Computational algorithm to predict interacting MHC alleles from TCR sequences

摘要 主要组织相容性复合体(MHC)通过提呈抗原来引导免疫应答 细胞表面的碎片与T细胞受体(TCR)相互作用。近年来，许多 T细胞疗法已成功地使T细胞靶向MHC抗原复合体 与癌症和其他疾病有关。然而，大多数T细胞疗法都需要识别 与感兴趣的MHC抗原复合体相互作用的TCR，这是一项缓慢而昂贵的研究 进程。我们的建议旨在通过一种计算算法来加速搜索过程 这将预测TCR是否会与感兴趣的MHC等位基因相互作用。当前筛选 检测低频TCR的假阳性率很高。研究人员可以使用我们的工具来 在运行之前计算筛选与特定MHC等位基因相互作用的TCR候选 昂贵的验证实验。在这份提案中，我们将首先通过一个 我们将在公共TCR-MHC相互作用数据上训练的原型算法。然后我们将进行 新的四聚体染色实验，解决了开发 跨多个MHC等位基因的算法：缺乏A*02以外的等位基因的相互作用数据， 以及现有公共数据中有限的抗原多样性。这些实验将提供 四种常见MHC等位基因A*01：01，A*02：01，A*11：01， 和B*07：02。最后，我们将为每个MHC构建和验证计算算法 等位基因和评估各种TCR成分的重要性(例如，α或βChan， CDR3)预测TCR-MHC相互作用。我们的工作将产生第一个计算工具 帮助T细胞治疗开发商根据MHC特异性筛选TCR候选药物。单元格之外 治疗，这个工具还将帮助研究人员追踪MHC等位基因发挥作用的疾病中的T细胞 主要角色。

Abstract Major histocompatibility complexes (MHC) guide immune response by presenting antigen fragments on a cell’s surface and interacting with T-cell receptors (TCRs). In recent years, many T-cell therapies have successfully engineered T-cells to target MHC-antigen complexes associated with cancers and other diseases. However, most T-cell therapies require identifying a TCR that interacts with an MHC-antigen complex of interest, a slow and expensive search process. Our proposal aims to speed up this search process through a computational algorithm that will predict whether a TCR will interact with an MHC allele of interest. Current screening assays for low frequency TCRs have high false positive rates. Researchers can use our tool to computationally filter TCR candidates for interaction with a specific MHC allele before running expensive validation experiments. In this proposal, we will first validate our approach through a prototype algorithm that we will train on public TCR-MHC interaction data. We will then conduct new tetramer staining experiments that address two major challenges for developing an algorithm across multiple MHC alleles: the lack of interaction data for alleles other than A*02, and the limited antigen diversity in existing public data. These experiments will provide TCR-MHC data across 800 antigens for four common MHC alleles: A*01:01, A*02:01, A*11:01, and B*07:02. Finally, we will construct and validate computational algorithms for each MHC allele and evaluate the importance of various TCR components (e.g., alpha or beta chan, CDR3) in predicting TCR-MHC interaction. Our work will result in the first computational tool to help T-cell therapy developers filter TCR candidates based on MHC specificity. Beyond cell therapies, this tool will also help researchers track T-cells in diseases where MHC alleles play a major role.