Abstract
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.