Zhang Xianyu, Zhao Dezhi, Yin Yanling, Yang Ting, You Zilong, Li Dalin, Chen Yanbo, Jiang Yongdong, Xu Shouping, Geng Jingshu, Zhao Yashuang, Wang Jun, Li Hui, Tao Jinsheng, Lei Shan, Jiang Zeyu, Chen Zhiwei, Yu Shihui, Fan Jian-Bing, Pang Da
Department of Breast Surgery, Harbin Medical University Cancer Hospital, Harbin, China.
Department of Research and Development, AnchorDx Medical Co., Ltd., Guangzhou, China.
NPJ Breast Cancer. 2021 Aug 16;7(1):106. doi: 10.1038/s41523-021-00316-7.
Mammography is used to detect breast cancer (BC), but its sensitivity is limited, especially for dense breasts. Circulating cell-free DNA (cfDNA) methylation tests is expected to compensate for the deficiency of mammography. We derived a specific panel of markers based on computational analysis of the DNA methylation profiles from The Cancer Genome Atlas (TCGA). Through training (n = 160) and validation set (n = 69), we developed a diagnostic prediction model with 26 markers, which yielded a sensitivity of 89.37% and a specificity of 100% for differentiating malignant disease from normal lesions [AUROC = 0.9816 (95% CI: 96.09-100%), and AUPRC = 0.9704 (95% CI: 94.54-99.46%)]. A simplified 4-marker model including cg23035715, cg16304215, cg20072171, and cg21501525 had a similar diagnostic power [AUROC = 0.9796 (95% CI: 95.56-100%), and AUPRC = 0.9220 (95% CI: 91.02-94.37%)]. We found that a single cfDNA methylation marker, cg23035715, has a high diagnostic power [AUROC = 0.9395 (95% CI: 89.72-99.27%), and AUPRC = 0.9111 (95% CI: 88.45-93.76%)], with a sensitivity of 84.90% and a specificity of 93.88%. In an independent testing dataset (n = 104), the obtained diagnostic prediction model discriminated BC patients from normal controls with high accuracy [AUROC = 0.9449 (95% CI: 90.07-98.91%), and AUPRC = 0.8640 (95% CI: 82.82-89.98%)]. We compared the diagnostic power of cfDNA methylation and mammography. Our model yielded a sensitivity of 94.79% (95% CI: 78.72-97.87%) and a specificity of 98.70% (95% CI: 86.36-100%) for differentiating malignant disease from normal lesions [AUROC = 0.9815 (95% CI: 96.75-99.55%), and AUPRC = 0.9800 (95% CI: 96.6-99.4%)], with better diagnostic power and had better diagnostic power than that of using mammography [AUROC = 0.9315 (95% CI: 89.95-96.34%), and AUPRC = 0.9490 (95% CI: 91.7-98.1%)]. In addition, hypermethylation profiling provided insights into lymph node metastasis stratifications (p < 0.05). In conclusion, we developed and tested a cfDNA methylation model for BC diagnosis with better performance than mammography.
乳腺钼靶摄影用于检测乳腺癌（BC），但其敏感性有限，尤其是对于致密型乳腺。循环游离DNA（cfDNA）甲基化检测有望弥补乳腺钼靶摄影的不足。我们基于对癌症基因组图谱（TCGA）DNA甲基化谱的计算分析得出了一组特定的标志物。通过训练集（n = 160）和验证集（n = 69），我们开发了一个包含26个标志物的诊断预测模型，该模型在区分恶性疾病与正常病变方面的敏感性为89.37%，特异性为100% [受试者工作特征曲线下面积（AUROC）= 0.9816（95%置信区间：96.09 - 100%），精确率曲线下面积（AUPRC）= 0.9704（95%置信区间：94.54 - 99.46%）]。一个简化的包含cg23035715、cg16304215、cg20072171和cg21501525这4个标志物的模型具有相似的诊断能力[AUROC = = 0.9796（95%置信区间：95.56 - 100%），AUPRC = 0.9220（95%置信区间：91.02 - 94.37%）]。我们发现单个cfDNA甲基化标志物cg23035715具有较高的诊断能力[AUROC = 0.9395（95%置信区间：89.72 - 99.27%），AUPRC = 0.9111（95%置信区间：88.45 - 93.76%）]，敏感性为84.90%，特异性为93.88%。在一个独立测试数据集（n = 104）中，所获得的诊断预测模型能够高精度地区分BC患者与正常对照[AUROC = 0.9449（95%置信区间：90.07 - 98.91%），AUPRC = 0.8640（95%置信区间：82.82 - 89.98%）]。我们比较了cfDNA甲基化和乳腺钼靶摄影的诊断能力。我们的模型在区分恶性疾病与正常病变方面的敏感性为94.79%（95%置信区间：78.72 - 97.87%），特异性为98.70%（95%置信区间：86.36 - 100%）[AUROC = 0.9815（95%置信区间：96.75 - 99.55%），AUPRC = 0.9800（95%置信区间：96.6 - 99.4%）]，具有比乳腺钼靶摄影更好的诊断能力[AUROC = 0.9315（95%置信区间：89.95 - 96.34%），AUPRC = 0.9490（95%置信区间：91.7 - 98.1%）]。此外，高甲基化谱分析为淋巴结转移分层提供了见解（p < 0.05）。总之，我们开发并测试了一种用于BC诊断的cfDNA甲基化模型，其性能优于乳腺钼靶摄影。
