Supplementary Table 7_Manuscript.xlsx

Context: 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.<br>Objective: Use machine learning to develop predictive models of PNET metastatic potential dependent upon transcriptomic signature.<br>Methods: 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.<br><br>Results: Gene expression analysis identified concordant differentially expressed genes between the two 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 AUROC of 0.886.<br><br>Conclusions: We identified and validated an eight-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 versus non-operative management.

研究背景：胰腺神经内分泌肿瘤（Pancreatic neuroendocrine tumors, PNETs）的生物学行为跨度极大，从局限性病变到侵袭性转移均有表现，目前仍缺乏可有效区分此类不同表型的全面转录组学特征。<br>研究目标：借助机器学习方法，基于转录组学特征构建胰腺神经内分泌肿瘤转移潜能的预测模型。<br>研究方法：对国际队列中95例经手术切除的原发性胰腺神经内分泌肿瘤的RNA测序（RNA-sequencing）数据进行分析，构建了两个转移瘤组成比例均衡的队列；采用机器学习算法构建区分局限性肿瘤与转移性肿瘤的预测模型，并利用临床可用的mRNA定量平台NanoString nCounter®，在包含29例福尔马林固定石蜡包埋（formalin-fixed, paraffin-embedded）样本的独立验证队列中对模型进行验证。<br>研究结果：基因表达分析在两个队列中鉴定出了一致的差异表达基因；基因集富集分析进一步鉴定出参与转移性胰腺神经内分泌肿瘤富集生物学通路的其他基因。将上述基因的表达值与另外7种已知参与胰腺神经内分泌肿瘤发生及预后的基因（包括ARX与PDX1）进行整合，最终筛选出8个特异性基因（AURKA、CDCA8、CPB2、MYT1L、NDC80、PAPPA2、SFMBT1、ZPLD1），仅依靠这些基因即可对转移状态进行分类，其灵敏度达87.5%~93.8%，特异性达78.1%~96.9%。在独立验证队列中，利用NanoString nCounter®平台检测上述基因表达，模型仍可有效预测转移表型，受试者工作特征曲线下面积（Area Under the Receiver Operating Characteristic Curve, AUROC）中位数达0.886。<br>研究结论：本研究鉴定并验证了一款可预测胰腺神经内分泌肿瘤转移表型的8基因检测组合，该组合可通过临床可用的NanoString nCounter®平台完成检测。未来可开展前瞻性研究以评估该组合在指导手术与非手术治疗方案选择中的应用价值。