Sun Yaoting, Wang He, Li Lu, Wang Jianbiao, Chen Wanyuan, Peng Li, Hu Pingping, Yu Jing, Cai Xue, Yao Nan, Zhou Yan, Wang Jiatong, Wang Yingrui, Qian Liqin, Ge Weigang, Chen Mengni, Yang Feng, Gui Zhiqiang, Sun Wei, Wang Zhihong, Ge Minghua, He Yi, Wang Guangzhi, Zhao Yongfu, Chen Huanjie, Wu Xiaohong, Du Yuxin, Wei Wenjun, Wu Fan, Luo Dingcun, Lin Xiangfeng, Zheng Haitao, Zhu Xin, Wei Bei, Shen Jiafei, Yao Jincao, Yuan Zhennan, Liu Tong, Pan Jun, Zhang Yifeng, Lv Yangfan, Guo Qiaonan, Wu Qijun, Gong Tingting, Chen Ting, Zheng Shu, Zhu Jingqiang, Liu Hanqing, Chen Chuang, Han Hong, Selvarajan Sathiyamoorthy, Xing Michael Mingzhao, Kakudo Kennichi, Alexander Erik K, Wu Yijun, Wang Yu, Xu Dong, Zhang Hao, Nie Xiu, Kon Oi Lian, Iyer N Gopalakrishna, Liu Zhiyan, Zhu Yi, Guan Haixia, Guo Tiannan
Affiliated Hangzhou First People's Hospital, State Key Laboratory of Medical Proteomics, School of Medicine, Westlake University, No. 18 Shilongshan Road, Hangzhou, 310024, China.
Westlake Centre for Intelligent Proteomics, Westlake Laboratory of Life Sciences and Biomedicine, No. 600 Dunyu Road, Hangzhou, 310030, China.
EMBO Mol Med. 2025 May 29. doi: 10.1038/s44321-025-00242-2.
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.
由于滤泡性甲状腺腺瘤（FTA）和滤泡癌（FTC）的组织学特征相似，且与侵袭无关，因此将两者区分开来仍然具有挑战性。本研究开发并验证了基于DNA和/或蛋白质的分类器。从中国和新加坡的24个中心收集了1568例患者的2443份甲状腺样本。对一个包含66个基因的基因 panel 进行二代测序，发现41个（62.1%）可检测基因，25个不可检测基因，它们显示出相似的改变模式，但突变频率不同。蛋白质组学定量了10336种蛋白质，其中187种失调。基于发现蛋白质的XGBoost模型的曲线下面积（AUROC）为0.899（95%置信区间，0.849 - 0.949），优于基于基因的模型（AUROC 0.670 [95%置信区间，0.612 - 0.729]）。随后通过靶向质谱法开发并在三个独立数据集上验证的24蛋白分类器，在回顾性队列（AUROC 0.871 [95%置信区间，0.833 - 0.910]和0.853 [95%置信区间，0.772 - 0.934]）和前瞻性活检（AUROC 0.781 [95%置信区间，0.5
