<p>Oxaliplatin-based chemotherapy is a standard treatment for metastatic colorectal cancer (mCRC), yet accurate biomarkers to identify responders remain lacking. In this study, we developed and validated a genomic copy number alteration (CNA)-based biomarker to predict clinical response to oxaliplatin-based chemotherapy. A total of 297 samples were collected, and shallow sequencing was employed to extract CNA features. The resulting model named “CNA fingerprint” is an XGBoost model trained using 7 CNA features. The model was validated across three independent test cohorts from two centers, achieving area under the receiver operating characteristic curve (AUC) of 0.87, 0.87, and 0.85, respectively. The primary predictor was the number of DNA segments with high absolute copy numbers. Our findings suggest that the CNA fingerprint could be used as biomarker for oxaliplatin-based chemotherapy response prediction in mCRC. Further prospective clinical trials are warranted to evaluate CNA fingerprint’s performance in clinical applications.</p>

错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

Copy number alteration fingerprint predicts the clinical response of oxaliplatin-based chemotherapy in metastatic colorectal cancer

  • Junyong Weng,
  • Jinyu Wang,
  • Ziyu Tao,
  • Tao Wu,
  • Kaixuan Diao,
  • Jiexuan Wang,
  • Nan Wang,
  • Zilan Ye,
  • Ruoxin Zhang,
  • Jiayu Shen,
  • Xiangyu Zhao,
  • XinXing Li,
  • Xinxiang Li,
  • Xue-Song Liu

摘要

Oxaliplatin-based chemotherapy is a standard treatment for metastatic colorectal cancer (mCRC), yet accurate biomarkers to identify responders remain lacking. In this study, we developed and validated a genomic copy number alteration (CNA)-based biomarker to predict clinical response to oxaliplatin-based chemotherapy. A total of 297 samples were collected, and shallow sequencing was employed to extract CNA features. The resulting model named “CNA fingerprint” is an XGBoost model trained using 7 CNA features. The model was validated across three independent test cohorts from two centers, achieving area under the receiver operating characteristic curve (AUC) of 0.87, 0.87, and 0.85, respectively. The primary predictor was the number of DNA segments with high absolute copy numbers. Our findings suggest that the CNA fingerprint could be used as biomarker for oxaliplatin-based chemotherapy response prediction in mCRC. Further prospective clinical trials are warranted to evaluate CNA fingerprint’s performance in clinical applications.