TSTScope Unifies Single‐Cell Multi‐Omics to Identify Functional T Cell States Predictive of Immunotherapy Response
9 affiliations
- 1School of Life Science and Technology ShanghaiTech University Shanghai China
- 2Guangzhou National Laboratory Guangzhou China
- 3Multimedia Laboratory (MMLab) The Chinese University of Hong Kong Hong Kong China
- 4Key Laboratory of Systems Health Science of Zhejiang Province School of Life Science Hangzhou Institute for Advanced Study University of Chinese Academy of Sciences Hangzhou China
- 5School of Intelligent Systems Engineering Sun Yat‐sen University Shenzhen China
- 6Department of Medical Oncology The First Affiliated Hospital Zhejiang University School of Medicine Hangzhou China
- 7GMU‐GIBH Joint School of Life Sciences The Guangdong‐Hong Kong‐Macau Joint Laboratory For Cell Fate Regulation and Diseases Guangzhou Medical University Guangzhou China
- 8School of Life Sciences and Biotechnology Shanghai Jiao Tong University Shanghai China
- 9Shanghai Institute of Nutrition and Health Chinese Academy of Sciences Shanghai China
Abstract
Immune checkpoint blockade (ICB) can produce durable responses in cancer, but reliable predictors of benefit are still lacking. CD8+ tumor‐specific T cells (TSTs) are essential for ICB efficacy, yet it remains unclear which functional states of these cells are associated with therapeutic benefit. To address this, we developed TSTScope, an interpretable deep learning framework that integrates single‐cell transcriptomic and T‐cell receptor sequencing data to generate unified representations of CD8+ T‐cell identity. By applying TSTScope to non‐small cell lung cancer (NSCLC) datasets, we characterized the gene programs defining tumor specificity and computationally inferred a population of potential TSTs (pTSTs). Our analyses show that clinical response is associated with the functional state of these cells rather than their abundance alone. We derived the major pathological response (MPR) score, a metric capturing this functional potential. In an independent validation cohort, the MPR score was associated with pathological response and recurrence‐free survival and provided complementary information to selected response‐associated biomarkers. Collectively, TSTScope identifies a distinct functional state of tumor‐specific T cells linked to ICB response, providing an interpretable framework for studying receptor‐linked T‐cell function in immunotherapy cohorts.
Related
- Incremental Predictive Value and Representation of Transcriptomic Features for Immunotherapy Response in Advanced Urothelial Carcinoma
- Spark-like T cell represents a novel functional state of CD8+T cells associated with anti-PD-1 immunotherapy response and clinical prognosis in non-small cell lung cancer
- Heterogeneous nuclear ribonucleoproteins depict a new predictive risk model for ovarian cancer prognosis and immunotherapy
- Brief Report: Reassessment of bTMB as a Predictive Biomarker in NSCLC Immunotherapy—A Reanalysis of OAK and POPLAR
- Patient-Derived Glioma Models Preserve Tumor Heterogeneity and Identify Stearoyl-CoA Desaturase1 (SCD1) as a Candidate Biomarker for Precision Immunotherapy
BibTeX
@article{cao2026tstscope,
title = {{TSTScope Unifies Single‐Cell Multi‐Omics to Identify Functional T Cell States Predictive of Immunotherapy Response}},
author = {Shiwei Cao and Jinyu Cheng and Feng‐ao Wang and Chenxin Yi and Jiajun Chen and Keyue Wang and Lulu Liu and Junwei Liu and Yixue Li},
journal = {Advanced Science},
year = {2026},
month = aug,
doi = {10.1002/advs.76983},
url = {https://doi.org/10.1002/advs.76983},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - TSTScope Unifies Single‐Cell Multi‐Omics to Identify Functional T Cell States Predictive of Immunotherapy Response
AU - Shiwei Cao
AU - Jinyu Cheng
AU - Feng‐ao Wang
AU - Chenxin Yi
AU - Jiajun Chen
AU - Keyue Wang
AU - Lulu Liu
AU - Junwei Liu
AU - Yixue Li
PY - 2026
DA - 2026/08/05
JO - Advanced Science
DO - 10.1002/advs.76983
UR - https://doi.org/10.1002/advs.76983
AB - Immune checkpoint blockade (ICB) can produce durable responses in cancer, but reliable predictors of benefit are still lacking. CD8+ tumor‐specific T cells (TSTs) are essential for ICB efficacy, yet it remains unclear which functional states of these cells are associated with therapeutic benefit. To address this, we developed TSTScope, an interpretable deep learning framework that integrates single‐cell transcriptomic and T‐cell receptor sequencing data to generate unified representations of CD8+ T‐cell identity. By applying TSTScope to non‐small cell lung cancer (NSCLC) datasets, we characterized the gene programs defining tumor specificity and computationally inferred a population of potential TSTs (pTSTs). Our analyses show that clinical response is associated with the functional state of these cells rather than their abundance alone. We derived the major pathological response (MPR) score, a metric capturing this functional potential. In an independent validation cohort, the MPR score was associated with pathological response and recurrence‐free survival and provided complementary information to selected response‐associated biomarkers. Collectively, TSTScope identifies a distinct functional state of tumor‐specific T cells linked to ICB response, providing an interpretable framework for studying receptor‐linked T‐cell function in immunotherapy cohorts.
SN - 2198-3844
ER -