Predicting antigen specificity of single T cells based on
            <scp>TCR CDR</scp>
            3 regions

Fischer, David; Wu, Yihan; Schubert, Benjamin; Theis, Fabian J.

doi:10.15252/msb.20199416

Cited by 77 publications

(59 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, ALICE is for detecting groups of homologous/expanded TCRs ( 13 ). TcellMatch uses cell-specific covariates (e.g., gene expression) but not TCR sequence alone as input, and its performance was tested on the noisy 10x Genomics Immune Map data without further cleanup ( 20 ).…”

Section: Resultsmentioning

confidence: 99%

“…As next-generation screening technologies have increased the volume of available TCR-pMHC binding data, robust classifiers to computationally validate and subsequently predict TCR-pMHC–specific recognition are desired. While the results from initial TCR-pMHC binding classifiers are encouraging, most of them were only trained using CDR loop sequences or β-chain sequences alone and thus unable to learn the overall complex sequence patterns from full-length TCR sequences, resulting in suboptimal prediction accuracy for highly diverse pMHC binding TCRs ( 13 , 14 , 19 , 20 ). Leveraging the ability of deep learning algorithms to learn complex patterns, a couple of neural network–based classifiers were recently proposed ( 17 , 18 ) to uncover binding patterns in large, highly complex pMHC binding TCR sequences.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A framework for highly multiplexed dextramer mapping and prediction of T cell receptor sequences to antigen specificity

et al. 2021

View full text Add to dashboard Cite

T cell receptor (TCR) antigen–specific recognition is essential for the adaptive immune system. However, building a TCR-antigen interaction map has been challenging due to the staggering diversity of TCRs and antigens. Accordingly, highly multiplexed dextramer-TCR binding assays have been recently developed, but the utility of the ensuing large datasets is limited by the lack of robust computational methods for normalization and interpretation. Here, we present a computational framework comprising a novel method, ICON (Integrative COntext-specific Normalization), for identifying reliable TCR-pMHC (peptide–major histocompatibility complex) interactions and a neural network–based classifier TCRAI that outperforms other state-of-the-art methods for TCR-antigen specificity prediction. We further demonstrated that by combining ICON and TCRAI, we are able to discover novel subgroups of TCRs that bind to a given pMHC via different mechanisms. Our framework facilitates the identification and understanding of TCR-antigen–specific interactions for basic immunological research and clinical immune monitoring.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A framework for highly multiplexed dextramer mapping and prediction of T cell receptor sequences to antigen specificity

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Low counts of lymphocytes ( 11 ) and functionally impaired monocytes ( 8 ) make the patients susceptible to infection/reactivation of infective microorganisms. Effective T cell activation in response to a given pathogen needs the presence of a large number of lymphocytes to have a chance in finding cell having CDR3 able to align with the presented epitope ( 82 ). If it happens T cells may activate B cells having compatible membrane bound immunoglobulins named B cell receptor.…”

Section: Lymphocytes and Monocytes In The Pro-inflammatory Environmentmentioning

confidence: 99%

Cytokine Overproduction and Immune System Dysregulation in alloHSCT and COVID-19 Patients

Lange

Lange²,

Jaskuła

2021

Front. Immunol.

View full text Add to dashboard Cite

The COVID-19 pathomechanism depends on (i) the pathogenicity of the virus, (ii) ability of the immune system to respond to the cytopathic effect of the virus infection, (iii) co-morbidities. Inflammatory cytokine production constitutes a hallmark of COVID-19 that is facilitated by inability of adaptive immunity to control virus invasion. The effect of cytokine release syndrome is deleterious, but the severity of it depends on other confounding factors: age and comorbidities. In this study, we analyze the literature data on the post-transplant course of allogeneic hematopoietic stem cell transplanted (alloHSCT) patients, which is affected by generated inflammatory cytokines. The sequence of events boosting cytokine production was analyzed in relation to clinical and laboratory data highlighting the impact of cytokine generation on the post-transplant course. The collected data were compared to those from studies on COVID-19 patients. The similarities are: (i) the damage/pathogen-associated molecular pattern (DAMP/PAMP) stage is similar except for the initiation hit being sterile in alloHSCT (toxic damage of conditioning regimen) and viral in COVID-19; (ii) genetic host-derived factors play a role; (iii) adaptive immunity fails, DAMP signal(s) increases, over-production of cytokines occurs; (iv) monocytes lacking HLADR expression emerge, being suppressor cells hampering adaptive immunity; (v) immune system homeostasis is broken, the patient’s status deteriorates to bed dependency, leading to hypo-oxygenation and malnutrition, which in turn stimulates the intracellular alert pathways with vigorous transcription of cytokine genes. All starts with the interaction between DAMPs with appropriate receptors, which leads to the production of pro-inflammatory cytokines, the inflammatory process spreads, tissue is damaged, DAMPs are released and a vicious cycle occurs. Attempts to modify intracellular signaling pathways in patients with post-alloHSCT graft vs host disease have already been undertaken. The similarities documented in this study show that this approach may also be used in COVID-19 patients for tuning signal transduction processes to interrupt the cycle that powers the cytokine overproduction.

show abstract

“…Another complicating factor is that despite the advent of single cell TCR paired chain sequencing, the currently available TCR-epitope binding data still mostly consists of single-chain (usually beta-chain) data, while in reality both the alpha and beta chains are thought to contribute to binding specificity. Indeed, recent studies have suggested that utilizing both chains could increase the accuracy of predictive TCR-epitope models [ 15 , 16 ].…”

Section: Introductionmentioning

confidence: 99%

Current challenges for unseen-epitope TCR interaction prediction and a new perspective derived from image classification

Moris¹,

Pauw²,

Postovskaya³

et al. 2020

Briefings in Bioinformatics

109

183

View full text Add to dashboard Cite

The prediction of epitope recognition by T-cell receptors (TCRs) has seen many advancements in recent years, with several methods now available that can predict recognition for a specific set of epitopes. However, the generic case of evaluating all possible TCR-epitope pairs remains challenging, mainly due to the high diversity of the interacting sequences and the limited amount of currently available training data. In this work, we provide an overview of the current state of this unsolved problem. First, we examine appropriate validation strategies to accurately assess the generalization performance of generic TCR-epitope recognition models when applied to both seen and unseen epitopes. In addition, we present a novel feature representation approach, which we call ImRex (interaction map recognition). This approach is based on the pairwise combination of physicochemical properties of the individual amino acids in the CDR3 and epitope sequences, which provides a convolutional neural network with the combined representation of both sequences. Lastly, we highlight various challenges that are specific to TCR-epitope data and that can adversely affect model performance. These include the issue of selecting negative data, the imbalanced epitope distribution of curated TCR-epitope datasets and the potential exchangeability of TCR alpha and beta chains. Our results indicate that while extrapolation to unseen epitopes remains a difficult challenge, ImRex makes this feasible for a subset of epitopes that are not too dissimilar from the training data. We show that appropriate feature engineering methods and rigorous benchmark standards are required to create and validate TCR-epitope predictive models.

show abstract

Predicting antigen specificity of single T cells based on TCR CDR 3 regions

Cited by 77 publications

References 30 publications

A framework for highly multiplexed dextramer mapping and prediction of T cell receptor sequences to antigen specificity

A framework for highly multiplexed dextramer mapping and prediction of T cell receptor sequences to antigen specificity

Cytokine Overproduction and Immune System Dysregulation in alloHSCT and COVID-19 Patients

Current challenges for unseen-epitope TCR interaction prediction and a new perspective derived from image classification

Contact Info

Product

Resources

About