Related Experiment Video
Updated: Jul 1, 2025
T and B Cell Receptor Immune Repertoire Analysis using Next-generation Sequencing
Published on: January 12, 2021
Prediction of tumor-reactive T cell receptors from scRNA-seq data for personalized T cell therapy
C L Tan1,2,3,4, K Lindner1,2,3,5, T Boschert1,2,3,4,6
1CCU Neuroimmunology and Brain Tumor Immunology, German Cancer Research Center, Heidelberg, Germany.
Abstract:
The identification of patient-derived, tumor-reactive T cell receptors (TCRs) as a basis for personalized transgenic T cell therapies remains a time- and cost-intensive endeavor. Current approaches to identify tumor-reactive TCRs analyze tumor mutations to predict T cell activating (neo)antigens and use these to either enrich tumor infiltrating lymphocyte (TIL) cultures or validate individual TCRs for transgenic autologous therapies. Here we combined high-throughput TCR cloning and reactivity validation to train predicTCR, a machine learning classifier that identifies individual tumor-reactive TILs in an antigen-agnostic manner based on single-TIL RNA sequencing. PredicTCR identifies tumor-reactive TCRs in TILs from diverse cancers better than previous gene set enrichment-based approaches, increasing specificity and sensitivity (geometric mean) from 0.38 to 0.74. By predicting tumor-reactive TCRs in a matter of days, TCR clonotypes can be prioritized to accelerate the manufacture of personalized T cell therapies.
Insights
Identifying tumor-reactive T cell receptors (TCRs) for personalized cancer therapies is challenging. A new machine learning tool, predicTCR, rapidly identifies tumor-reactive T cells from diverse cancers, accelerating therapy development.
Area of Science:
- Immunology
- Computational Biology
- Oncology
Background:
- Personalized T cell therapies rely on identifying patient-derived, tumor-reactive T cell receptors (TCRs).
- Current methods for TCR identification are time-consuming and costly, often involving neoantigen prediction and validation.
- These existing approaches face limitations in efficiency and broad applicability across different cancer types.
Purpose of the Study:
- To develop a faster and more accurate method for identifying tumor-reactive TCRs.
- To enable antigen-agnostic identification of tumor-reactive T cells.
- To accelerate the development of personalized T cell therapies.
Main Methods:
- Combined high-throughput TCR cloning and reactivity validation.
- Trained a machine learning classifier, predicTCR, using single-T cell RNA sequencing data.
- Evaluated predicTCR's performance on T cells infiltrating diverse human cancers.
Main Results:
- PredicTCR accurately identifies tumor-reactive T cells in an antigen-agnostic manner.
- Achieved significant improvements in specificity and sensitivity (geometric mean from 0.38 to 0.74) compared to previous methods.
- Demonstrated superior performance across various cancer types.
Conclusions:
- PredicTCR offers a rapid, antigen-agnostic approach to identify tumor-reactive T cells.
- This method can significantly accelerate the prioritization of TCR clonotypes for manufacturing personalized T cell therapies.
- Enables faster development of effective cancer immunotherapies.
