scholarly journals Deep generative selection models of T and B cell receptor repertoires with soNNia

2021 ◽  
Vol 118 (14) ◽  
pp. e2023141118
Author(s):  
Giulio Isacchini ◽  
Aleksandra M. Walczak ◽  
Thierry Mora ◽  
Armita Nourmohammad
Keyword(s):  
Machine Learning ◽  
B Cell ◽  
Cell Receptor ◽  
T Cell Subsets ◽  
Sequence Information ◽  
Specific Sequence ◽  
Linear Classifiers ◽  
Functional Roles ◽  
Biophysical Models ◽  
Selection Processes

Subclasses of lymphocytes carry different functional roles to work together and produce an immune response and lasting immunity. Additionally to these functional roles, T and B cell lymphocytes rely on the diversity of their receptor chains to recognize different pathogens. The lymphocyte subclasses emerge from common ancestors generated with the same diversity of receptors during selection processes. Here, we leverage biophysical models of receptor generation with machine learning models of selection to identify specific sequence features characteristic of functional lymphocyte repertoires and subrepertoires. Specifically, using only repertoire-level sequence information, we classify CD4+ and CD8+ T cells, find correlations between receptor chains arising during selection, and identify T cell subsets that are targets of pathogenic epitopes. We also show examples of when simple linear classifiers do as well as more complex machine learning methods.

scholarly journals Deep generative selection models of T and B cell receptor repertoires with soNNia

2020 ◽  
Author(s):  
Giulio Isacchini ◽  
Aleksandra M. Walczak ◽  
Thierry Mora ◽  
Armita Nourmohammad
Keyword(s):  
Machine Learning ◽  
T Cells ◽  
B Cell ◽  
Cell Receptor ◽  
Sequence Information ◽  
Specific Sequence ◽  
Linear Classifiers ◽  
Functional Roles ◽  
Biophysical Models ◽  
Selection Processes

Subclasses of lymphocytes carry different functional roles to work together to produce an immune response and lasting immunity. Additionally to these functional roles, T and B-cell lymphocytes rely on the diversity of their receptor chains to recognize different pathogens. The lymphocyte subclasses emerge from common ancestors generated with the same diversity of receptors during selection processes. Here we leverage biophysical models of receptor generation with machine learning models of selection to identify specific sequence features characteristic of functional lymphocyte repertoires and subrepertoires. Specifically using only repertoire level sequence information, we classify CD4+ and CD8+ T-cells, find correlations between receptor chains arising during selection and identify T-cells subsets that are targets of pathogenic epitopes. We also show examples of when simple linear classifiers do as well as more complex machine learning methods.

scholarly journals OP0287 A MACHINE LEARNING APPROACH FOR PRECISION STRATIFICATION OF JUVENILE-ONSET SLE

2020 ◽  
Vol 79 (Suppl 1) ◽  
pp. 179.2-179
Author(s):  
G. Robinson ◽  
J. Peng ◽  
P. Dönnes ◽  
L. Coelewij ◽  
M. Naja ◽  
...  
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
T Cell ◽  
B Cell ◽  
T Cell Subsets ◽  
Healthy Controls ◽  
Juvenile Onset ◽  
Immune Signature ◽  
Immune Phenotyping ◽  
Over Time

Background:Juvenile-onset systemic lupus erythematosus (JSLE) is a complex and heterogeneous disease characterised by diagnosis and treatment delays. An unmet need exists to better characterise the immunological profile of JSLE patients and investigate its links with the disease trajectory over time.Objectives:A machine learning (ML) approach was applied to explore new diagnostic signatures for JSLE based on immune-phenotyping data and stratify patients by specific immune characteristics to investigate longitudinal clinical outcome.Methods:Immune-phenotyping of 28 T-cell, B-cell and myeloid-cell subsets in 67 age and sex-matched JSLE patients and 39 healthy controls (HCs) was performed by flow cytometry. A balanced random forest (BRF) ML predictive model was developed (10,000 decision trees). 10-fold cross validation, Sparse Partial Least Squares-Discriminant Analysis (sPLS-DA) and logistic regression was used to validate the model. Longitudinal clinical data were related to the immunological features identified by ML analysis.Results:The BRF-model discriminated JSLE patients from healthy controls with 91% prediction accuracy suggesting that JSLE patients could be distinguished from HCs with high confidence using immunological parameters. The top-ranked immunological features from the BRF-model were confirmed using sPLS-DA and logistic regression and included CD19+ unswitched memory B-cells, naïve B-cells, CD14+monocytes and total CD4+, CD8+and memory T-cell subsets.K-mean clustering was applied to stratify patients using the validated signature. Four groups were identified, each with a distinct immune and clinical profile. Notably, CD8+T-cell subsets were important in driving patient stratification while B-cell markers were similarly expressed across the JSLE cohort. JSLE patients with elevated effector memory CD8+T-cell frequencies had more persistently active disease over time, and this was associated with increased treatment burden and prevalence of lupus nephritis. Finally, network analysis identified specific clinical features associated with each of the top JSLE immune-signature variables.Conclusion:Using a combined ML approach, a distinct immune signature was identified that discriminated between JSLE patients and HCs and further stratified patients. This signature could have diagnostic and therapeutic implications. Further immunological association studies are warranted to develop data-driven personalised medicine approaches for JSLE.Acknowledgments:Lupus UK, Rosetrees Trust, Versus ArthritisDisclosure of Interests:George Robinson: None declared, Junjie Peng: None declared, Pierre Dönnes: None declared, Leda Coelewij: None declared, Meena Naja: None declared, Anna Radziszewska: None declared, Chris Wincup: None declared, Hannah Peckham: None declared, David Isenberg Consultant of: Study Investigator and Consultant to Genentech, Yiannis Ioannou: None declared, Ines Pineda Torra: None declared, Coziana Ciurtin Grant/research support from: Pfizer, Consultant of: Roche, Modern Biosciences, Elizabeth Jury: None declared

scholarly journals Naïve Regulatory T Cell Subset Is Altered in X-Linked Agammaglobulinemia

2021 ◽  
Vol 12 ◽  
Author(s):  
Pavel V. Shelyakin ◽  
Ksenia R. Lupyr ◽  
Evgeny S. Egorov ◽  
Ilya A. Kofiadi ◽  
Dmitriy B. Staroverov ◽  
...  
Keyword(s):  
T Cells ◽  
T Cell ◽  
B Cell ◽  
Cell Subset ◽  
Cell Receptor ◽  
T Cell Subsets ◽  
Cell Compartments ◽  
Expression Of Genes ◽  
Tcr Repertoire ◽  
Antigen Presenting

The interplay between T- and B-cell compartments during naïve, effector and memory T cell maturation is critical for a balanced immune response. Primary B-cell immunodeficiency arising from X-linked agammaglobulinemia (XLA) offers a model to explore B cell impact on T cell subsets, starting from the thymic selection. Here we investigated characteristics of naïve and effector T cell subsets in XLA patients, revealing prominent alterations in the corresponding T-cell receptor (TCR) repertoires. We observed immunosenescence in terms of decreased diversity of naïve CD4+ and CD8+ TCR repertoires in XLA donors. The most substantial alterations were found within naïve CD4+ subsets, and we have investigated these in greater detail. In particular, increased clonality and convergence, along with shorter CDR3 regions, suggested narrower focused antigen-specific maturation of thymus-derived naïve Treg (CD4+CD45RA+CD27+CD25+) in the absence of B cells - normally presenting diverse self and commensal antigens. The naïve Treg proportion among naïve CD4 T cells was decreased in XLA patients, supporting the concept of impaired thymic naïve Treg selection. Furthermore, the naïve Treg subset showed prominent differences at the transcriptome level, including increased expression of genes specific for antigen-presenting and myeloid cells. Altogether, our findings suggest active B cell involvement in CD4 T cell subsets maturation, including B cell-dependent expansion of the naïve Treg TCR repertoire that enables better control of self-reactive T cells.

scholarly journals Role of B-cell receptors for B-cell development and antigen-induced differentiation

F1000Research ◽  
2018 ◽  
Vol 7 ◽  
pp. 429 ◽  
Author(s):  
Juan Carlos Yam-Puc ◽  
Lingling Zhang ◽  
Yang Zhang ◽  
Kai-Michael Toellner
Keyword(s):  
B Cells ◽  
B Cell ◽  
Cell Receptor ◽  
Cell Development ◽  
B Cell Development ◽  
B Cell Maturation ◽  
Selection Processes ◽  
Fate Decision ◽  
Follicular B Cells

B-cell development is characterized by a number of tightly regulated selection processes. Signals through the B-cell receptor (BCR) guide and are required for B-cell maturation, survival, and fate decision. Here, we review the role of the BCR during B-cell development, leading to the emergence of B1, marginal zone, and peripheral follicular B cells. Furthermore, we discuss BCR-derived signals on activated B cells that lead to germinal center and plasma cell differentiation.

scholarly journals Machine Learning Analysis of Naïve B-Cell Receptor Repertoires Stratifies Celiac Disease Patients and Controls

2021 ◽  
Vol 12 ◽  
Author(s):  
Or Shemesh ◽  
Pazit Polak ◽  
Knut E. A. Lundin ◽  
Ludvig M. Sollid ◽  
Gur Yaari
Keyword(s):  
Machine Learning ◽  
T Cells ◽  
Celiac Disease ◽  
B Cells ◽  
B Cell ◽  
Cd4 T Cells ◽  
Cell Receptor ◽  
B Cell Receptor ◽  
Machine Learning Classification ◽  
Gluten Peptides

Celiac disease (CeD) is a common autoimmune disorder caused by an abnormal immune response to dietary gluten proteins. The disease has high heritability. HLA is the major susceptibility factor, and the HLA effect is mediated via presentation of deamidated gluten peptides by disease-associated HLA-DQ variants to CD4+ T cells. In addition to gluten-specific CD4+ T cells the patients have antibodies to transglutaminase 2 (autoantigen) and deamidated gluten peptides. These disease-specific antibodies recognize defined epitopes and they display common usage of specific heavy and light chains across patients. Interactions between T cells and B cells are likely central in the pathogenesis, but how the repertoires of naïve T and B cells relate to the pathogenic effector cells is unexplored. To this end, we applied machine learning classification models to naïve B cell receptor (BCR) repertoires from CeD patients and healthy controls. Strikingly, we obtained a promising classification performance with an F1 score of 85%. Clusters of heavy and light chain sequences were inferred and used as features for the model, and signatures associated with the disease were then characterized. These signatures included amino acid (AA) 3-mers with distinct bio-physiochemical characteristics and enriched V and J genes. We found that CeD-associated clusters can be identified and that common motifs can be characterized from naïve BCR repertoires. The results may indicate a genetic influence by BCR encoding genes in CeD. Analysis of naïve BCRs as presented here may become an important part of assessing the risk of individuals to develop CeD. Our model demonstrates the potential of using BCR repertoires and in particular, naïve BCR repertoires, as disease susceptibility markers.

scholarly journals Relevant Characteristics Analysis Using Natural Language Processing and Machine Learning Based on Phenotypes and T-Cell Subsets in Systemic Lupus Erythematosus Patients With Anxiety

2021 ◽  
Vol 12 ◽  
Author(s):  
Xi-xi Gu ◽  
Yi Jin ◽  
Ting Fu ◽  
Xiao-ming Zhang ◽  
Teng Li ◽  
...  
Keyword(s):  
Machine Learning ◽  
Systemic Lupus Erythematosus ◽  
Natural Language Processing ◽  
T Cell ◽  
B Cell ◽  
Language Processing ◽  
Lupus Erythematosus ◽  
T Cell Subsets ◽  
Systemic Lupus ◽  
B Cell Subsets

Anxiety is frequently observed in patients with systemic lupus erythematosus (SLE) and the immune system could act as a trigger for anxiety. To recognize abnormal T-cell and B-cell subsets for SLE patients with anxiety, in this study, patient disease phenotypes data from electronic lupus symptom records were extracted by using natural language processing. The Hospital Anxiety and Depression Scale (HADS) was used to distinguish patients, and 107 patients were selected to meet research requirements. Then, peripheral blood was collected from two patient groups for multicolor flow cytometry experiments. The characteristics of 75 T-cell and 15 B-cell subsets were investigated between SLE patients with- (n = 23) and without-anxiety (n = 84) groups by four machine learning methods. The findings showed 13 T-cell subsets were significantly different between the two groups. Furthermore, BMI, fatigue, depression, unstable emotions, CD27+CD28+ Th/Treg, CD27−CD28− Th/Treg, CD45RA−CD27− Th, and CD45RA+HLADR+ Th cells may be important characteristics between SLE patients with- and without-anxiety groups. The findings not only point out the difference of T-cell subsets in SLE patients with or without anxiety, but also imply that T cells might play the important role in patients with anxiety disorder.

scholarly journals Coordinated changes in glycosylation regulate the germinal centre through CD22

2021 ◽  
Author(s):  
Jhon R. Enterina ◽  
Susmita Sarkar ◽  
Laura Streith ◽  
Jaesoo Jung ◽  
Britni M. Arlian ◽  
...  
Keyword(s):  
B Cells ◽  
B Cell ◽  
Cell Receptor ◽  
Affinity Maturation ◽  
B Cell Receptor ◽  
Antibody Affinity ◽  
Critical Function ◽  
Functional Roles ◽  
Germinal Centres ◽  
Follicular B Cells

AbstractGerminal centres (GC) are sites of B-cell expansion and selection, which are essential for antibody affinity maturation. Compared to naive follicular B-cells, GC B-cells have several notable changes in their cell surface glycans. While these changes are routinely used to identify the GC, functional roles for these changes have yet to be ascribed. Detection of GCs by the antibody GL7 reflects a reduction in the glycan ligands for CD22, which is an inhibitory co-receptor of the B-cell receptor (BCR). To test a functional role for downregulated CD22 ligands in the GC, we generated a mouse model that maintains CD22 ligands on GC B-cells. With this model, we demonstrate that glycan remodeling is crucial for proper GC B-cell response, including plasma cell output and affinity maturation of antibodies. The defect we observe in this model is dependent on CD22, highlighting that coordinated downregulation of CD22 ligands on B cells plays a critical function in the GC. Collectively, our study uncovers a crucial role for glycan remodeling and CD22 in B-cell fitness in the GC.

scholarly journals Machine learning analysis of naïve B-cell receptor repertoires stratifies celiac disease patients and controls

2020 ◽  
Author(s):  
Or Shemesh ◽  
Pazit Polak ◽  
Knut E.A. Lundin ◽  
Ludvig M. Sollid ◽  
Gur Yaari
Keyword(s):  
Machine Learning ◽  
T Cells ◽  
Celiac Disease ◽  
B Cells ◽  
B Cell ◽  
Cd4 T Cells ◽  
Cell Receptor ◽  
B Cell Receptor ◽  
Machine Learning Classification ◽  
Gluten Peptides

AbstractCeliac disease (CeD) is a common autoimmune disorder caused by an abnormal immune response to dietary gluten proteins. The disease has high heritability. HLA is the major susceptibility factor, and the HLA effect is mediated via presentation of deamidated gluten peptides by disease-associated HLA-DQ variants to CD4+ T cells. In addition to gluten-specific CD4+ T cells the patients have antibodies to transglutaminase 2 (autoantigen) and deamidated gluten peptides. These disease-specific antibodies recognize defined epitopes and they display common usage of specific heavy and light chains across patients. Interactions between T cells and B cells are likely central in the pathogenesis, but how the repertoires of naïve T and B cells relate to the pathogenic effector cells is unexplored. To this end, we applied machine learning classification models to naïve B cell receptor (BCR) repertoires from CeD patients and healthy controls. Strikingly, we obtained a promising classification performance with an F1 score of 85%. Clusters of heavy and light chain sequences were inferred and used as features for the model, and signatures associated with the disease were then characterized. These signatures included amino acid (AA) 3-mers with distinct bio-physiochemical characteristics and enriched V and J genes. We found that CeD-associated clusters can be identified and that common motifs can be characterized from naïve BCR repertoires. The results may indicate a genetic influence by BCR encoding genes in CeD. Analysis of naïve BCRs as presented here may become an important part of assessing the risk of individuals to develop CeD. Our model demonstrates the potential of using BCR repertoires and in particular, naïve BCR repertoires, as disease susceptibility markers.

scholarly journals Population matched (pm) germline allelic variants of immunoglobulin (IG) loci: Relevance in infectious diseases and vaccination studies in human populations

2021 ◽  
Author(s):  
Indu Khatri ◽  
Magdalena A. Berkowska ◽  
Erik B. van den Akker ◽  
Cristina Teodosio ◽  
Marcel J. T. Reinders ◽  
...  
Keyword(s):  
Infectious Diseases ◽  
Immune Responses ◽  
B Cell ◽  
Association Studies ◽  
Cell Receptor ◽  
Human Populations ◽  
Allelic Variants ◽  
Evolutionary Selection ◽  
Selection Processes ◽  
Novel Alleles

AbstractImmunoglobulin (IG) loci harbor inter-individual allelic variants in many different germline IG variable, diversity and joining genes of the IG heavy (IGH), kappa (IGK) and lambda (IGL) loci, which together form the genetic basis of the highly diverse antigen-specific B-cell receptors. These allelic variants can be shared between or be specific to human populations. The current immunogenetics resources gather the germline alleles, however, lack the population specificity of the alleles which poses limitations for disease-association studies related to immune responses in different human populations. Therefore, we systematically identified germline alleles from 26 different human populations around the world, profiled by “1000 Genomes” data. We identified 409 IGHV, 179 IGKV, and 199 IGLV germline alleles supported by at least seven haplotypes. The diversity of germline alleles is the highest in Africans. Remarkably, the variants in the identified novel alleles show strikingly conserved patterns, the same as found in other IG databases, suggesting over-time evolutionary selection processes. We could relate the genetic variants to population-specific immune responses, e.g. IGHV1-69 for flu in Africans. The population matched IG (pmIG) resource will enhance our understanding of the SHM-related B-cell receptor selection processes in (infectious) diseases and vaccination within and between different human populations.

Sign in / Sign up

Export Citation Format

Share Document