Antigen-specificity measurements are the key to understanding T cell responses

Tippalagama, Rashmi; Chihab, Leila; Kearns, Kendall; Lewis, Sloan A.; Panda, Sudhasini; Willemsen, Lisa; Burel, Julie G.; Arlehamn, Cecilia S. Lindestam

doi:10.3389/fimmu.2023.1127470

Cited by 3 publications

(2 citation statements)

References 239 publications

(116 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is well known that CD3, CD4, and CD8 are mainly expressed on the surface of T cells and are CD molecules involved in recognition, adhesion, and activation [31]. CD3 forms a complex with T cell surface receptors and transmits signals into cells to initiate T cell activation [32].…”

Section: Discussionmentioning

confidence: 99%

MDA5 with Complete CARD2 Region Inhibits the Early Replication of H9N2 AIV and Enhances the Immune Response during Vaccination

Li,

Cai,

et al. 2023

Vaccines

View full text Add to dashboard Cite

Chicken melanoma differentiation-associated gene 5 (MDA5) is a member of the RLRs family that recognizes the viral RNAs invading cells and activates downstream interferon regulatory pathways, thereby inhibiting viral replication. The caspase activation and recruitment domain (CARD) is the most important region in MDA5 protein. However, the antiviral and immune enhancement of MDA5 with the CARD region remains unclear. In this study, two truncated MDA5 genes with different CARD regions, namely MDA5-1 with CARD1 plus partial CARD2 domain and MDA5-2 with CARD1 plus complete CARD2 domain, were cloned via reverse transcription PCR and ligated into plasmid Flag-N vector to be Flag-MDA5-1 and Flag-MDA5-2 plasmids. DF-1 cells were transfected with two plasmids for 24 h and then inoculated with H9N2 virus (0.1 MOI) for 6 h to detect the levels of IFN-β, PKR, MAVS, and viral HA, NA, and NS proteins expression. The results showed that MDA5-1 and MDA5-2 increased the expression of IFN-β and PKR, activated the downstream molecule MAVS production, and inhibited the expression of HA, NA, and NS proteins. The knockdown of MDA5 genes confirmed that MDA5-2 had a stronger antiviral effect than that of MDA5-1. Furthermore, the recombinant proteins MDA5-1 and MDA5-2 were combined with H9N2 inactivated vaccine to immunize SPF chickens subcutaneously injected in the neck three times. The immune response of the immunized chicken was investigated. It was observed that the antibody titers and expressions of immune-related molecules from the chicken immunized with MDA5-1 and MDA5-2 group were increased, in which the inducing function of MDA5-2 groups was the highest among all immunization groups. These results suggested that the truncated MDA5 recombinant proteins with complete CARD2 region could play vital roles in antiviral and immune enhancement. This study provides important material for the further study of the immunoregulatory function and clinical applications of MDA5 protein.

show abstract

Section: Discussionmentioning

confidence: 99%

MDA5 with Complete CARD2 Region Inhibits the Early Replication of H9N2 AIV and Enhances the Immune Response during Vaccination

Li,

Cai,

et al. 2023

Vaccines

View full text Add to dashboard Cite

show abstract

“…The remarkable diversity of TCRs, estimated at approximately 10 15 -10 61 (Dash et al, 2017), results from genetic recombination of somatic-cell DNA encoding V (variable), D (diversity), and J (joining) segments(Bradley & Thomas, 2019; Rudolph et al, 2006). Due to this high diversity arising from a combinatorial explosion of different VDJ recombination possibilities, T-cells are capable of recognizing a large variety of epitopes that can be exogenous or derived from endogenous mutated proteins (Tippalagama et al, 2023).…”

Section: Introductionmentioning

confidence: 99%

TCR-H: Machine Learning Prediction of T-cell Receptor Epitope Binding on Unseen Datasets

T.,

Demerdash,

Smith

2023

Preprint

View full text Add to dashboard Cite

AI/ML approaches to predicting T-cell receptor (TCR) epitope specificity achieve high performance metrics on test datasets which include sequences that are also part of the training set but fail to generalize to test sets consisting of epitopes and TCRs that are absent from the training set, i.e., unseen. We present TCR-H, a supervised classification Support Vector Machines model using physicochemical features trained on the largest dataset available to date using only experimentally validated non-binders as negative datapoints. TCR-H exhibits an area under the curve of the receiver-operator characteristic (AUC of ROC) of 0.87 for epitope ‘hard splitting’ (i.e., on test sets with all epitopes unseen), 0.92 for TCR hard splitting and 0.89 for ‘strict splitting’ in which neither the epitopes nor the TCRs in the test set are seen in the training data. TCR-H may thus represent a significant step towards general applicability of epitope:TCR specificity prediction.

show abstract

TCR-H: explainable machine learning prediction of T-cell receptor epitope binding on unseen datasets

T.,

Demerdash,

Smith

2024

Front. Immunol.

View full text Add to dashboard Cite

Artificial-intelligence and machine-learning (AI/ML) approaches to predicting T-cell receptor (TCR)-epitope specificity achieve high performance metrics on test datasets which include sequences that are also part of the training set but fail to generalize to test sets consisting of epitopes and TCRs that are absent from the training set, i.e., are ‘unseen’ during training of the ML model. We present TCR-H, a supervised classification Support Vector Machines model using physicochemical features trained on the largest dataset available to date using only experimentally validated non-binders as negative datapoints. TCR-H exhibits an area under the curve of the receiver-operator characteristic (AUC of ROC) of 0.87 for epitope ‘hard splitting’ (i.e., on test sets with all epitopes unseen during ML training), 0.92 for TCR hard splitting and 0.89 for ‘strict splitting’ in which neither the epitopes nor the TCRs in the test set are seen in the training data. Furthermore, we employ the SHAP (Shapley additive explanations) eXplainable AI (XAI) method for post hoc interrogation to interpret the models trained with different hard splits, shedding light on the key physiochemical features driving model predictions. TCR-H thus represents a significant step towards general applicability and explainability of epitope:TCR specificity prediction.

show abstract

Antigen-specificity measurements are the key to understanding T cell responses

Cited by 3 publications

References 239 publications

MDA5 with Complete CARD2 Region Inhibits the Early Replication of H9N2 AIV and Enhances the Immune Response during Vaccination

MDA5 with Complete CARD2 Region Inhibits the Early Replication of H9N2 AIV and Enhances the Immune Response during Vaccination

TCR-H: Machine Learning Prediction of T-cell Receptor Epitope Binding on Unseen Datasets

TCR-H: explainable machine learning prediction of T-cell receptor epitope binding on unseen datasets

Contact Info

Product

Resources

About