Related Experiment Video
Updated: Jun 13, 2025
Detection of Human Leukocyte Antigen Biomarkers in Breast Cancer Utilizing Label-free Biosensor Technology
Published on: March 24, 2015
Phage display enables machine learning discovery of cancer antigen-specific TCRs
Giancarlo Croce1,2,3,4, Rachid Lani4,5, Delphine Tardivon4,5
1Department of Oncology UNIL CHUV, Ludwig Institute for Cancer Research, University of Lausanne, Lausanne, Switzerland.
Abstract:
T cells targeting epitopes in infectious diseases or cancer play a central role in spontaneous and therapy-induced immune responses. Epitope recognition is mediated by the binding of the T cell receptor (TCR), and TCRs recognizing clinically relevant epitopes are promising for T cell-based therapies. Starting from a TCR targeting the cancer-testis antigen NY-ESO-1157-165 epitope, we built large phage display libraries of TCRs with randomized complementary determining region 3 of the β chain. The TCR libraries were panned against NY-ESO-1, which enabled us to collect thousands of epitope-specific TCR sequences. Leveraging these data, we trained a machine learning TCR-epitope interaction predictor and identified several epitope-specific TCRs from TCR repertoires. Cellular assays revealed that the predicted TCRs displayed activity toward NY-ESO-1 and no detectable cross-reactivity. Our work demonstrates how display technologies combined with TCR-epitope interaction predictors can effectively leverage large TCR repertoires for TCR discovery.
Insights
Researchers developed a machine learning model to discover T cell receptors (TCRs) targeting cancer epitopes. This method efficiently identifies specific TCRs for potential cancer immunotherapies.
Area of Science:
- Immunology
- Biotechnology
- Computational Biology
Background:
- T cells and their T cell receptors (TCRs) are crucial for immune responses against infections and cancer.
- TCRs recognizing specific epitopes are key for developing effective T cell-based therapies.
- Identifying novel TCRs targeting clinically relevant epitopes remains a significant challenge.
Purpose of the Study:
- To develop a method for discovering T cell receptors (TCRs) that specifically recognize cancer-associated epitopes.
- To leverage phage display technology and machine learning for efficient TCR discovery.
- To identify and validate novel TCRs targeting the NY-ESO-1 antigen for potential cancer immunotherapy applications.
Main Methods:
- Construction of large phage display libraries of T cell receptors (TCRs) with randomized CDR3β regions.
- Panning of TCR libraries against the cancer-testis antigen NY-ESO-1 to isolate epitope-specific TCR sequences.
- Training a machine learning model to predict TCR-epitope interactions using collected sequence data.
- Identification and validation of novel TCRs from repertoires using the predictive model and cellular assays.
Main Results:
- Thousands of T cell receptor (TCR) sequences specific to the NY-ESO-1157-165 epitope were collected.
- A machine learning predictor successfully identified epitope-specific TCRs from large repertoires.
- Validated TCRs demonstrated specific activity against NY-ESO-1 with no detectable cross-reactivity in cellular assays.
Conclusions:
- The combination of display technologies and machine learning-driven TCR-epitope interaction prediction is effective for TCR discovery.
- This approach enables efficient leveraging of large T cell receptor (TCR) repertoires for identifying therapeutic candidates.
- The identified TCRs show promise for developing targeted T cell-based immunotherapies against cancers expressing NY-ESO-1.
