scholarly journals Machine learning identifies the immunological signature of Juvenile Idiopathic Arthritis

2018 ◽  
Author(s):  
Erika Van Nieuwenhove ◽  
Vasiliki Lagou ◽  
Lien Van Eyck ◽  
James Dooley ◽  
Ulrich Bodenhofer ◽  
...  
Keyword(s):  
Machine Learning ◽  
Juvenile Idiopathic Arthritis ◽  
Large Scale ◽  
Inflammatory Diseases ◽  
Adaptive Immune System ◽  
Healthy Children ◽  
Adaptive Immune ◽  
Systemic Jia ◽  
Response Group ◽  
Learning Analysis

AbstractJuvenile idiopathic arthritis (JIA) is the most common childhood rheumatic disease, with a strongly debated pathophysiological origin. Both adaptive and innate immune processes have been proposed as primary drivers, which may account for the observed clinical heterogeneity, but few high-depth studies have been performed. Here we profiled the adaptive immune system of 85 JIA patients and 43 age-matched controls, identifying immunological changes unique to JIA and others common across a broad spectrum of childhood inflammatory diseases. The JIA immune signature was shared between clinically distinct subsets, but was accentuated in the systemic JIA patients and those patients with active disease. Despite the extensive overlap in the immunological spectrum exhibited by healthy children and JIA patients, machine learning analysis of the dataset proved capable of diagnosis of JIA patients with ~90% accuracy. These results pave the way for large-scale longitudinal studies of JIA, where machine learning could be used to predict immune signatures that correspond to treatment response group.

Machine learning identifies an immunological pattern associated with multiple juvenile idiopathic arthritis subtypes

2019 ◽  
Vol 78 (5) ◽  
pp. 617-628 ◽  
Author(s):  
Erika Van Nieuwenhove ◽  
Vasiliki Lagou ◽  
Lien Van Eyck ◽  
James Dooley ◽  
Ulrich Bodenhofer ◽  
...  
Keyword(s):  
Machine Learning ◽  
Juvenile Idiopathic Arthritis ◽  
Large Scale ◽  
Inflammatory Diseases ◽  
Adaptive Immune System ◽  
Healthy Children ◽  
Learning Approaches ◽  
Data Set ◽  
Immune Signature ◽  
Systemic Jia

ObjectivesJuvenile idiopathic arthritis (JIA) is the most common class of childhood rheumatic diseases, with distinct disease subsets that may have diverging pathophysiological origins. Both adaptive and innate immune processes have been proposed as primary drivers, which may account for the observed clinical heterogeneity, but few high-depth studies have been performed.MethodsHere we profiled the adaptive immune system of 85 patients with JIA and 43 age-matched controls with indepth flow cytometry and machine learning approaches.ResultsImmune profiling identified immunological changes in patients with JIA. This immune signature was shared across a broad spectrum of childhood inflammatory diseases. The immune signature was identified in clinically distinct subsets of JIA, but was accentuated in patients with systemic JIA and those patients with active disease. Despite the extensive overlap in the immunological spectrum exhibited by healthy children and patients with JIA, machine learning analysis of the data set proved capable of discriminating patients with JIA from healthy controls with ~90% accuracy.ConclusionsThese results pave the way for large-scale immune phenotyping longitudinal studies of JIA. The ability to discriminate between patients with JIA and healthy individuals provides proof of principle for the use of machine learning to identify immune signatures that are predictive to treatment response group.

scholarly journals immuneML: an ecosystem for machine learning analysis of adaptive immune receptor repertoires

2021 ◽  
Author(s):  
Milena Pavlović ◽  
Lonneke Scheffer ◽  
Keshav Motwani ◽  
Chakravarthi Kanduri ◽  
Radmila Kompova ◽  
...  
Keyword(s):  
Machine Learning ◽  
Large Scale ◽  
Antigen Specificity ◽  
Immune Receptor ◽  
Adaptive Immune ◽  
User Adoption ◽  
Extensive Documentation ◽  
Command Line Tool ◽  
Novel Method ◽  
Learning Analysis

AbstractAdaptive immune receptor repertoires (AIRR) are key targets for biomedical research as they record past and ongoing adaptive immune responses. The capacity of machine learning (ML) to identify complex discriminative sequence patterns renders it an ideal approach for AIRR-based diagnostic and therapeutic discovery. To date, widespread adoption of AIRR ML has been inhibited by a lack of reproducibility, transparency, and interoperability. immuneML (immuneml.uio.no) addresses these concerns by implementing each step of the AIRR ML process in an extensible, open-source software ecosystem that is based on fully specified and shareable workflows. To facilitate widespread user adoption, immuneML is available as a command-line tool and through an intuitive Galaxy web interface, and extensive documentation of workflows is provided. We demonstrate the broad applicability of immuneML by (i) reproducing a large-scale study on immune state prediction, (ii) developing, integrating, and applying a novel method for antigen specificity prediction, and (iii) showcasing streamlined interpretability-focused benchmarking of AIRR ML.

scholarly journals PPARγAgonists in Adaptive Immunity: What Do Immune Disorders and Their Models Have to Tell Us?

PPAR Research ◽  
2013 ◽  
Vol 2013 ◽  
pp. 1-9 ◽  
Author(s):  
Laurindo Ferreira da Rocha Junior ◽  
Andréa Tavares Dantas ◽  
Ângela Luzia Branco Pinto Duarte ◽  
Moacyr Jesus Barreto de Melo Rego ◽  
Ivan da Rocha Pitta ◽  
...  
Keyword(s):  
Adaptive Immunity ◽  
Inflammatory Diseases ◽  
Cell Lineage ◽  
Adaptive Immune System ◽  
Innate And Adaptive Immunity ◽  
Adaptive Immune ◽  
Cytokines And Chemokines ◽  
Autoimmune And Inflammatory Diseases ◽  
Ppar Agonists ◽  
T Cell Survival

Adaptive immunity has evolved as a very powerful and highly specialized tool of host defense. Its classical protagonists are lymphocytes of the T- and B-cell lineage. Cytokines and chemokines play a key role as effector mechanisms of the adaptive immunity. Some autoimmune and inflammatory diseases are caused by disturbance of the adaptive immune system. Recent advances in understanding the pathogenesis of autoimmune diseases have led to research on new molecular and therapeutic targets. PPARγare members of the nuclear receptor superfamily and are transcription factors involved in lipid metabolism as well as innate and adaptive immunity. PPARγis activated by synthetic and endogenous ligands. Previous studies have shown that PPAR agonists regulate T-cell survival, activation and T helper cell differentiation into effector subsets: Th1, Th2, Th17, and Tregs. PPARγhas also been associated with B cells. The present review addresses these issues by placing PPARγagonists in the context of adaptive immune responses and the relation of the activation of these receptors with the expression of cytokines involved in adaptive immunity.

Abnormal expression of the genes involved in cytokine networks and mitochondrial function in systemic juvenile idiopathic arthritis identified by DNA microarray analysis

2008 ◽  
Vol 68 (2) ◽  
pp. 264-272 ◽  
Author(s):  
S Ishikawa ◽  
T Mima ◽  
C Aoki ◽  
N Yoshio-Hoshino ◽  
Y Adachi ◽  
...  
Keyword(s):  
Gene Ontology ◽  
Juvenile Idiopathic Arthritis ◽  
Nuclear Dna ◽  
Mitochondrial Disorder ◽  
Systemic Juvenile Idiopathic Arthritis ◽  
Defence Response ◽  
Differentially Expressed ◽  
Healthy Children ◽  
Peripheral Leukocytes ◽  
Response Group

Objectives:Systemic juvenile idiopathic arthritis (sJIA) is a rheumatic disease in childhood characterised by systemic symptoms and a relatively poor prognosis. Peripheral leukocytes are thought to play a pathological role in sJIA although the exact cause of the disease is still obscure. In this study, we aimed to clarify cellular functional abnormalities in sJIA.Methods:We analysed the gene expression profile in peripheral leukocytes from 51 patients with sJIA, 6 patients with polyarticular type JIA (polyJIA) and 8 healthy children utilising DNA microarrays. Gene ontology analysis and network analysis were performed on the genes differentially expressed in sJIA to clarify the cellular functional abnormalities.Result:A total of 3491 genes were differentially expressed in patients with sJIA compared to healthy individuals. They were functionally categorised mainly into a defence response group and a metabolism group according to gene ontology, suggesting the possible abnormalities in these functions. In the defence response group, molecules predominantly constituting interferon (IFN)γ and tumour necrosis factor (TNF) network cascades were upregulated. In the metabolism group, oxidative phosphorylation-related genes were downregulated, suggesting a mitochondrial disorder. Expression of mitochondrial DNA-encoded genes including cytochrome c oxidase subunit 1(MT-CO1) and MT-CO2 were suppressed in patients with sJIA but not in patients with polyJIA or healthy children. However, nuclear DNA-encoded cytochrome c oxidases were intact.Conclusion:Our findings suggest that sJIA is not only an immunological disease but also a metabolic disease involving mitochondria disorder.

scholarly journals Toll-Like Receptors: General Molecular and Structural Biology

2021 ◽  
Vol 2021 ◽  
pp. 1-21
Author(s):  
Payam Behzadi ◽  
Herney Andrés García-Perdomo ◽  
Tomasz M. Karpiński
Keyword(s):  
Immune System ◽  
Drug Discovery ◽  
Structural Biology ◽  
English Language ◽  
Inflammatory Diseases ◽  
Adaptive Immune System ◽  
Toll Like Receptors ◽  
Adaptive Immune ◽  
Molecular Patterns

Background/Aim. Toll-like receptors (TLRs) are pivotal biomolecules in the immune system. Today, we are all aware of the importance of TLRs in bridging innate and adaptive immune system to each other. The TLRs are activated through binding to damage/danger-associated molecular patterns (DAMPs), microbial/microbe-associated molecular patterns (MAMPs), pathogen-associated molecular patterns (PAMPs), and xenobiotic-associated molecular patterns (XAMPs). The immunogenetic molecules of TLRs have their own functions, structures, coreceptors, and ligands which make them unique. These properties of TLRs give us an opportunity to find out how we can employ this knowledge for ligand-drug discovery strategies to control TLRs functions and contribution, signaling pathways, and indirect activities. Hence, the authors of this paper have a deep observation on the molecular and structural biology of human TLRs (hTLRs). Methods and Materials. To prepare this paper and fulfill our goals, different search engines (e.g., GOOGLE SCHOLAR), Databases (e.g., MEDLINE), and websites (e.g., SCOPUS) were recruited to search and find effective papers and investigations. To reach this purpose, we tried with papers published in the English language with no limitation in time. The iCite bibliometrics was exploited to check the quality of the collected publications. Results. Each TLR molecule has its own molecular and structural biology, coreceptor(s), and abilities which make them unique or a complementary portion of the others. These immunogenetic molecules have remarkable roles and are much more important in different sections of immune and nonimmune systems rather than that we understand to date. Conclusion. TLRs are suitable targets for ligand-drug discovery strategies to establish new therapeutics in the fields of infectious and autoimmune diseases, cancers, and other inflammatory diseases and disorders.

scholarly journals A cross-sectional cohort study of the activity and turnover of neutrophil granulocytes in juvenile idiopathic arthritis

2021 ◽  
Vol 19 (1) ◽  
Author(s):  
Malin Backlund ◽  
Per Venge ◽  
Lillemor Berntson
Keyword(s):  
Juvenile Idiopathic Arthritis ◽  
Medical Treatment ◽  
Disease Activity ◽  
Rank Correlation ◽  
Adaptive Immune System ◽  
Clinical Aspects ◽  
Enzyme Linked Immunosorbent Assay ◽  
Neutrophil Granulocytes ◽  
Healthy Children ◽  
Cross Sectional

Abstract Background The inflammatory process in juvenile idiopathic arthritis (JIA) involves both the innate and the adaptive immune system. The turnover and activity of neutrophil granulocytes may be reflected by proteins secreted from primary or secondary granules and from the cytoplasm of sequestered cells. Our primary aim was to compare the levels of the secondary neutrophil granule protein human neutrophil lipocalin (HNL), in JIA patients and controls, and to explore a possible priming of neutrophils through parallel analyses in plasma and serum. A secondary aim was to relate the levels of HNL to two other well-studied leukocyte proteins, S100A8/A9 and myeloperoxidase (MPO), as well as to clinical aspects of JIA. Methods The concentrations of the three biomarkers in serum, two of them also in plasma, were measured using enzyme-linked immunosorbent assay in 37 children with JIA without medical treatment, in high disease activity based on juvenile arthritis disease activity score 27 (JADAS27), 32 children on medical treatment, mainly in lower disease activity, and 16 healthy children. We assessed for differences between two groups using the Mann-Whitney U test, and used the Kruskal-Wallis test for multiple group comparisons. Spearman rank correlation, linear and multiple regression analyses were used for evaluation of associations between biomarker concentrations and clinical scores. Results The concentrations of HNL and MPO in serum were significantly increased in children with JIA (p < 0.001, p = 0.002) compared with healthy children, but we found no difference in the plasma levels of HNL and MPO between children with JIA and controls. The serum concentrations of MPO and HNL were unaffected by medical treatment, but S100A8/A9 was reduced by medical treatment and correlated with JADAS27 in both univariate (r = 0.58, p < 0.001) and multivariate (r = 0.59, p < 0.001) analyses. Conclusions Neutrophil granulocytes in children with JIA are primed to release primary and secondary granule proteins, without relation to medical treatment, whereas signs of increased turnover and sequestration of neutrophil granulocytes are reduced by treatment. Levels of neutrophil-originating proteins in serum most likely reflect underlying disease activities of JIA.

scholarly journals The immuneML ecosystem for machine learning analysis of adaptive immune receptor repertoires

2021 ◽  
Vol 3 (11) ◽  
pp. 936-944
Author(s):  
Milena Pavlović ◽  
Lonneke Scheffer ◽  
Keshav Motwani ◽  
Chakravarthi Kanduri ◽  
Radmila Kompova ◽  
...  
Keyword(s):  
Machine Learning ◽  
Immune Receptor ◽  
Adaptive Immune ◽  
Learning Analysis

scholarly journals COVID-19 Immunobiology: Lessons Learned, New Questions Arise

2021 ◽  
Vol 12 ◽  
Author(s):  
Aimilios Kaklamanos ◽  
Konstantinos Belogiannis ◽  
Panagiotis Skendros ◽  
Vassilis G. Gorgoulis ◽  
Panayiotis G. Vlachoyiannopoulos ◽  
...  
Keyword(s):  
Cellular Senescence ◽  
Inflammatory Responses ◽  
Inflammatory Diseases ◽  
Severe Disease ◽  
Adaptive Immune System ◽  
Subsequent Development ◽  
Lessons Learned ◽  
Cellular Stress Response ◽  
Etiologic Factor ◽  
Adaptive Immune

There is strong evidence that COVID-19 pathophysiology is mainly driven by a spatiotemporal immune deregulation. Both its phenotypic heterogeneity, spanning from asymptomatic to severe disease/death, and its associated mortality, are dictated by and linked to maladaptive innate and adaptive immune responses against SARS-CoV-2, the etiologic factor of the disease. Deregulated interferon and cytokine responses, with the contribution of immune and cellular stress-response mediators (like cellular senescence or uncontrolled inflammatory cell death), result in innate and adaptive immune system malfunction, endothelial activation and inflammation (endothelitis), as well as immunothrombosis (with enhanced platelet activation, NET production/release and complement hyper-activation). All these factors play key roles in the development of severe COVID-19. Interestingly, another consequence of this immune deregulation, is the production of autoantibodies and the subsequent development of autoimmune phenomena observed in some COVID-19 patients with severe disease. These new aspects of the disease that are now emerging (like autoimmunity and cellular senescence), could offer us new opportunities in the field of disease prevention and treatment. Simultaneously, lessons already learned from the immunobiology of COVID-19 could offer new insights, not only for this disease, but also for a variety of chronic inflammatory responses observed in autoimmune and (auto)inflammatory diseases.

scholarly journals Machine learning predicts new anti-CRISPR proteins

2020 ◽  
Vol 48 (9) ◽  
pp. 4698-4708 ◽  
Author(s):  
Simon Eitzinger ◽  
Amina Asif ◽  
Kyle E Watters ◽  
Anthony T Iavarone ◽  
Gavin J Knott ◽  
...  
Keyword(s):  
Machine Learning ◽  
Gene Editing ◽  
Adaptive Immune System ◽  
Streptococcus Iniae ◽  
Sequence Information ◽  
Bacterial Genomes ◽  
Training Set ◽  
Direct Identification ◽  
Adaptive Immune ◽  
Shared Set

Abstract The increasing use of CRISPR–Cas9 in medicine, agriculture, and synthetic biology has accelerated the drive to discover new CRISPR–Cas inhibitors as potential mechanisms of control for gene editing applications. Many anti-CRISPRs have been found that inhibit the CRISPR–Cas adaptive immune system. However, comparing all currently known anti-CRISPRs does not reveal a shared set of properties for facile bioinformatic identification of new anti-CRISPR families. Here, we describe AcRanker, a machine learning based method to aid direct identification of new potential anti-CRISPRs using only protein sequence information. Using a training set of known anti-CRISPRs, we built a model based on XGBoost ranking. We then applied AcRanker to predict candidate anti-CRISPRs from predicted prophage regions within self-targeting bacterial genomes and discovered two previously unknown anti-CRISPRs: AcrllA20 (ML1) and AcrIIA21 (ML8). We show that AcrIIA20 strongly inhibits Streptococcus iniae Cas9 (SinCas9) and weakly inhibits Streptococcus pyogenes Cas9 (SpyCas9). We also show that AcrIIA21 inhibits SpyCas9, Streptococcus aureus Cas9 (SauCas9) and SinCas9 with low potency. The addition of AcRanker to the anti-CRISPR discovery toolkit allows researchers to directly rank potential anti-CRISPR candidate genes for increased speed in testing and validation of new anti-CRISPRs. A web server implementation for AcRanker is available online at http://acranker.pythonanywhere.com/.

scholarly journals Machine Learning Predicts New Anti-CRISPR Proteins

2019 ◽  
Author(s):  
Simon Eitzinger ◽  
Amina Asif ◽  
Kyle E. Watters ◽  
Anthony T. Iavarone ◽  
Gavin J. Knott ◽  
...  
Keyword(s):  
Machine Learning ◽  
Gene Editing ◽  
External Validation ◽  
Adaptive Immune System ◽  
Streptococcus Iniae ◽  
Sequence Information ◽  
Bacterial Genomes ◽  
Training Set ◽  
Adaptive Immune ◽  
Shared Set

ABSTRACTThe increasing use of CRISPR-Cas9 in medicine, agriculture and synthetic biology has accelerated the drive to discover new CRISPR-Cas inhibitors as potential mechanisms of control for gene editing applications. Many such anti-CRISPRs have been found in mobile genetic elements that disable the CRISPR-Cas adaptive immune system. However, comparing all currently known anti-CRISPRs does not reveal a shared set of properties that can be used for facile bioinformatic identification of new anti-CRISPR families. Here, we describe AcRanker, a machine learning based method for identifying new potential anti-CRISPRs directly from proteomes using protein sequence information only. Using a training set of known anti-CRISPRs, we built a model based on XGBoost ranking and extensively benchmarked it through non-redundant cross-validation and external validation. We then applied AcRanker to predict candidate anti-CRISPRs from self-targeting bacterial genomes and discovered two previously unknown anti-CRISPRs: AcrllA16 (ML1) and AcrIIA17 (ML8). We show that AcrIIA16 strongly inhibits Streptococcus iniae Cas9 (SinCas9) and weakly inhibits Streptococcus pyogenes Cas9 (SpyCas9). We also show that AcrIIA17 inhibits both SpyCas9 and SauCas9 with low potency. The addition of AcRanker to the anti-CRISPR discovery toolkit allows researchers to directly rank potential anti-CRISPR candidate genes for increased speed in testing and validation of new anti-CRISPRs. A web server implementation for AcRanker is available online at http://acranker.pythonanywhere.com/.

Sign in / Sign up

Export Citation Format

Share Document