2. Academic Validation
  3. Machine learning identified extrachromosomal DNA-related 12 gene signatures to predict cancer immunotherapy response

Machine learning identified extrachromosomal DNA-related 12 gene signatures to predict cancer immunotherapy response

  • Cancer Cell Int. 2025 Dec 18;25(1):436. doi: 10.1186/s12935-025-04056-7.
Yan Ju # 1 2 3,  Jingwei Zhang # 1 2 3,  Jiaming Deng 1 2 3,  Xingyuan Wu 1 2 3,  Haotian Yang 4,  Changyu Tao 5 6,  Xiao Li 7 8 9
Affiliations

Affiliations

  • 1 Thoracic Oncology Institute, Department of Thoracic Surgery, Peking University People's Hospital, Beijing, 100044, China.
  • 2 Research Unit of Intelligence Diagnosis and Treatment in Early Non-small Cell Lung Cancer, Chinese Academy of Medical Sciences, Peking University People's Hospital, Beijing, 2021RU002, 100044, China.
  • 3 Institute of Advanced Clinical Medicine, Peking University, Beijing, China.
  • 4 Peking University Health Science Center, Beijing, 100191, China.
  • 5 Department of Medical Bioinformatics, School of Basic Medical Sciences, Peking University Health Science Center, Beijing, 100191, China. [email protected].
  • 6 Department of Human Anatomy, Histology and Embryology, School of Basic Medical Sciences, Peking University Health Science Center, Beijing, 100191, China. [email protected].
  • 7 Thoracic Oncology Institute, Department of Thoracic Surgery, Peking University People's Hospital, Beijing, 100044, China. [email protected].
  • 8 Research Unit of Intelligence Diagnosis and Treatment in Early Non-small Cell Lung Cancer, Chinese Academy of Medical Sciences, Peking University People's Hospital, Beijing, 2021RU002, 100044, China. [email protected].
  • 9 Institute of Advanced Clinical Medicine, Peking University, Beijing, China. [email protected].
  • # Contributed equally.
PMID: 41413526 DOI: 10.1186/s12935-025-04056-7
Abstract

Extrachromosomal circular DNA (ecDNA) has emerged as a critical determinant of poor clinical outcomes and immune escape in tumors, but the high cost and technical complexity of current detecting techniques limit its broader investigation in Cancer Immunotherapy. Leveraging the combined machine learning algorithms including the least absolute shrinkage and selection operator (LASSO) regression, RandomForest (RF) and Recursive Feature Elimination (RFE), we developed a 12-gene transcriptomic score (EC_score) to predict the existence of ecDNA through RNA-seq. EC_score demonstrated reliable predictive performance in two independent cohorts (AUC > 0.70), validated by fluorescence in situ hybridization (FISH) in both cell lines and clinical samples. Next, we found that EC_score emerged as an independent adverse prognostic factor across multiple immunotherapy cohorts. Notably, high EC_score correlated with cell cycle activation and immunosuppression, characterized by reduced lymphocytes infiltration and upregulated immunosuppressive markers, including MHC molecules, co-inhibitory immune checkpoints and TGF-β signals. In general, we established and validated a 12-gene signature (EC_score) derived from RNA-seq, offering a novel computational tool for predicting the presence of extrachromosomal circular DNA and stratifying Cancer Immunotherapy response.

Keywords

Cancer immunotherapy; Extrachromosomal circular DNA (ecDNA); Immune infiltration; Machine learning; Oncogene amplification.

Figures
Products