6 October 2022 in Genomics, Proteomics & Bioinformatics
In recent years, neoantigens have been recognized as ideal targets for tumor immunotherapy. With the development of neoantigen-based tumor immunotherapy, comprehensive neoantigen databases are urgently needed to meet the growing demand for clinical studies. We have built the tumor-specific neoantigen database (TSNAdb) previously, which has attracted much attention. In this study, we provide TSNAdb v2.0, an updated version of the TSNAdb. TSNAdb v2.0 offers several new features, including (1) adopting more stringent criteria for neoantigen identification, (2) providing predicted neoantigens derived from three types of somatic mutations, and (3) collecting experimentally validated neoantigens and dividing them according to the experimental level. TSNAdb v2.0 is freely available at https://pgx.zju.edu.cn/tsnadb/.
21 April 2025 in Genomics, Proteomics & Bioinformatics
Comprehensive and integrated resources on interactions between T-cell receptors (TCRs) and antigens are still lacking for adoptive T-cell-based immunotherapies, highlighting a significant gap that must be addressed to fully understand the mechanisms of antigen recognition by T cells. In this study, we present the T-cell receptor–antigen interaction database (TRAIT), a comprehensive database that profiles the interactions between TCRs and antigens. TRAIT stands out due to its comprehensive description of TCR–antigen interactions by integrating sequences, structures, and affinities. It provides millions of experimentally validated TCR–antigen pairs, resulting in an exhaustive landscape of antigen-specific TCRs. Notably, TRAIT emphasizes single-cell omics as a major reliable data source for TCR–antigen interactions and includes millions of reliable non-interactive TCRs. Additionally, it thoroughly demonstrates the interactions between mutations of TCRs and antigens, thereby benefiting affinity optimization of engineered TCRs as well as vaccine design. TCRs on clinical trials are innovatively provided. With the significant efforts made toward elucidating the complex interactions between TCRs and antigens, TRAIT is expected to ultimately contribute superior algorithms and substantial advancements in the field of T-cell-based immunotherapies. TRAIT is freely accessible at https://pgx.zju.edu.cn/traitdb.
21 November 2024 in bioRxiv
Comprehensive and integrated resources on interactions between T-cell receptors and antigens are still lacking for adoptive T-cell-based immunotherapies, highlighting a significant gap that must be addressed to fully comprehend the mechanisms of antigen recognition by T-cells. In this study, we present TRAIT, a comprehensive database that profiles the interactions between T-cell receptors (TCRs) and antigens. TRAIT stands out due to its comprehensive description of TCR-antigen interactions by integrating sequences, structures and affinities. It provides nearly 8 million experimentally validated TCR-antigen pairs, resulting in an exhaustive landscape of antigen-specific TCRs. Notably, TRAIT emphasizes single-cell omics as a major reliable data source for TCR-antigen interactions and includes millions of reliable non-interactive TCRs. Additionally, it thoroughly demonstrates the interactions between mutations of TCRs and antigens, thereby benefiting affinity maturation of engineered TCRs as well as vaccine design. TCRs on clinical trials were innovatively provided. With the significant efforts made towards elucidating the complex interactions between TCRs and antigens, TRAIT is expected to ultimately contribute superior algorithms and substantial advancements in the field of T-cell-based immunotherapies. TRAIT is freely accessible at https://pgx.zju.edu.cn/traitdb .
2 November 2026 in Briefings in Bioinformatics
Accurate prediction of peptide–major histocompatibility complex (pMHC) binding is central to understanding antigen presentation and identifying T-cell epitopes in cancer immunotherapy. Although recent methods have achieved notable progress, most approaches rely predominantly on sequence-based features and only partially capture structural determinants of pMHC recognition. In this study, we present MultiMHC, a multiscale deep learning framework that integrates complementary sequential and biologically-informed residue contact topology for pMHC binding prediction. MultiMHC combines a recurrent neural network to model global sequence context with a graph-based representation to encode residue contact patterns derived from known pMHC binding interfaces. Features from these two pathways are subsequently fused to generate binding predictions across peptides of varying lengths. Benchmark evaluations show that MultiMHC achieves performance comparable to existing state-of-the-art methods, with particularly strong performance in ranking-based assessments. Moreover, evaluation on the Tumor Neoantigen Selection Alliance dataset showed that MultiMHC binding scores can enrich experimentally validated T-cell epitopes among top-ranked candidates, supporting its potential utility as an upstream binding-based filtering step in neoantigen discovery workflows. Together, these results highlight the value of incorporating residue interaction patterns and lightweight structural information into pMHC modeling and establish MultiMHC as a robust and extensive framework for antigen presentation analysis.
17 June 2026 in Phenomics