image: Interpretable Multi-Task Deep Learning Framework for Tumor Heterogeneity Analysis and Risk Prediction in HNSCC. T
Credit: The authors.
In a groundbreaking study published in Current Molecular Pharmacology, researchers have identified a novel biomarker for predicting prognosis and immunotherapy response in head and neck squamous cell carcinoma (HNSCC). The study, led by Yuhui Li and colleagues, utilized single-cell RNA sequencing and spatial transcriptomics to analyze tumor heterogeneity and its impact on treatment outcomes. The researchers discovered that the ratio of DKK1 to CALML5 (DC score) in tumor cells could serve as a robust biomarker for predicting patient prognosis and response to immunotherapy.
The study employed a multi-task deep learning framework to classify patients into distinct risk subgroups based on survival outcomes. The analysis revealed that DKK1 and CALML5 are predominantly expressed in tumor cells, with DKK1+ cells exhibiting immunosuppressive characteristics and CALML5+ cells associated with cytotoxic immune infiltration. "Our findings suggest that the DC score could be a more accurate and reliable biomarker for predicting immunotherapy outcomes in HNSCC patients," said Yuhui Li, one of the lead authors of the study.
The researchers further validated their findings using multiplex immunofluorescence and digital spatial profiling. They observed that a higher DC score correlated with incomplete pathological response and poorer overall survival. "The DC score not only provides a powerful tool for predicting patient outcomes but also offers insights into the spatial and molecular heterogeneity of HNSCC," said Qunxing Li, another lead author.
This study addresses a critical need for more accurate biomarkers in HNSCC treatment, where current markers such as PD-L1 expression and tumor mutational burden have shown limited predictive power. The findings have the potential to significantly improve clinical outcomes for HNSCC patients by enabling more personalized and effective treatment strategies.
COI Statement
The authors declare no competing financial interests or personal relationships that could have influenced the work.