Abstract
T cells initiate anticancer immune responses at an early stage of tumorigenesis, thus enabling dynamic monitoring of peripheral blood T-cell receptor (TCR) repertoire changes as a promising strategy for early cancer detection. However, the current TCR-based cancer detection methods focus on limited high-frequency TCRs instead of repertoire-scale representation, overlooking numerous crucial cancer-associated TCRs (caTCR). Herein, we developed ScanTCR, a computational framework for early cancer detection that introduces a reference-guided repertoire-scale encoding method capable of incorporating all TCRs. ScanTCR exhibited remarkable precision in distinguishing patients with cancer from noncancer individuals using peripheral blood TCRs. In a pan-cancer analysis encompassing seven cancer types, ScanTCR demonstrated robust performance in detecting both cancer types included in the training data and unseen cancer types, surpassing state-of-the-art TCR-based methods. Furthermore, ScanTCR identified caTCRs in which corresponding T cells exhibit enhanced cellular immune capacity. Collectively, this work proposes a TCR-based approach enabling repertoire-scale representation of immune receptors for noninvasive early cancer detection. Significance: Overcoming limitations of current methods that favor high-frequency cancer-associated T-cell receptors, repertoire-scale profiling preserves all sequences for accurate cancer detection, supporting the potential of this approach for early-stage cancer diagnostics.
Funding Information
  • National Natural Science Foundation of China (T2325009)
  • National Natural Science Foundation of China (92574205)
  • National Natural Science Foundation of China (U24A20370)
  • National Natural Science Foundation of China (32270789)
  • National Natural Science Foundation of China (T2495273)
  • National Natural Science Foundation of China (T2541068)
  • National Natural Science Foundation of China (32470691)
  • National Natural Science Foundation of China (32470689)
  • National Natural Science Foundation of China (T2541054)
  • National Natural Science Foundation of China (32400643)
  • National Natural Science Foundation of China (32400542)
  • National Natural Science Foundation of China (32500822)
  • National Natural Science Foundation of China (U25A20649)
  • National Natural Science Foundation of China (62501199)
  • National Natural Science Foundation of China (325B2037)
  • National Science and Technology Major Project (2022ZD0117700)
  • New Era Longjiang Outstanding Master’s and Doctoral Thesis Project (LJYXL2024-020)