A machine learning model integrating circulating Temra cell transcriptional profiles to predict immunotherapy efficacy - PubMed
7 hours ago
- #immunotherapy
- #biomarker
- #machine learning
- A machine learning model was developed to predict immunotherapy efficacy using circulating Temra cell transcriptional profiles.
- The study analyzed paired peripheral blood and tumor samples from 15 patients using single-cell RNA sequencing and T cell receptor sequencing.
- Circulating Temra cells were identified as the most clonally expanded CD8+ subset in peripheral blood, with distinct differentiation trajectories between responders and non-responders.
- The predictive model, based on Temra cell transcriptional profiles, achieved high accuracy (87%-95%) in external validation cohorts.
- Validation in a prospective cohort of 131 advanced NSCLC patients confirmed strong predictive performance (AUC = 0.834).
- The study suggests that circulating Temra cells serve as robust predictors of immunotherapy efficacy, potentially improving clinical decision-making in immuno-oncology.