Nature Medicine ( IF 58.7 ) Pub Date : 2023-08-07 , DOI: 10.1038/s41591-023-02482-6
Intae Moon 1, 2 , Jaclyn LoPiccolo 3 , Sylvan C Baca 3, 4 , Lynette M Sholl 5 , Kenneth L Kehl 2 , Michael J Hassett 2 , David Liu 2, 3, 6 , Deborah Schrag 7 , Alexander Gusev 2, 6, 8
|
Cancer of unknown primary (CUP) is a type of cancer that cannot be traced back to its primary site and accounts for 3–5% of all cancers. Established targeted therapies are lacking for CUP, leading to generally poor outcomes. We developed OncoNPC, a machine-learning classifier trained on targeted next-generation sequencing (NGS) data from 36,445 tumors across 22 cancer types from three institutions. Oncology NGS-based primary cancer-type classifier (OncoNPC) achieved a weighted F1 score of 0.942 for high confidence predictions (\(\ge 0.9\)) on held-out tumor samples, which made up 65.2% of all the held-out samples. When applied to 971 CUP tumors collected at the Dana-Farber Cancer Institute, OncoNPC predicted primary cancer types with high confidence in 41.2% of the tumors. OncoNPC also identified CUP subgroups with significantly higher polygenic germline risk for the predicted cancer types and with significantly different survival outcomes. Notably, patients with CUP who received first palliative intent treatments concordant with their OncoNPC-predicted cancers had significantly better outcomes (hazard ratio (HR) = 0.348; 95% confidence interval (CI) = 0.210–0.570; P = \(2.32\times {10}^{-5}\)). Furthermore, OncoNPC enabled a 2.2-fold increase in patients with CUP who could have received genomically guided therapies. OncoNPC thus provides evidence of distinct CUP subgroups and offers the potential for clinical decision support for managing patients with CUP.
中文翻译:

机器学习用于未知原发癌的基于遗传学的分类和治疗反应预测
原发性不明癌症 (CUP) 是一种无法追溯到其原发部位的癌症,占所有癌症的 3-5%。缺乏针对 CUP 的既定靶向治疗,导致结果普遍不佳。我们开发了 OncoNPC,这是一种机器学习分类器,根据来自三个机构 22 种癌症类型的 36,445 个肿瘤的靶向下一代测序 (NGS) 数据进行训练。基于肿瘤学 NGS 的原发性癌症类型分类器 (OncoNPC) 在保留的肿瘤样本上实现了高置信度预测 (\(\ge 0.9\)) 的加权 F1 评分 (\(\ge 0.9\)),占所有保留样本的 65.2%。当应用于 Dana-Farber 癌症研究所收集的 971 例 CUP 肿瘤时,OncoNPC 预测原发性癌症类型,对 41.2% 的肿瘤具有高置信度。OncoNPC 还确定了 CUP 亚组,对于预测的癌症类型,多基因种系风险显著升高,并且生存结果显著不同。值得注意的是,接受与 OncoNPC 预测的癌症一致的首次姑息性治疗的 CUP 患者预后显著更好(风险比 (HR) = 0.348;95% 置信区间 (CI) = 0.210–0.570;P=\(2.32\times {10}^{-5}\))。此外,OncoNPC 使本可以接受基因组指导治疗的 CUP 患者增加了 2.2 倍。因此,OncoNPC 提供了不同 CUP 亚组的证据,并为管理 CUP 患者提供了临床决策支持的潜力。