A protein-based classifier for differentiating follicular thyroid adenoma and carcinoma

作者：Yaoting Sun, He Wang, Li Lu, Jianbiao Wang, Jianbiao Wang, Wanyuan Chen, Li Peng, Pingping Hu, Jing Yu, Xue Cai, Nan Yao, Yan Zhou, Jiatong Wang, Jiatong Wang, Yingrui Wang, Liqin Qian, Weigang Ge, M S Chen, Feng Yang, Zhiqiang Gui, Wei Sun, Zhihong Wang, Minghua Ge, Yi He, Guangzhi Wang, Yongfu Zhao, Huanjie Chen, Xiaohong Wu, Yuxin Du, Wenjun Wei, Fan Wu, Dingcun Luo, Xiangfeng Lin, Haitao Zheng, Xin Zhu, Bei Wei, Jiafei Shen, Jincao Yao, Zhennan Yuan, Tong Liu, Jun Pan, Yi-Feng Zhang, Yangfan Lv, Qiao‐Nan Guo, Qi‐Jun Wu, Tingting Gong, Ting Chen, Shu Zheng, Jingqiang Zhu, Hanqing Liu, Chuang Chen, Hong Han, Sathiyamoorthy Selvarajan, Michael Mingzhao Xing, Kennichi Kakudo, Erik K. Alexander, Yijun Wu, Yu Wang, Dong Xu, Hao Zhang, Xiu Nie, Oi Lian Kon, N. Gopalakrishna Iyer, Zhiyan Liu, Yi Zhu, Haixia Guan, Tiannan Guo, We-TEC Investigators · 发表于：EMBO Molecular Medicine · 年份：2025 · DOI：10.1038/s44321-025-00242-2 · 被引用次数：3 · 研究领域：Thyroid Cancer Diagnosis and Treatment、Genetic factors in colorectal cancer、Ferroptosis and cancer prognosis

Differentiating follicular thyroid adenoma (FTA) from carcinoma (FTC) remains challenging due to similar histological features separate from invasion. This study developed and validated DNA- and/or protein-based classifiers. A total of 2443 thyroid samples from 1568 patients were obtained from 24 centers in China and Singapore. Next-generation sequencing of a 66-gene panel revealed 41 (62.1%) detectable genes, while 25 were not, showing similar alteration patterns with differing mutation frequencies. Proteomics quantified 10,336 proteins, with 187 dysregulated. A discovery protein-based XGBoost model achieved an AUROC of 0.899 (95% CI, 0.849-0.949), outperforming the gene-based model (AUROC 0.670 [95% CI, 0.612-0.729]). A subsequent 24-protein classifier, developed via targeted mass spectrometry and validated in three independent sets, showed high performance in retrospective cohorts (AUROC 0.871 [95% CI, 0.833-0.910] and 0.853 [95% CI, 0.772-0.934]) and prospective biopsies (AUROC 0.781 [95% CI, 0.563-1.000]). It exhibited a 95.7% negative predictive value for ruling out malignancy. This study presents a promising protein-based approach for the differential diagnosis of FTA and FTC, potentially enhancing diagnostic accuracy and clinical decision-making.