RESUMO
Understanding the mechanisms of T-cell antigen recognition that underpin adaptive immune responses is critical for the development of vaccines, immunotherapies, and treatments against autoimmune diseases. Despite extensive research efforts, the accurate identification of T cell receptor (TCR)-antigen binding pairs remains a significant challenge due to the vast diversity and cross-reactivity of TCRs. Here, we propose a deep-learning framework termed Epitope-anchored Contrastive Transfer Learning (EPACT) tailored to paired human CD8+ TCRs from single-cell sequencing data. Harnessing the pre-trained representations and the contrastive co-embedding space, EPACT demonstrates state-of-the-art model generalizability in predicting TCR binding specificity for unseen epitopes and distinct TCR repertoires, offering potential values for practical outcomes in real-world scenarios. The contrastive learning paradigm achieves highly precise predictions for immunodominant epitopes and facilitates interpretable analysis of epitope-specific T cells. The TCR binding strength predicted by EPACT aligns well with the surge in spike-specific immune responses targeting SARS-CoV-2 epitopes after vaccination. We further fine-tune EPACT on TCR-epitope structural data to decipher the residue-level interactions involved in T-cell antigen recognition. EPACT not only exhibits superior capabilities in quantifying inter-chain distance matrices and identifying contact residue pairs but also corroborates the presence of molecular mimicry across multiple tumor-associated antigens. Together, EPACT can serve as a useful AI approach with significant potential in practical applications and contribute toward the development of TCR-based diagnostics and immunotherapies.
Assuntos
Doenças Autoimunes , Síndrome Respiratória Aguda Grave , Neoplasias , Deficiências da AprendizagemRESUMO
Angiotensin-converting enzyme 2 (ACE2) is protective in cardiovascular disease, lung injury and diabetes yet paradoxically underlies our susceptibility to SARs-CoV2 infection and the fatal heart and lung disease it can induce. Furthermore, diabetic patients have chronic, systemic inflammation and altered ACE2 expression resulting in increased risk of severe COVID-19 and the associated mortality. A drug that could increase ACE2 activity and inhibit cellular uptake of severe acute respiratory syndrome coronavirus 2 (SARs-CoV2), thus decrease infection, would be of high relevance to cardiovascular disease, diabetes and SARs-CoV2 infection. While the need for such a drug lead was highlighted over a decade ago receiving over 600 citations,1 to date, no such drugs are available.2 Here, we report the development of a novel ACE2 stimulator, designated ‘2A’(international PCT filed), which is a 10 amino acid peptide derived from a snake venom, and demonstrate its in vitro and in vivo efficacy against SARs-CoV2 infection and associated lung inflammation. Peptide 2A also provides remarkable protection against glycaemic dysregulation, weight loss and disease severity in a mouse model of type 1 diabetes. No untoward effects of 2A were observed in these pre-clinical models suggesting its strong clinical translation potential.