European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Hinxton, Cambridgeshire, UK.
Cancer Research UK Cambridge Institute, University of Cambridge, Li Ka Shing Centre, Robinson Way, Cambridge, UK.
Nat Commun. 2021 Feb 18;12(1):1137. doi: 10.1038/s41467-021-21207-2.
Adjuvant systemic therapies are now routinely used following resection of stage III melanoma, however accurate prognostic information is needed to better stratify patients. We use differential expression analyses of primary tumours from 204 RNA-sequenced melanomas within a large adjuvant trial, identifying a 121 metastasis-associated gene signature. This signature strongly associated with progression-free (HR = 1.63, p = 5.24 × 10) and overall survival (HR = 1.61, p = 1.67 × 10), was validated in 175 regional lymph nodes metastasis as well as two externally ascertained datasets. The machine learning classification models trained using the signature genes performed significantly better in predicting metastases than models trained with clinical covariates (p = 7.03 × 10), or published prognostic signatures (p < 0.05). The signature score negatively correlated with measures of immune cell infiltration (ρ = -0.75, p < 2.2 × 10), with a higher score representing reduced lymphocyte infiltration and a higher 5-year risk of death in stage II melanoma. Our expression signature identifies melanoma patients at higher risk of metastases and warrants further evaluation in adjuvant clinical trials.
辅助全身治疗现在已常规用于 III 期黑色素瘤切除术后，但需要准确的预后信息来更好地分层患者。我们使用来自大型辅助试验的 204 个 RNA 测序黑色素瘤的原发肿瘤差异表达分析，确定了 121 个与转移相关的基因特征。该特征与无进展生存（HR=1.63，p=5.24×10）和总生存（HR=1.61，p=1.67×10）强烈相关，在 175 个区域淋巴结转移和另外两个外部确定的数据集得到验证。使用特征基因训练的机器学习分类模型在预测转移方面明显优于使用临床协变量（p=7.03×10）或已发表的预后特征（p<0.05）训练的模型。该特征评分与免疫细胞浸润的衡量标准呈负相关（ρ=-0.75，p<2.2×10），评分越高代表淋巴细胞浸润减少，II 期黑色素瘤患者的 5 年死亡率越高。我们的表达特征确定了具有更高转移风险的黑色素瘤患者，值得在辅助临床试验中进一步评估。
