ABSTRACT
Artificial intelligence (AI) and machine learning (ML) research within medicine has been exponentially increasing 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 utilization of larger electronic health record (EHR) datasets, 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 (CDSS) to refine the diagnosis and management of IEI.
ABSTRACT
Solid tumors harbor immunosuppressive microenvironments that inhibit tumor infiltrating lymphocytes (TILs) through the voracious consumption of glucose. We sought to restore TIL function by providing them with an exclusive fuel source. The glucose disaccharide cellobiose, which is a building block of cellulose, contains a ß-1,4-glycosidic bond that cannot be hydrolyzed by animals (or their tumors), but fungal and bacterial organisms have evolved enzymes to catabolize cellobiose and use the resulting glucose. By equipping T cells with two proteins that enable import and hydrolysis of cellobiose, we demonstrate that supplementation of cellobiose during glucose withdrawal restores T cell cytokine production and cellular proliferation. Murine tumor growth is suppressed and survival is prolonged. Offering exclusive access to a natural disaccharide is a new tool that augments cancer immunotherapies. Beyond cancer, this approach could be used to answer questions about the regulation of glucose metabolism across many cell types, biological processes, and diseases.
ABSTRACT
Human inborn errors of immunity include rare disorders entailing functional and quantitative antibody deficiencies due to impaired B cells called the common variable immunodeficiency (CVID) phenotype. Patients with CVID face delayed diagnoses and treatments for 5 to 15 years after symptom onset because the disorders are rare (prevalence of ~1/25,000), and there is extensive heterogeneity in CVID phenotypes, ranging from infections to autoimmunity to inflammatory conditions, overlapping with other more common disorders. The prolonged diagnostic odyssey drives excessive system-wide costs before diagnosis. Because there is no single causal mechanism, there are no genetic tests to definitively diagnose CVID. Here, we present PheNet, a machine learning algorithm that identifies patients with CVID from their electronic health records (EHRs). PheNet learns phenotypic patterns from verified CVID cases and uses this knowledge to rank patients by likelihood of having CVID. PheNet could have diagnosed more than half of our patients with CVID 1 or more years earlier than they had been diagnosed. When applied to a large EHR dataset, followed by blinded chart review of the top 100 patients ranked by PheNet, we found that 74% were highly probable to have CVID. We externally validated PheNet using >6 million records from disparate medical systems in California and Tennessee. As artificial intelligence and machine learning make their way into health care, we show that algorithms such as PheNet can offer clinical benefits by expediting the diagnosis of rare diseases.
Subject(s)
Common Variable Immunodeficiency , Electronic Health Records , Humans , Common Variable Immunodeficiency/diagnosis , Machine Learning , Algorithms , Male , Female , Phenotype , Adult , Undiagnosed Diseases/diagnosisABSTRACT
Activated phosphoinositide 3-kinase delta syndrome (APDS) is an inborn error of immunity with heterogeneous clinical manifestations of infections, immune dysregulation, autoimmunity; lymphoproliferation; and malignancy. Immune complex-mediated vasculitides have not yet been described in APDS patients. Here we offer a case series of three patients with APDS who have refractory IgA vasculitis (also called Henoch-Schönlein purpura), a form of immune complex-mediated vasculitis that activates complement and attracts neutrophils, macrophages and eosinophils to cause local tissue injury. Leniolisib is an inhibitor of PI3K p110δ and an FDA-approved treatment for APDS. IgA vasculitis resolved upon treatment with leniolisib. Patients with immune dysregulation including IgA vasculitis should be screened for APDS.
Subject(s)
Giant Cell Arteritis , Granulomatosis with Polyangiitis , IgA Vasculitis , Mucocutaneous Lymph Node Syndrome , Polyarteritis Nodosa , Pyridines , Pyrimidines , Humans , Antigen-Antibody Complex , Phosphatidylinositol 3-Kinase/therapeutic use , Phosphatidylinositol 3-KinasesABSTRACT
The durability of a protective immune response generated by a vaccine depends on its ability to induce long-term T cell immunity, which tends to decline in aging populations. The longest protection appears to arise from T memory stem cells (TMSCs) that confer high expandability and effector functions when challenged. Here we engineered artificial antigen presenting cells (aAPC) with optimized size, stiffness and activation signals to induce human and mouse CD8+ TMSCs in vitro. This platform was optimized as a vaccine booster of TMSCs (Vax-T) with prolonged release of small-molecule blockade of the glycogen synthase kinase-3ß together with target antigens. By using SARS-CoV-2 antigen as a model, we show that a single injection of Vax-T induces durable antigen-specific CD8+ TMSCs in young and aged mice, and generates humoral responses at a level stronger than or similar to soluble vaccines. This Vax-T approach can boost long-term immunity to fight infectious diseases, cancer, and other diseases.
Subject(s)
CD8-Positive T-Lymphocytes , Vaccines , Mice , Humans , Animals , Immunologic Memory , Biocompatible Materials , Stem CellsABSTRACT
Here, we summarize the proceedings of the inaugural Artificial Intelligence in Primary Immune Deficiencies conference, during which experts and advocates gathered to advance research into the applications of artificial intelligence (AI), machine learning, and other computational tools in the diagnosis and management of inborn errors of immunity (IEIs). The conference focused on the key themes of expediting IEI diagnoses, challenges in data collection, roles of natural language processing and large language models in interpreting electronic health records, and ethical considerations in implementation. Innovative AI-based tools trained on electronic health records and claims databases have discovered new patterns of warning signs for IEIs, facilitating faster diagnoses and enhancing patient outcomes. Challenges in training AIs persist on account of data limitations, especially in cases of rare diseases, overlapping phenotypes, and biases inherent in current data sets. Furthermore, experts highlighted the significance of ethical considerations, data protection, and the necessity for open science principles. The conference delved into regulatory frameworks, equity in access, and the imperative for collaborative efforts to overcome these obstacles and harness the transformative potential of AI. Concerted efforts to successfully integrate AI into daily clinical immunology practice are still needed.
Subject(s)
Artificial Intelligence , Primary Immunodeficiency Diseases , Humans , Machine Learning , Natural Language Processing , Data CollectionABSTRACT
BACKGROUND: Sepsis is a highly heterogeneous syndrome, which has hindered the development of effective therapies. This has prompted investigators to develop a precision medicine approach aimed at identifying biologically homogenous subgroups of patients with septic shock and critical illnesses. Transcriptomic analysis can identify subclasses derived from differences in underlying pathophysiological processes that may provide the basis for new targeted therapies. The goal of this study was to elucidate pathophysiological pathways and identify pediatric septic shock subclasses based on whole blood RNA expression profiles. METHODS: The subjects were critically ill children with cardiopulmonary failure who were a part of a prospective randomized insulin titration trial to treat hyperglycemia. Genome-wide expression profiling was conducted using RNA sequencing from whole blood samples obtained from 46 children with septic shock and 52 mechanically ventilated noninfected controls without shock. Patients with septic shock were allocated to subclasses based on hierarchical clustering of gene expression profiles, and we then compared clinical characteristics, plasma inflammatory markers, cell compositions using GEDIT, and immune repertoires using Imrep between the two subclasses. RESULTS: Patients with septic shock depicted alterations in innate and adaptive immune pathways. Among patients with septic shock, we identified two subtypes based on gene expression patterns. Compared with Subclass 2, Subclass 1 was characterized by upregulation of innate immunity pathways and downregulation of adaptive immunity pathways. Subclass 1 had significantly worse clinical outcomes despite the two classes having similar illness severity on initial clinical presentation. Subclass 1 had elevated levels of plasma inflammatory cytokines and endothelial injury biomarkers and demonstrated decreased percentages of CD4 T cells and B cells and less diverse T cell receptor repertoires. CONCLUSIONS: Two subclasses of pediatric septic shock patients were discovered through genome-wide expression profiling based on whole blood RNA sequencing with major biological and clinical differences. Trial Registration This is a secondary analysis of data generated as part of the observational CAF-PINT ancillary of the HALF-PINT study (NCT01565941). Registered March 29, 2012.
Subject(s)
Sepsis , Shock, Septic , Child , Humans , Gene Expression Profiling , Prospective Studies , Sepsis/genetics , Shock, Septic/therapy , Transcriptome , Randomized Controlled Trials as Topic , Observational Studies as TopicABSTRACT
A wide array of clinical manifestations follow infection with Coccidioides immitis or Coccidioides posadasii, ranging from asymptomatic infection to life-threatening pulmonary disease or extrapulmonary dissemination and meningitis. Epidemiological studies require consistent definitions of cases and their comparative clinical features. Understanding host and pathogen determinants of the severity of coccidioidomycosis also requires that specific clinical features (such as coccidioidal meningitis) and their overlap be precisely defined and quantified. Here we propose a system for categorization of outcomes of coccidioidomycosis in individuals who are not overtly immunocompromised that harmonizes clinical assessments during translational research of this increasingly common disease.
ABSTRACT
Background: Sepsis is a highly heterogeneous syndrome, that has hindered the development of effective therapies. This has prompted investigators to develop a precision medicine approach aimed at identifying biologically homogenous subgroups of patients with septic shock and critical illnesses. Transcriptomic analysis can identify subclasses derived from differences in underlying pathophysiological processes that may provide the basis for new targeted therapies. The goal of this study was to elucidate pathophysiological pathways and identify pediatric septic shock subclasses based on whole blood RNA expression profiles. Methods: The subjects were critically ill children with cardiopulmonary failure who were a part of a prospective randomized insulin titration trial to treat hyperglycemia. Genome-wide expression profiling was conducted using RNA-sequencing from whole blood samples obtained from 46 children with septic shock and 52 mechanically ventilated noninfected controls without shock. Patients with septic shock were allocated to subclasses based on hierarchical clustering of gene expression profiles, and we then compared clinical characteristics, plasma inflammatory markers, cell compositions using GEDIT, and immune repertoires using Imrep between the two subclasses. Results: Patients with septic shock depicted alterations in innate and adaptive immune pathways. Among patients with septic shock, we identified two subtypes based on gene expression patterns. Compared with Subclass 2, Subclass 1 was characterized by upregulation of innate immunity pathways and downregulation of adaptive immunity pathways. Subclass 1 had significantly worse clinical outcomes despite the two classes having similar illness severity on initial clinical presentation. Subclass 1 had elevated levels of plasma inflammatory cytokines and endothelial injury biomarkers and demonstrated decreased percentages of CD4 T cells and B cells, and less diverse T-Cell receptor repertoires. Conclusions: Two subclasses of pediatric septic shock patients were discovered through genome-wide expression profiling based on whole blood RNA sequencing with major biological and clinical differences. Trial Registration: This is a secondary analysis of data generated as part of the observational CAF PINT ancillary of the HALF PINT study (NCT01565941). Registered 29 March 2012.
ABSTRACT
A tumour microenvironment abundant in regulatory T (Treg) cells aids solid tumours to evade clearance by effector T cells. Systemic strategies to suppress Treg cells or to augment immunity can elicit autoimmune side effects, cytokine storms and other toxicities. Here we report the design, fabrication and therapeutic performance of a biodegradable macroporous scaffold, implanted peritumourally, that releases a small-molecule inhibitor of transforming growth factor ß to suppress Treg cells, chemokines to attract effector T cells and antibodies to stimulate them. In two mouse models of aggressive tumours, the implant boosted the recruitment and activation of effector T cells into the tumour and depleted it of Treg cells, which resulted in an 'immunological abscopal effect' on distant metastases and in the establishment of long-term memory that impeded tumour recurrence. We also show that the scaffold can be used to deliver tumour-antigen-specific T cells into the tumour. Peritumourally implanted immunomodulatory scaffolds may represent a general strategy to enhance T-cell immunity and avoid the toxicities of systemic therapies.
Subject(s)
Neoplasms , T-Lymphocytes, Regulatory , Mice , Animals , Immunity , Neoplasms/therapy , Antigens, Neoplasm/metabolism , Disease Models, Animal , Tumor MicroenvironmentABSTRACT
Immune responses are governed by signals from the tissue microenvironment, and in addition to biochemical signals, mechanical cues and forces arising from the tissue, its extracellular matrix and its constituent cells shape immune cell function. Indeed, changes in biophysical properties of tissue alter the mechanical signals experienced by cells in many disease conditions, in inflammatory states and in the context of ageing. These mechanical cues are converted into biochemical signals through the process of mechanotransduction, and multiple pathways of mechanotransduction have been identified in immune cells. Such pathways impact important cellular functions including cell activation, cytokine production, metabolism, proliferation and trafficking. Changes in tissue mechanics may also represent a new form of 'danger signal' that alerts the innate and adaptive immune systems to the possibility of injury or infection. Tissue mechanics can change temporally during an infection or inflammatory response, offering a novel layer of dynamic immune regulation. Here, we review the emerging field of mechanoimmunology, focusing on how mechanical cues at the scale of the tissue environment regulate immune cell behaviours to initiate, propagate and resolve the immune response.
Subject(s)
Extracellular Matrix , Mechanotransduction, Cellular , Humans , Extracellular Matrix/metabolismABSTRACT
BACKGROUND: Large medical centers in urban areas, like Los Angeles, care for a diverse patient population and offer the potential to study the interplay between genetic ancestry and social determinants of health. Here, we explore the implications of genetic ancestry within the University of California, Los Angeles (UCLA) ATLAS Community Health Initiative-an ancestrally diverse biobank of genomic data linked with de-identified electronic health records (EHRs) of UCLA Health patients (N=36,736). METHODS: We quantify the extensive continental and subcontinental genetic diversity within the ATLAS data through principal component analysis, identity-by-descent, and genetic admixture. We assess the relationship between genetically inferred ancestry (GIA) and >1500 EHR-derived phenotypes (phecodes). Finally, we demonstrate the utility of genetic data linked with EHR to perform ancestry-specific and multi-ancestry genome and phenome-wide scans across a broad set of disease phenotypes. RESULTS: We identify 5 continental-scale GIA clusters including European American (EA), African American (AA), Hispanic Latino American (HL), South Asian American (SAA) and East Asian American (EAA) individuals and 7 subcontinental GIA clusters within the EAA GIA corresponding to Chinese American, Vietnamese American, and Japanese American individuals. Although we broadly find that self-identified race/ethnicity (SIRE) is highly correlated with GIA, we still observe marked differences between the two, emphasizing that the populations defined by these two criteria are not analogous. We find a total of 259 significant associations between continental GIA and phecodes even after accounting for individuals' SIRE, demonstrating that for some phenotypes, GIA provides information not already captured by SIRE. GWAS identifies significant associations for liver disease in the 22q13.31 locus across the HL and EAA GIA groups (HL p-value=2.32×10-16, EAA p-value=6.73×10-11). A subsequent PheWAS at the top SNP reveals significant associations with neurologic and neoplastic phenotypes specifically within the HL GIA group. CONCLUSIONS: Overall, our results explore the interplay between SIRE and GIA within a disease context and underscore the utility of studying the genomes of diverse individuals through biobank-scale genotyping linked with EHR-based phenotyping.
Subject(s)
Electronic Health Records , Public Health , Asian People , Biological Specimen Banks , Genomics , HumansABSTRACT
The recombination-activating genes (RAG) 1 and 2 are indispensable for diversifying the primary B cell receptor repertoire and pruning self-reactive clones via receptor editing in the bone marrow; however, the impact of RAG1/RAG2 on peripheral tolerance is unknown. Partial RAG deficiency (pRD) manifesting with late-onset immune dysregulation represents an 'experiment of nature' to explore this conundrum. By studying B cell development and subset-specific repertoires in pRD, we demonstrate that reduced RAG activity impinges on peripheral tolerance through the generation of a restricted primary B cell repertoire, persistent antigenic stimulation and an inflammatory milieu with elevated B cell-activating factor. This unique environment gradually provokes profound B cell dysregulation with widespread activation, remarkable extrafollicular maturation and persistence, expansion and somatic diversification of self-reactive clones. Through the model of pRD, we reveal a RAG-dependent 'domino effect' that impacts stringency of tolerance and B cell fate in the periphery.
Subject(s)
B-Lymphocytes , DNA-Binding Proteins , Homeodomain Proteins , Nuclear Proteins , Cell Differentiation , DNA-Binding Proteins/deficiency , DNA-Binding Proteins/genetics , Homeodomain Proteins/genetics , Humans , Immune Tolerance , Lymphocyte Count , Nuclear Proteins/deficiencyABSTRACT
Endothelial progenitor cells (EPCs) contribute to de novo angiogenesis, tissue regeneration, and remodeling. Interleukin 10 (IL-10), an anti-inflammatory cytokine that primarily signals via STAT3, has been shown to drive EPC recruitment to injured tissues. Our previous work demonstrated that overexpression of IL-10 in dermal wounds promotes regenerative tissue repair via STAT3-dependent regulation of fibroblast-specific hyaluronan synthesis. However, IL-10's role and specific mode of action on EPC recruitment, particularly in dermal wound healing and neovascularization in both normal and diabetic wounds, remain to be defined. Therefore, inducible skin-specific STAT3 knockdown mice were studied to determine IL-10's impact on EPCs, dermal wound neovascularization and healing, and whether it is STAT3-dependent. We show that IL-10 overexpression significantly elevated EPC counts in the granulating wound bed, which was associated with robust capillary lumen density and enhanced re-epithelialization of both control and diabetic (db/db) wounds at day 7. We noted increased VEGF and high C-X-C motif chemokine 12 (CXCL12) levels in wounds and a favorable CXCL12 gradient at day 3 that may support EPC mobilization and infiltration from bone marrow to wounds, an effect that was abrogated in STAT3 knockdown wounds. These findings were supported in vitro. IL-10 promoted VEGF and CXCL12 synthesis in primary murine dermal fibroblasts, with blunted VEGF expression upon blocking CXCL12 in the media by antibody binding. IL-10-conditioned fibroblast media also significantly promoted endothelial sprouting and network formation. In conclusion, these studies demonstrate that overexpression of IL-10 in dermal wounds recruits EPCs and leads to increased vascular structures and faster re-epithelialization.
Subject(s)
Diabetes Mellitus , Endothelial Progenitor Cells , Interleukin-10/metabolism , Animals , Culture Media, Conditioned/metabolism , Diabetes Mellitus/metabolism , Endothelial Progenitor Cells/metabolism , Interleukin-10/genetics , Mice , Neovascularization, Physiologic/physiology , STAT3 Transcription Factor/metabolism , Vascular Endothelial Growth Factor A/metabolism , Wound Healing/physiologyABSTRACT
Periodontal diseases are caused by microbial infection and the recruitment of destructive immune cells. Current therapies mainly deal with bacteria elimination, but the regeneration of periodontal tissues remains a challenge. Here we developed a modular microneedle (MN) patch that delivered both antibiotic and cytokines into the local gingival tissue to achieve immunomodulation and tissue regeneration. This MN patch included a quickly dissolvable gelatin membrane for an immediate release of tetracycline and biodegradable GelMA MNs that contained tetracycline-loaded poly(lactic-co-glycolic acid) nanoparticles and cytokine-loaded silica microparticles for a sustained release. Antibiotic release completely inhibited bacteria growth, and the release of IL-4 and TGF-ß induced the repolarization of anti-inflammatory macrophages and the formation of regulatory T cells in vitro. In vivo delivery of MN patch into periodontal tissues suppressed proinflammatory factors and promoted pro-regenerative signals and tissue healing, which demonstrated the therapeutic potential of local immunomodulation for tissue regeneration.