunological dataset to classify patients at risk for POCD.

RESULTS

The analysis identified cell-type and signaling-specific immune trajectories differentiating patients with and without POCD. The most prominent trajectory features revealed early exacerbation of JAK/STAT and dampening of inhibitory κB and nuclear factor-κB immune signaling responses in patients with POCD. Further analyses integrating immunological and clinical data collected before surgery identified a preoperative predictive model comprising one plasma protein and 10 immune cell features that classified patients at risk for POCD with excellent accuracy (AUC=0.80, P =2.21e-02 U -test).

CONCLUSION

Immune system-wide monitoring of patients over 60 years old undergoing surgery unveiled a peripheral immune signature of POCD. A predictive model built on immunological data collected before surgery demonstrated greater accuracy in predicting POCD compared to known clinical preoperative risk factors, offering a concise list of biomarker candidates to personalize perioperative management.

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.

Predicting viral proteins that evade the innate immune system: a machine learning-based immunoinformatics tool

Viral proteins that evade the host's innate immune response play a crucial role in pathogenesis, significantly impacting viral infections and potential therapeutic strategies. Identifying these proteins through traditional methods is challenging and time-consuming due to the complexity of virus-host interactions. Leveraging advancements in computational biology, we present VirusHound-II, a novel tool that utilizes machine learning techniques to predict viral proteins evading the innate immune response with high accuracy. We evaluated a comprehensive range of machine learning models, including ensemble methods, neural networks, and support vector machines. Using a dataset of 1337 viral proteins known to evade the innate immune response (VPEINRs) and an equal number of non-VPEINRs, we employed pseudo amino acid composition as the molecular descriptor. Our methodology involved a tenfold cross-validation strategy on 80% of the data for training, followed by testing on an independent dataset comprising the remaining 20%. The random forest model demonstrated superior performance metrics, achieving 0.9290 accuracy, 0.9283 F1 score, 0.9354 precision, and 0.9213 sensitivity in the independent testing phase. These results establish VirusHound-II as an advancement in computational virology, accessible via a user-friendly web application. We anticipate that VirusHound-II will be a crucial resource for researchers, enabling the rapid and reliable prediction of viral proteins evading the innate immune response. This tool has the potential to accelerate the identification of therapeutic targets and enhance our understanding of viral evasion mechanisms, contributing to the development of more effective antiviral strategies and advancing our knowledge of virus-host interactions.

Artificial Intelligence and Machine Learning for Inborn Errors of Immunity: Current State and Future Promise

Artificial intelligence (AI) and machine learning (ML) research within medicine has exponentially increased over the last decade, with studies showcasing the potential of AI/ML algorithms to improve clinical practice and outcomes. Ongoing research and efforts to develop AI-based models have expanded to aid in the identification of inborn errors of immunity (IEI). The use of larger electronic health record data sets, coupled with advances in phenotyping precision and enhancements in ML techniques, has the potential to significantly improve the early recognition of IEI, thereby increasing access to equitable care. In this review, we provide a comprehensive examination of AI/ML for IEI, covering the spectrum from data preprocessing for AI/ML analysis to current applications within immunology, and address the challenges associated with implementing clinical decision support systems to refine the diagnosis and management of IEI.

Single-cell peripheral immunoprofiling of lewy body and Parkinson's disease in a multi-site cohort

BACKGROUND

Multiple lines of evidence support peripheral organs in the initiation or progression of Lewy body disease (LBD), a spectrum of neurodegenerative diagnoses that include Parkinson's Disease (PD) without or with dementia (PDD) and dementia with Lewy bodies (DLB). However, the potential contribution of the peripheral immune response to LBD remains unclear. This study aims to characterize peripheral immune responses unique to participants with LBD at single-cell resolution to highlight potential biomarkers and increase mechanistic understanding of LBD pathogenesis in humans.

METHODS

In a case-control study, peripheral mononuclear cell (PBMC) samples from research participants were randomly sampled from multiple sites across the United States. The diagnosis groups comprise healthy controls (HC, n = 159), LBD (n = 110), Alzheimer's disease dementia (ADD, n = 97), other neurodegenerative disease controls (NDC, n = 19), and immune disease controls (IDC, n = 14). PBMCs were activated with three stimulants (LPS, IL-6, and IFNa) or remained at basal state, stained by 13 surface markers and 7 intracellular signal markers, and analyzed by flow cytometry, which generated 1,184 immune features after gating.

RESULTS

The model classified LBD from HC with an AUROC of 0.87 ± 0.06 and AUPRC of 0.80 ± 0.06. Without retraining, the same model was able to distinguish LBD from ADD, NDC, and IDC. Model predictions were driven by pPLCγ2, p38, and pSTAT5 signals from specific cell populations under specific activation. The immune responses characteristic for LBD were not associated with other common medical conditions related to the risk of LBD or dementia, such as sleep disorders, hypertension, or diabetes.

CONCLUSIONS AND RELEVANCE

Quantification of PBMC immune response from multisite research participants yielded a unique pattern for LBD compared to HC, multiple related neurodegenerative diseases, and autoimmune diseases thereby highlighting potential biomarkers and mechanisms of disease.

Artificial Intelligence in Perioperative Care: Opportunities and Challenges

Artificial intelligence (AI) applications have great potential to enhance perioperative care. This paper explores promising areas for AI in anesthesiology; expertise, stakeholders, and infrastructure for development; and barriers and challenges to implementation.

Recent Developments in Machine Learning for Mass Spectrometry

Statistical analysis and modeling of mass spectrometry (MS) data have a long and rich history with several modern MS-based applications using statistical and chemometric methods. Recently, machine learning (ML) has experienced a renaissance due to advents in computational hardware and the development of new algorithms for artificial neural networks (ANN) and deep learning architectures. Moreover, recent successes of new ANN and deep learning architectures in several areas of science, engineering, and society have further strengthened the ML field. Importantly, modern ML methods and architectures have enabled new approaches for tasks related to MS that are now widely adopted in several popular MS-based subdisciplines, such as mass spectrometry imaging and proteomics. Herein, we aim to provide an introductory summary of the practical aspects of ML methodology relevant to MS. Additionally, we seek to provide an up-to-date review of the most recent developments in ML integration with MS-based techniques while also providing critical insights into the future direction of the field.

Solving the Puzzle of Preterm Birth

Solving the puzzle of preterm birth has been challenging and will require novel integrative solutions as preterm birth likely arises from many etiologies. It has been demonstrated that many sociodemographic and psychological determinants of preterm birth relate to its complex biology. It is this understanding that has enabled the development of a novel preventative strategy, which integrates the omics profile (genome, epigenome, transcriptome, proteome, metabolome, microbiome) with sociodemographic, environmental, and psychological determinants of individual pregnant people to solve the puzzle of preterm birth.

Reframing sepsis immunobiology for translation: towards informative subtyping and targeted immunomodulatory therapies

Sepsis is a common and deadly condition. Within the current model of sepsis immunobiology, the framing of dysregulated host immune responses into proinflammatory and immunosuppressive responses for the testing of novel treatments has not resulted in successful immunomodulatory therapies. Thus, the recent focus has been to parse observable heterogeneity into subtypes of sepsis to enable personalised immunomodulation. In this Personal View, we highlight that many fundamental immunological concepts such as resistance, disease tolerance, resilience, resolution, and repair are not incorporated into the current sepsis immunobiology model. The focus for addressing heterogeneity in sepsis should be broadened beyond subtyping to encompass the identification of deterministic molecular networks or dominant mechanisms. We explicitly reframe the dysregulated host immune responses in sepsis as altered homoeostasis with pathological disruption of immune-driven resistance, disease tolerance, resilience, and resolution mechanisms. Our proposal highlights opportunities to identify novel treatment targets and could enable successful immunomodulation in the future.

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 review of mechanistic learning in mathematical oncology

Mechanistic learning refers to the synergistic combination of mechanistic mathematical modeling and data-driven machine or deep learning. This emerging field finds increasing applications in (mathematical) oncology. This review aims to capture the current state of the field and provides a perspective on how mechanistic learning may progress in the oncology domain. We highlight the synergistic potential of mechanistic learning and point out similarities and differences between purely data-driven and mechanistic approaches concerning model complexity, data requirements, outputs generated, and interpretability of the algorithms and their results. Four categories of mechanistic learning (sequential, parallel, extrinsic, intrinsic) of mechanistic learning are presented with specific examples. We discuss a range of techniques including physics-informed neural networks, surrogate model learning, and digital twins. Example applications address complex problems predominantly from the domain of oncology research such as longitudinal tumor response predictions or time-to-event modeling. As the field of mechanistic learning advances, we aim for this review and proposed categorization framework to foster additional collaboration between the data- and knowledge-driven modeling fields. Further collaboration will help address difficult issues in oncology such as limited data availability, requirements of model transparency, and complex input data which are embraced in a mechanistic learning framework.

An immune signature of postoperative cognitive decline in elderly patients

Postoperative cognitive decline (POCD) is the predominant complication affecting elderly patients following major surgery, yet its prediction and prevention remain challenging. Understanding biological processes underlying the pathogenesis of POCD is essential for identifying mechanistic biomarkers to advance diagnostics and therapeutics. This longitudinal study involving 26 elderly patients undergoing orthopedic surgery aimed to characterize the impact of peripheral immune cell responses to surgical trauma on POCD. Trajectory analyses of single-cell mass cytometry data highlighted early JAK/STAT signaling exacerbation and diminished MyD88 signaling post-surgery in patients who developed POCD. Further analyses integrating single-cell and plasma proteomic data collected before surgery with clinical variables yielded a sparse predictive model that accurately identified patients who would develop POCD (AUC = 0.80). The resulting POCD immune signature included one plasma protein and ten immune cell features, offering a concise list of biomarker candidates for developing point-of-care prognostic tests to personalize perioperative management of at-risk patients. The code and the data are documented and available at https://github.com/gregbellan/POCD .

Teaser

Modeling immune cell responses and plasma proteomic data predicts postoperative cognitive decline.

A novel intelligent model for visualized inference of medical diagnosis: A case of TCM

How to present an intelligent model based on known diagnostic knowledge to assist medical diagnosis and display the reasoning process is an interesting issue worth exploring. This study developed a novel intelligent model for visualized inference of medical diagnosis with a case of Traditional Chinese Medicine (TCM). Four classes of TCM's diagnosis composed of Yin deficiency, Liver Yin deficiency, Kidney Yin deficiency, and Liver-Kidney Yin deficiency were selected as research examples. According to the knowledge of diagnostic points in "Diagnostics of TCM", a total of 2000 samples for training and testing were randomly generated for the four classes of TCM's diagnosis. In addition, a total of 60 clinical samples were collected from hospital clinical cases. Training samples were sent to the pre-training language model of Chinese Bert for training to generate intelligent diagnostic module. Simultaneously, a mathematical algorithm was developed to generate inferential digraphs. In order to evaluate the performance of the model, the values of accuracy, F1 score, Mse, Loss and other indicators were calculated for model training and testing. And the confusion matrices and ROC curves were plotted to estimate the predictive ability of the model. The novel model was also compared with RF and XGBOOST. And some instances of inferential digraphs with the model were displayed and analyzed. It may be a new attempt to solve the problem of interpretable and inferential intelligent models in the field of artificial intelligence on medical diagnosis of TCM.

An integrated Bayesian framework for multi-omics prediction and classification

With the growing commonality of multi-omics datasets, there is now increasing evidence that integrated omics profiles lead to more efficient discovery of clinically actionable biomarkers that enable better disease outcome prediction and patient stratification. Several methods exist to perform host phenotype prediction from cross-sectional, single-omics data modalities but decentralized frameworks that jointly analyze multiple time-dependent omics data to highlight the integrative and dynamic impact of repeatedly measured biomarkers are currently limited. In this article, we propose a novel Bayesian ensemble method to consolidate prediction by combining information across several longitudinal and cross-sectional omics data layers. Unlike existing frequentist paradigms, our approach enables uncertainty quantification in prediction as well as interval estimation for a variety of quantities of interest based on posterior summaries. We apply our method to four published multi-omics datasets and demonstrate that it recapitulates known biology in addition to providing novel insights while also outperforming existing methods in estimation, prediction, and uncertainty quantification. Our open-source software is publicly available at https://github.com/himelmallick/IntegratedLearner.

DOME Registry: implementing community-wide recommendations for reporting supervised machine learning in biology

Supervised machine learning (ML) is used extensively in biology and deserves closer scrutiny. The Data Optimization Model Evaluation (DOME) recommendations aim to enhance the validation and reproducibility of ML research by establishing standards for key aspects such as data handling and processing, optimization, evaluation, and model interpretability. The recommendations help to ensure that key details are reported transparently by providing a structured set of questions. Here, we introduce the DOME registry (URL: registry.dome-ml.org), a database that allows scientists to manage and access comprehensive DOME-related information on published ML studies. The registry uses external resources like ORCID, APICURON, and the Data Stewardship Wizard to streamline the annotation process and ensure comprehensive documentation. By assigning unique identifiers and DOME scores to publications, the registry fosters a standardized evaluation of ML methods. Future plans include continuing to grow the registry through community curation, improving the DOME score definition and encouraging publishers to adopt DOME standards, and promoting transparency and reproducibility of ML in the life sciences.

The benefits and pitfalls of machine learning for biomarker discovery

Prospects for the discovery of robust and reproducible biomarkers have improved considerably with the development of sensitive omics platforms that can enable measurement of biological molecules at an unprecedented scale. With technical barriers to success lowering, the challenge is now moving into the analytical domain. Genome-wide discovery presents a problem of scale and multiple testing as standard statistical methods struggle to distinguish signal from noise in increasingly complex biological systems. Machine learning and AI methods are good at finding answers in large datasets, but they have a tendency to overfit solutions. It may be possible to find a local answer or mechanism in a specific patient sample or small group of samples, but this may not generalise to wider patient populations due to the high likelihood of false discovery. The rise of explainable AI offers to improve the opportunity for true discovery by providing explanations for predictions that can be explored mechanistically before proceeding to costly and time-consuming validation studies. This review aims to introduce some of the basic concepts of machine learning and AI for biomarker discovery with a focus on post hoc explanation of predictions. To illustrate this, we consider how explainable AI has already been used successfully, and we explore a case study that applies AI to biomarker discovery in rheumatoid arthritis, demonstrating the accessibility of tools for AI and machine learning. We use this to illustrate and discuss some of the potential challenges and solutions that may enable AI to critically interrogate disease and response mechanisms.

Maternal Vaccination to Prevent Adverse Pregnancy Outcomes: An Underutilized Molecular Immunological Intervention?

Adverse pregnancy outcomes including maternal mortality, stillbirth, preterm birth, intrauterine growth restriction cause millions of deaths each year. More effective interventions are urgently needed. Maternal immunization could be one such intervention protecting the mother and newborn from infection through its pathogen-specific effects. However, many adverse pregnancy outcomes are not directly linked to the infectious pathogens targeted by existing maternal vaccines but rather are linked to pathological inflammation unfolding during pregnancy. The underlying pathogenesis driving such unfavourable outcomes have only partially been elucidated but appear to relate to altered immune regulation by innate as well as adaptive immune responses, ultimately leading to aberrant maternal immune activation. Maternal immunization, like all immunization, impacts the immune system beyond pathogen-specific immunity. This raises the possibility that maternal vaccination could potentially be utilised as a pathogen-agnostic immune modulatory intervention to redirect abnormal immune trajectories towards a more favourable phenotype providing pregnancy protection. In this review we describe the epidemiological evidence surrounding this hypothesis, along with the mechanistic plausibility and present a possible path forward to accelerate addressing the urgent need of adverse pregnancy outcomes.

In-silico generation of high-dimensional immune response data in patients using a deep neural network

Technologies for single-cell profiling of the immune system have enabled researchers to extract rich interconnected networks of cellular abundance, phenotypical and functional cellular parameters. These studies can power machine learning approaches to understand the role of the immune system in various diseases. However, the performance of these approaches and the generalizability of the findings have been hindered by limited cohort sizes in translational studies, partially due to logistical demands and costs associated with longitudinal data collection in sufficiently large patient cohorts. An evolving challenge is the requirement for ever-increasing cohort sizes as the dimensionality of datasets grows. We propose a deep learning model derived from a novel pipeline of optimal temporal cell matching and overcomplete autoencoders that uses data from a small subset of patients to learn to forecast an entire patient's immune response in a high dimensional space from one timepoint to another. In our analysis of 1.08 million cells from patients pre- and post-surgical intervention, we demonstrate that the generated patient-specific data are qualitatively and quantitatively similar to real patient data by demonstrating fidelity, diversity, and usefulness.

Postoperative systemic inflammatory dysregulation and corticosteroids: a narrative review

In some patients, the inflammatory-immune response to surgical injury progresses to a harmful, dysregulated state. We posit that postoperative systemic inflammatory dysregulation forms part of a pathophysiological response to surgical injury that places patients at increased risk of complications and subsequently prolongs hospital stay. In this narrative review, we have outlined the evolution, measurement and prediction of postoperative systemic inflammatory dysregulation, distinguishing it from a healthy and self-limiting host response. We reviewed the actions of glucocorticoids and the potential for heterogeneous responses to peri-operative corticosteroid supplementation. We have then appraised the evidence highlighting the safety of corticosteroid supplementation, and the potential benefits of high/repeated doses to reduce the risks of major complications and death. Finally, we addressed how clinical trials in the future should target patients at higher risk of peri-operative inflammatory complications, whereby corticosteroid regimes should be tailored to modify not only the a priori risk, but also further adjusted in response to markers of an evolving pathophysiological response.

Modulating Immune Response in Viral Infection for Quantitative Forecasts of Drug Efficacy

The antiretroviral drug, the total level of viral production, and the effectiveness of immune responses are the main topics of this review because they are all dynamically interrelated. Immunological and viral processes interact in extremely complex and non-linear ways. For reliable analysis and quantitative forecasts that may be used to follow the immune system and create a disease profile for each patient, mathematical models are helpful in characterizing these non-linear interactions. To increase our ability to treat patients and identify individual differences in disease development, immune response profiling might be useful. Identifying which patients are moving from mild to severe disease would be more beneficial using immune system parameters. Prioritize treatments based on their inability to control the immune response and prevent T cell exhaustion. To increase treatment efficacy and spur additional research in this field, this review intends to provide examples of the effects of modelling immune response in viral infections, as well as the impact of pharmaceuticals on immune response.

Omics approaches: interactions at the maternal-fetal interface and origins of child health and disease

Immunoperinatology is an emerging field. Transdisciplinary efforts by physicians, physician-scientists, basic science researchers, and computational biologists have made substantial advancements by identifying unique immunologic signatures of specific diseases, discovering innovative preventative or treatment strategies, and establishing foundations for individualized neonatal intensive care of the most vulnerable neonates. In this review, we summarize the immunobiology and immunopathology of pregnancy, highlight omics approaches to study the maternal-fetal interface, and their contributions to pregnancy health. We examined the importance of transdisciplinary, multiomic (such as genomics, transcriptomics, proteomics, metabolomics, and immunomics) and machine-learning strategies in unraveling the mechanisms of adverse pregnancy, neonatal, and childhood outcomes and how they can guide the development of novel therapies to improve maternal and neonatal health. IMPACT: Discuss immunoperinatology research from the lens of omics and machine-learning approaches. Identify opportunities for omics-based approaches to delineate infection/inflammation-associated maternal, neonatal, and later life adverse outcomes (e.g., histologic chorioamnionitis [HCA]).

Neuroimaging is the new "spatial omic": multi-omic approaches to neuro-inflammation and immuno-thrombosis in acute ischemic stroke

Ischemic stroke (IS) is the leading cause of acquired disability and the second leading cause of dementia and mortality. Current treatments for IS are primarily focused on revascularization of the occluded artery. However, only 10% of patients are eligible for revascularization and 50% of revascularized patients remain disabled at 3 months. Accumulating evidence highlight the prognostic significance of the neuro- and thrombo-inflammatory response after IS. However, several randomized trials of promising immunosuppressive or immunomodulatory drugs failed to show positive results. Insufficient understanding of inter-patient variability in the cellular, functional, and spatial organization of the inflammatory response to IS likely contributed to the failure to translate preclinical findings into successful clinical trials. The inflammatory response to IS involves complex interactions between neuronal, glial, and immune cell subsets across multiple immunological compartments, including the blood-brain barrier, the meningeal lymphatic vessels, the choroid plexus, and the skull bone marrow. Here, we review the neuro- and thrombo-inflammatory responses to IS. We discuss how clinical imaging and single-cell omic technologies have refined our understanding of the spatial organization of pathobiological processes driving clinical outcomes in patients with an IS. We also introduce recent developments in machine learning statistical methods for the integration of multi-omic data (biological and radiological) to identify patient-specific inflammatory states predictive of IS clinical outcomes.

Engineering time-controlled immunotherapy

Designer lymphocytes expand the dynamic range of possibilities for treating disease.

Non-invasive classification of macrophage polarisation by 2P-FLIM and machine learning

In this study, we utilise fluorescence lifetime imaging of NAD(P)H-based cellular autofluorescence as a non-invasive modality to classify two contrasting states of human macrophages by proxy of their governing metabolic state. Macrophages derived from human blood-circulating monocytes were polarised using established protocols and metabolically challenged using small molecules to validate their responding metabolic actions in extracellular acidification and oxygen consumption. Large field-of-view images of individual polarised macrophages were obtained using fluorescence lifetime imaging microscopy (FLIM). These were challenged in real time with small-molecule perturbations of metabolism during imaging. We uncovered FLIM parameters that are pronounced under the action of carbonyl cyanide-p-trifluoromethoxyphenylhydrazone (FCCP), which strongly stratifies the phenotype of polarised human macrophages; however, this performance is impacted by donor variability when analysing the data at a single-cell level. The stratification and parameters emanating from a full field-of-view and single-cell FLIM approach serve as the basis for machine learning models. Applying a random forests model, we identify three strongly governing FLIM parameters, achieving an area under the receiver operating characteristics curve (ROC-AUC) value of 0.944 and out-of-bag (OBB) error rate of 16.67% when classifying human macrophages in a full field-of-view image. To conclude, 2P-FLIM with the integration of machine learning models is showed to be a powerful technique for analysis of both human macrophage metabolism and polarisation at full FoV and single-cell level.

Where Nanosensors Meet Machine Learning: Prospects and Challenges in Detecting Disease X

Disease X is a hypothetical unknown disease that has the potential to cause an epidemic or pandemic outbreak in the future. Nanosensors are attractive portable devices that can swiftly screen disease biomarkers on site, reducing the reliance on laboratory-based analyses. However, conventional data analytics limit the progress of nanosensor research. In this Perspective, we highlight the integral role of machine learning (ML) algorithms in advancing nanosensing strategies toward Disease X detection. We first summarize recent progress in utilizing ML algorithms for the smart design and fabrication of custom nanosensor platforms as well as realizing rapid on-site prediction of infection statuses. Subsequently, we discuss promising prospects in further harnessing the potential of ML algorithms in other aspects of nanosensor development and biomarker detection.

Prior Knowledge for Predictive Modeling: The Case of Acute Aquatic Toxicity

Early assessment of the potential impact of chemicals on health and the environment requires toxicological properties of the molecules. Predictive modeling is often used to estimate the property values in silico from pre-existing experimental data, which is often scarce and uncertain. One of the ways to advance the predictive modeling procedure might be the use of knowledge existing in the field. Scientific publications contain a vast amount of knowledge. However, the amount of manual work required to process the enormous volumes of information gathered in scientific articles might hinder its utilization. This work explores the opportunity of semiautomated knowledge extraction from scientific papers and investigates a few potential ways of its use for predictive modeling. The knowledge extraction and predictive modeling are applied to the field of acute aquatic toxicity. Acute aquatic toxicity is an important parameter of the safety assessment of chemicals. The extensive amount of diverse information existing in the field makes acute aquatic toxicity an attractive area for investigation of knowledge use for predictive modeling. The work demonstrates that the knowledge collection and classification procedure could be useful in hybrid modeling studies concerning the model and predictor selection, addressing data gaps, and evaluation of models' performance.

Heterogeneity and transcriptome changes of human CD8+ T cells across nine decades of life

The decline of CD8⁺ T cell functions contributes to deteriorating health with aging, but the mechanisms that underlie this phenomenon are not well understood. We use single-cell RNA sequencing with both cross-sectional and longitudinal samples to assess how human CD8⁺ T cell heterogeneity and transcriptomes change over nine decades of life. Eleven subpopulations of CD8⁺ T cells and their dynamic changes with age are identified. Age-related changes in gene expression result from changes in the percentage of cells expressing a given transcript, quantitative changes in the transcript level, or a combination of these two. We develop a machine learning model capable of predicting the age of individual cells based on their transcriptomic features, which are closely associated with their differentiation and mutation burden. Finally, we validate this model in two separate contexts of CD8⁺ T cell aging: HIV infection and CAR T cell expansion in vivo.

The characterisation of T cells during aging is important to predict functional outcomes in vaccination or infection. Here the authors use flow cytometry and scRNA sequencing to transcriptionally age CD8 T cells and then use a machine learning model to interpret cell age from transcriptional profiles.

Integrated plasma proteomic and single-cell immune signaling network signatures demarcate mild, moderate, and severe COVID-19

The biological determinants underlying the range of coronavirus 2019 (COVID-19) clinical manifestations are not fully understood. Here, over 1,400 plasma proteins and 2,600 single-cell immune features comprising cell phenotype, endogenous signaling activity, and signaling responses to inflammatory ligands are cross-sectionally assessed in peripheral blood from 97 patients with mild, moderate, and severe COVID-19 and 40 uninfected patients. Using an integrated computational approach to analyze the combined plasma and single-cell proteomic data, we identify and independently validate a multi-variate model classifying COVID-19 severity (multi-class area under the curve [AUC]training = 0.799, p = 4.2e-6; multi-class AUCvalidation = 0.773, p = 7.7e-6). Examination of informative model features reveals biological signatures of COVID-19 severity, including the dysregulation of JAK/STAT, MAPK/mTOR, and nuclear factor κB (NF-κB) immune signaling networks in addition to recapitulating known hallmarks of COVID-19. These results provide a set of early determinants of COVID-19 severity that may point to therapeutic targets for prevention and/or treatment of COVID-19 progression.

Signature for Pain Recovery IN Teens (SPRINT): protocol for a multisite prospective signature study in chronic musculoskeletal pain

INTRODUCTION

Current treatments for chronic musculoskeletal (MSK) pain are suboptimal. Discovery of robust prognostic markers separating patients who recover from patients with persistent pain and disability is critical for developing patient-specific treatment strategies and conceiving novel approaches that benefit all patients. Given that chronic pain is a biopsychosocial process, this study aims to discover and validate a robust prognostic signature that measures across multiple dimensions in the same adolescent patient cohort with a computational analysis pipeline. This will facilitate risk stratification in adolescent patients with chronic MSK pain and more resourceful allocation of patients to costly and potentially burdensome multidisciplinary pain treatment approaches.

METHODS AND ANALYSIS

Here we describe a multi-institutional effort to collect, curate and analyse a high dimensional data set including epidemiological, psychometric, quantitative sensory, brain imaging and biological information collected over the course of 12 months. The aim of this effort is to derive a multivariate model with strong prognostic power regarding the clinical course of adolescent MSK pain and function.

ETHICS AND DISSEMINATION

The study complies with the National Institutes of Health policy on the use of a single internal review board (sIRB) for multisite research, with Cincinnati Children's Hospital Medical Center Review Board as the reviewing IRB. Stanford's IRB is a relying IRB within the sIRB. As foreign institutions, the University of Toronto and The Hospital for Sick Children (SickKids) are overseen by their respective ethics boards. All participants provide signed informed consent. We are committed to open-access publication, so that patients, clinicians and scientists have access to the study data and the signature(s) derived. After findings are published, we will upload a limited data set for sharing with other investigators on applicable repositories.

TRIAL REGISTRATION NUMBER

NCT04285112.

Opportunities and challenges of physiologically based pharmacokinetic modeling in drug delivery

Physiologically based pharmacokinetic (PBPK) modeling is an important in silico tool to bridge drug properties and in vivo PK behaviors during drug development. Over the recent decade, the PBPK method has been largely applied to drug delivery systems (DDS), including oral, inhaled, transdermal, ophthalmic, and complex injectable products. The related therapeutic agents have included small-molecule drugs, therapeutic proteins, nucleic acids, and even cells. Simulation results have provided important insights into PK behaviors of new dosage forms, which strongly support drug regulation. In this review, we comprehensively summarize recent progress in PBPK applications in drug delivery, which shows large opportunities for facilitating drug development. In addition, we discuss the challenges of applying this methodology from a practical viewpoint.

Analysis of Half a Billion Datapoints Across Ten Machine-Learning Algorithms Identifies Key Elements Associated With Insulin Transcription in Human Pancreatic Islet Cells

Machine learning (ML)-workflows enable unprejudiced/robust evaluation of complex datasets. Here, we analyzed over 490,000,000 data points to compare 10 different ML-workflows in a large (N=11,652) training dataset of human pancreatic single-cell (sc-)transcriptomes to identify genes associated with the presence or absence of insulin transcript(s). Prediction accuracy/sensitivity of each ML-workflow was tested in a separate validation dataset (N=2,913). Ensemble ML-workflows, in particular Random Forest ML-algorithm delivered high predictive power (AUC=0.83) and sensitivity (0.98), compared to other algorithms. The transcripts identified through these analyses also demonstrated significant correlation with insulin in bulk RNA-seq data from human islets. The top-10 features, (including IAPP, ADCYAP1, LDHA and SST) common to the three Ensemble ML-workflows were significantly dysregulated in scRNA-seq datasets from Ire-1αβ-/- mice that demonstrate dedifferentiation of pancreatic β-cells in a model of type 1 diabetes (T1D) and in pancreatic single cells from individuals with type 2 Diabetes (T2D). Our findings provide direct comparison of ML-workflows in big data analyses, identify key elements associated with insulin transcription and provide workflows for future analyses.

Adenoviral delivery of an immunomodulatory protein to the tumor microenvironment controls tumor growth

Targeted modulation of the immune system against tumors can achieve responses in otherwise refractory cancers, which has spurred efforts aimed at optimizing such strategies. To this end, we have previously investigated cancer immunotherapy approaches using recombinant adenovirus vectors, as well as via modulation of the self-ligand receptor SLAMF7. Here, we present a gene transfer-based immunotherapy approach using targeted expression of a SLAMF7-Fc fusion construct directly into tumors at high concentrations via a recombinant adenoviral vector (Ad-SF7-Fc). Using multiple murine cancer models, we show that Ad-SF7-Fc can induce tumor control via augmentation of innate immunity; specifically, induction of type I interferons and activation of dendritic cells (DCs) and macrophages. Analogously, we find that modulating SLAMF7 signaling via an adenoviral vector expressing its intracellular adaptor, EAT-2, is also capable of inducing tumor control. Finally, we employ a novel in vivo prediction approach and dataset integration with machine learning to dissect how Ad-SF7-Fc modulates cell-type-specific responses in the tumor microenvironment to achieve tumor control. Thus, our novel combinatorial cancer immunotherapy highlights the benefit of multimodal immune modulation and lays a framework for combination with complementary approaches capable of inducing adaptive immune responses.

Integrated Single-cell and Plasma Proteomic Modeling to Predict Surgical Site Complications: A Prospective Cohort Study

OBJECTIVE

The aim of this study was to determine whether single-cell and plasma proteomic elements of the host's immune response to surgery accurately identify patients who develop a surgical site complication (SSC) after major abdominal surgery.

SUMMARY BACKGROUND DATA

SSCs may occur in up to 25% of patients undergoing bowel resection, resulting in significant morbidity and economic burden. However, the accurate prediction of SSCs remains clinically challenging. Leveraging high-content proteomic technologies to comprehensively profile patients' immune response to surgery is a promising approach to identify predictive biological factors of SSCs.

METHODS

Forty-one patients undergoing non-cancer bowel resection were prospectively enrolled. Blood samples collected before surgery and on postoperative day one (POD1) were analyzed using a combination of single-cell mass cytometry and plasma proteomics. The primary outcome was the occurrence of an SSC, including surgical site infection, anastomotic leak, or wound dehiscence within 30 days of surgery.

RESULTS

A multiomic model integrating the single-cell and plasma proteomic data collected on POD1 accurately differentiated patients with (n = 11) and without (n = 30) an SSC [area under the curve (AUC) = 0.86]. Model features included coregulated proinflammatory (eg, IL-6- and MyD88- signaling responses in myeloid cells) and immunosuppressive (eg, JAK/STAT signaling responses in M-MDSCs and Tregs) events preceding an SSC. Importantly, analysis of the immunological data obtained before surgery also yielded a model accurately predicting SSCs (AUC = 0.82).

CONCLUSIONS

The multiomic analysis of patients' immune response after surgery and immune state before surgery revealed systemic immune signatures preceding the development of SSCs. Our results suggest that integrating immunological data in perioperative risk assessment paradigms is a plausible strategy to guide individualized clinical care.

Immunotoxicity of nanomaterials in health and disease: Current challenges and emerging approaches for identifying immune modifiers in susceptible populations

Nanosafety assessment has experienced an intense era of research during the past decades driven by a vivid interest of regulators, industry, and society. Toxicological assays based on in vitro cellular models have undergone an evolution from experimentation using nanoparticulate systems on singular epithelial cell models to employing advanced complex models more realistically mimicking the respective body barriers for analyzing their capacity to alter the immune state of exposed individuals. During this phase, a number of lessons were learned. We have thus arrived at a state where the next chapters have to be opened, pursuing the following objectives: (1) to elucidate underlying mechanisms, (2) to address effects on vulnerable groups, (3) to test material mixtures, and (4) to use realistic doses on (5) sophisticated models. Moreover, data reproducibility has become a significant demand. In this context, we studied the emerging concept of adverse outcome pathways (AOPs) from the perspective of immune activation and modulation resulting in pro-inflammatory versus tolerogenic responses. When considering the interaction of nanomaterials with biological systems, protein corona formation represents the relevant molecular initiating event (e.g., by potential alterations of nanomaterial-adsorbed proteins). Using this as an example, we illustrate how integrated experimental-computational workflows combining in vitro assays with in silico models aid in data enrichment and upon comprehensive ontology-annotated (meta)data upload to online repositories assure FAIRness (Findability, Accessibility, Interoperability, Reusability). Such digital twinning may, in future, assist in early-stage decision-making during therapeutic development, and hence, promote safe-by-design innovation in nanomedicine. Moreover, it may, in combination with in silico-based exposure-relevant dose-finding, serve for risk monitoring in particularly loaded areas, for example, workplaces, taking into account pre-existing health conditions. This article is categorized under: Toxicology and Regulatory Issues in Nanomedicine > Toxicology of Nanomaterials.

Single-synapse analyses of Alzheimer's disease implicate pathologic tau, DJ1, CD47, and ApoE

Synaptic molecular characterization is limited for Alzheimer’s disease (AD). Our newly invented mass cytometry–based method, synaptometry by time of flight (SynTOF), was used to measure 38 antibody probes in approximately 17 million single-synapse events from human brains without pathologic change or with pure AD or Lewy body disease (LBD), nonhuman primates (NHPs), and PS/APP mice. Synaptic molecular integrity in humans and NHP was similar. Although not detected in human synapses, Aβ was in PS/APP mice single-synapse events. Clustering and pattern identification of human synapses showed expected disease-specific differences, like increased hippocampal pathologic tau in AD and reduced caudate dopamine transporter in LBD, and revealed previously unidentified findings including increased hippocampal CD47 and lowered DJ1 in AD and higher ApoE in AD with dementia. Our results were independently supported by multiplex ion beam imaging of intact tissue. This highlights the higher depth and breadth of insight on neurodegenerative diseases obtainable through SynTOF.

Measuring the human immune response to surgery: multiomics for the prediction of postoperative outcomes

PURPOSE OF REVIEW

Postoperative complications including infections, cognitive impairment, and protracted recovery occur in one-third of the 300 million surgeries performed annually worldwide. Complications cause personal suffering along with a significant economic burden on our healthcare system. However, the accurate prediction of postoperative complications and patient-targeted interventions for their prevention remain as major clinical challenges.

RECENT FINDINGS

Although multifactorial in origin, the dysregulation of immunological mechanisms that occur in response to surgical trauma is a key determinant of postoperative complications. Prior research, primarily focusing on inflammatory plasma markers, has provided important clues regarding their pathogenesis. However, the recent advent of high-content, single-cell transcriptomic, and proteomic technologies has considerably improved our ability to characterize the immune response to surgery, thereby providing new means to understand the immunological basis of postoperative complications and to identify prognostic biological signatures.

SUMMARY

The comprehensive and single-cell characterization of the human immune response to surgery has significantly advanced our ability to predict the risk of postoperative complications. Multiomic modeling of patients' immune states holds promise for the discovery of preoperative predictive biomarkers, ultimately providing patients and surgeons with actionable information to improve surgical outcomes. Although recent studies have generated a wealth of knowledge, laying the foundation for a single-cell atlas of the human immune response to surgery, larger-scale multiomic studies are required to derive robust, scalable, and sufficiently powerful models to accurately predict the risk of postoperative complications in individual patients.

Harnessing the Potential of Multiomics Studies for Precision Medicine in Infectious Disease

The field of infectious diseases currently takes a reactive approach and treats infections as they present in patients. Although certain populations are known to be at greater risk of developing infection (eg, immunocompromised), we lack a systems approach to define the true risk of future infection for a patient. Guided by impressive gains in "omics" technologies, future strategies to infectious diseases should take a precision approach to infection through identification of patients at intermediate and high-risk of infection and deploy targeted preventative measures (ie, prophylaxis). The advances of high-throughput immune profiling by multiomics approaches (ie, transcriptomics, epigenomics, metabolomics, proteomics) hold the promise to identify patients at increased risk of infection and enable risk-stratifying approaches to be applied in the clinic. Integration of patient-specific data using machine learning improves the effectiveness of prediction, providing the necessary technologies needed to propel the field of infectious diseases medicine into the era of personalized medicine.

Support vector machine-based prediction of pore-forming toxins (PFT) using distributed representation of reduced alphabets

Bacterial virulence can be attributed to a wide variety of factors including toxins that harm the host. Pore-forming toxins are one class of toxins that confer virulence to the bacteria and are one of the promising targets for therapeutic intervention. In this work, we develop a sequence-based machine learning framework for the prediction of pore-forming toxins. For this, we have used distributed representation of the protein sequence encoded by reduced alphabet schemes based on conformational similarity and hydropathy index as input features to Support Vector Machines (SVMs). The choice of conformational similarity and hydropathy indices is based on the functional mechanism of pore-forming toxins. Our methodology achieves about 81% accuracy indicating that conformational similarity, an indicator of the flexibility of amino acids, along with hydrophobic index can capture the intrinsic features of pore-forming toxins that distinguish it from other types of transporter proteins. Increased understanding of the mechanisms of pore-forming toxins can further contribute to the use of such "mechanism-informed" features that may increase the prediction accuracy further.

Informed Attentive Predictors: A Generalisable Architecture for Prior Knowledge-Based Assisted Diagnosis of Cancers

Due to the high mortality of many cancers and their related diseases, the prediction and prognosis techniques of cancers are being extensively studied to assist doctors in making diagnoses. Many machine-learning-based cancer predictors have been put forward, but many of them have failed to become widely utilised due to some crucial problems. For example, most methods require too much training data, which is not always applicable to institutes, and the complicated genetic mutual effects of cancers are generally ignored in many proposed methods. Moreover, a majority of these assist models are actually not safe to use, as they are generally built on black-box machine learners that lack references from related field knowledge. We observe that few machine-learning-based cancer predictors are capable of employing prior knowledge (PrK) to mitigate these issues. Therefore, in this paper, we propose a generalisable informed machine learning architecture named the Informed Attentive Predictor (IAP) to make PrK available to the predictor’s decision-making phases and apply it to the field of cancer prediction. Specifically, we make several implementations of the IAP and evaluate its performance on six TCGA datasets to demonstrate the effectiveness of our architecture as an assist system framework for actual clinical usage. The experimental results show a noticeable improvement in IAP models on accuracies, f1-scores and recall rates compared to their non-IAP counterparts (i.e., basic predictors).

A Peripheral Immune Signature of Labor Induction

Approximately 1 in 4 pregnant women in the United States undergo labor induction. The onset and establishment of labor, particularly induced labor, is a complex and dynamic process influenced by multiple endocrine, inflammatory, and mechanical factors as well as obstetric and pharmacological interventions. The duration from labor induction to the onset of active labor remains unpredictable. Moreover, prolonged labor is associated with severe complications for the mother and her offspring, most importantly chorioamnionitis, uterine atony, and postpartum hemorrhage. While maternal immune system adaptations that are critical for the maintenance of a healthy pregnancy have been previously characterized, the role of the immune system during the establishment of labor is poorly understood. Understanding maternal immune adaptations during labor initiation can have important ramifications for predicting successful labor induction and labor complications in both induced and spontaneous types of labor. The aim of this study was to characterize labor-associated maternal immune system dynamics from labor induction to the start of active labor. Serial blood samples from fifteen participants were collected immediately prior to labor induction (baseline) and during the latent phase until the start of active labor. Using high-dimensional mass cytometry, a total of 1,059 single-cell immune features were extracted from each sample. A multivariate machine-learning method was employed to characterize the dynamic changes of the maternal immune system after labor induction until the establishment of active labor. A cross-validated linear sparse regression model (least absolute shrinkage and selection operator, LASSO) predicted the minutes since induction of labor with high accuracy (R = 0.86, p = 6.7e-15, RMSE = 277 min). Immune features most informative for the model included STAT5 signaling in central memory CD8⁺ T cells and pro-inflammatory STAT3 signaling responses across multiple adaptive and innate immune cell subsets. Our study reports a peripheral immune signature of labor induction, and provides important insights into biological mechanisms that may ultimately predict labor induction success as well as complications, thereby facilitating clinical decision-making to improve maternal and fetal well-being.

Single-Cell Analysis of the Neonatal Immune System Across the Gestational Age Continuum

Although most causes of death and morbidity in premature infants are related to immune maladaptation, the premature immune system remains poorly understood. We provide a comprehensive single-cell depiction of the neonatal immune system at birth across the spectrum of viable gestational age (GA), ranging from 25 weeks to term. A mass cytometry immunoassay interrogated all major immune cell subsets, including signaling activity and responsiveness to stimulation. An elastic net model described the relationship between GA and immunome (R=0.85, p=8.75e-14), and unsupervised clustering highlighted previously unrecognized GA-dependent immune dynamics, including decreasing basal MAP-kinase/NFκB signaling in antigen presenting cells; increasing responsiveness of cytotoxic lymphocytes to interferon-α; and decreasing frequency of regulatory and invariant T cells, including NKT-like cells and CD8⁺CD161⁺ T cells. Knowledge gained from the analysis of the neonatal immune landscape across GA provides a mechanistic framework to understand the unique susceptibility of preterm infants to both hyper-inflammatory diseases and infections.

Radiomics-informed Deep Curriculum Learning for Breast Cancer Diagnosis

Convolutional Neural Networks (CNNs) are traditionally trained solely using the given imaging dataset. Additional clinical information is often available along with imaging data but is mostly ignored in the current practice of data-driven deep learning modeling. In this work, we propose a novel deep curriculum learning method that utilizes radiomics information as a source of additional knowledge to guide training using customized curriculums. Specifically, we define a new measure, termed radiomics score, to capture the difficulty of classifying a set of samples. We use the radiomics score to enable a newly designed curriculum-based training scheme. In this scheme, the loss function component is weighted and initialized by the corresponding radiomics score of each sample, and furthermore, the weights are continuously updated in the course of training based on our customized curriculums to enable curriculum learning. We implement and evaluate our methods on a typical computer-aided diagnosis of breast cancer. Our experiment results show benefits of the proposed method when compared to a direct use of radiomics model, a baseline CNN without using any knowledge, the standard curriculum learning using data resampling, an existing difficulty score from self-teaching, and previous methods that use radiomics features as additional input to CNN models.