Greenberg Jacques A, Shah Yajas, Ivanov Nikolay A, Marshall Teagan, Kulm Scott, Williams Jelani, Tran Catherine, Scognamiglio Theresa, Heymann Jonas J, Lee-Saxton Yeon J, Egan Caitlin, Majumdar Sonali, Min Irene M, Zarnegar Rasa, Howe James, Keutgen Xavier M, Fahey Thomas J, Elemento Olivier, Finnerty Brendan M
Department of Surgery, Weill Cornell Medicine, New York, NY 10065, USA.
Caryl and Israel Englander Institute for Precision Medicine, Weill Cornell Medicine, Cornell University, New York, NY, 10065, USA.
J Clin Endocrinol Metab. 2024 Dec 18;110(1):263-274. doi: 10.1210/clinem/dgae380.
Pancreatic neuroendocrine tumors (PNETs) exhibit a wide range of behavior from localized disease to aggressive metastasis. A comprehensive transcriptomic profile capable of differentiating between these phenotypes remains elusive.
Use machine learning to develop predictive models of PNET metastatic potential dependent upon transcriptomic signature.
RNA-sequencing data were analyzed from 95 surgically resected primary PNETs in an international cohort. Two cohorts were generated with equally balanced metastatic PNET composition. Machine learning was used to create predictive models distinguishing between localized and metastatic tumors. Models were validated on an independent cohort of 29 formalin-fixed, paraffin-embedded samples using NanoString nCounter®, a clinically available mRNA quantification platform.
Gene expression analysis identified concordant differentially expressed genes between the 2 cohorts. Gene set enrichment analysis identified additional genes that contributed to enriched biologic pathways in metastatic PNETs. Expression values for these genes were combined with an additional 7 genes known to contribute to PNET oncogenesis and prognosis, including ARX and PDX1. Eight specific genes (AURKA, CDCA8, CPB2, MYT1L, NDC80, PAPPA2, SFMBT1, ZPLD1) were identified as sufficient to classify the metastatic status with high sensitivity (87.5-93.8%) and specificity (78.1-96.9%). These models remained predictive of the metastatic phenotype using NanoString nCounter® on the independent validation cohort, achieving a median area under the receiving operating characteristic curve of 0.886.
We identified and validated an 8-gene panel predictive of the metastatic phenotype in PNETs, which can be detected using the clinically available NanoString nCounter® system. This panel should be studied prospectively to determine its utility in guiding operative vs nonoperative management.
胰腺神经内分泌肿瘤（PNETs）的行为表现范围广泛，从局限性疾病到侵袭性转移。能够区分这些表型的全面转录组图谱仍然难以捉摸。
利用机器学习开发基于转录组特征的PNET转移潜能预测模型。
分析了来自国际队列中95例手术切除的原发性PNET的RNA测序数据。生成了两个转移PNET组成均衡的队列。使用机器学习创建区分局限性和转移性肿瘤的预测模型。使用临床可用的mRNA定量平台NanoString nCounter®，在29个福尔马林固定、石蜡包埋样本的独立队列上对模型进行验证。
基因表达分析确定了两个队列之间一致的差异表达基因。基因集富集分析确定了其他有助于转移性PNET中生物途径富集的基因。这些基因的表达值与另外7个已知与PNET肿瘤发生和预后相关的基因（包括ARX和PDX1）相结合。确定了8个特定基因（AURKA、CDCA8、CPB2、MYT1L、NDC80、PAPPA2、SFMBT1、ZPLD1）足以以高灵敏度（87.5 - 93.8%）和特异性（78.1 - 96.9%）对转移状态进行分类。使用NanoString nCounter®在独立验证队列上，这些模型仍然能够预测转移表型，在接受者操作特征曲线下的中位数面积达到0.886。
我们鉴定并验证了一个8基因panel，可预测PNET的转移表型，该表型可使用临床可用的NanoString nCounter®系统检测。应前瞻性地研究该panel，以确定其在指导手术与非手术治疗管理中的效用。
