Summary T cells participate directly in the body's immune response to cancer, allowing immunotherapy treatments to effectively recognize and target cancer cells. We previously developed DeepCAT to demonstrate that T cells serve as a biomarker of immune response in cancer patients and can be utilized as a diagnostic tool to differentiate healthy and cancer patient samples. However, DeepCAT’s reliance on tumor bulk RNA-seq samples as training data limited its further performance improvement. Here, we benchmarked a new approach, AutoCAT, to predict tumor-associated TCRs from targeted TCR-seq data as a new form of input for DeepCAT, and observed the same level of predictive accuracy. Availability and implementation Source code is freely available at https://github.com/cew88/AutoCAT, and data is available at 10.5281/zenodo.5176884. Supplementary information Supplementary data are available at Bioinformatics online.

中文翻译：

---

AutoCAT：从 TCR-seq 数据中自动发现癌症相关的 TCR

总结 T细胞直接参与机体对癌症的免疫反应，使免疫疗法能够有效识别和靶向癌细胞。我们之前开发了 DeepCAT，以证明 T 细胞可作为癌症患者免疫反应的生物标志物，并可用作区分健康样本和癌症患者样本的诊断工具。然而，DeepCAT 对肿瘤块 RNA-seq 样本作为训练数据的依赖限制了其进一步的性能提升。在这里，我们对一种新方法 AutoCAT 进行了基准测试，以从靶向 TCR-seq 数据中预测肿瘤相关 TCR 作为 DeepCAT 的一种新输入形式，并观察到相同水平的预测准确性。可用性和实施​​源代码可在 https://github.com/cew88/AutoCAT 免费获得，数据可在 10.5281/zenodo.5176884 获得。