A gene expression signature identifies two prognostic subgroups of basal breast cancer
A gene expression signature identifies two prognostic subgroups of basal breast cancer
复制标题
DOI：
10.1007/s10549-010-0897-9
复制
发表时间：
2011-04-01
影响因子：
3.8
通讯作者：
Bertucci, Francois
中科院分区：
文献类型：
--
作者：
Sabatier, Renaud;Finetti, Pascal;Bertucci, Francois
基底乳腺癌的预后较差但具有异质性。髓样乳腺癌（MBC）表现出基础特征，但预后良好。我们假设先前发表的与 MBC 相关的 368 个基因表达特征可能有助于定义基底癌的预后分类器。我们收集了 2145 例侵袭性早期乳腺癌的公共基因表达和组织临床数据。我们基于学习集中的 368 个基因列表开发了支持向量机 (SVM) 分类器，并在独立验证集中测试了其预测性能。然后，我们评估了其预后价值以及其余 2034 个样本中无病生存 (DFS) 的六种预后特征。 SVM 模型对学习和验证集中的所有 MBC 样本进行了准确分类。共有 466 个病例是其他组的基础病例。 SVM 分类器将它们分为两个子组：子组 1（类似于 MBC）和子组 2（不类似于 MBC）。亚组 1 的 5 年 DFS 率为 71%，而亚组 2 为 50% (P = 9.93E-05)。该分类器在多变量分析中优于经典预后变量，使亚组 1 的复发风险较低（HR = 0.52，P = 3.9E-04）。该预后值特定于基础亚型，其中其他预后特征均不提供信息。本体分析显示，在预后良好的亚组中，有效的免疫反应（IR）、肿瘤细胞凋亡增强、转移抑制因子水平升高和转移促进因子水平较低，而在预后不良的亚组中，细胞迁移系统更加发达。总之，基于源自 MBC 特征的 368 基因 SVM 模型，基底乳腺癌被分为两个预后亚组，表明 MBC 和基底乳腺癌具有与侵袭性相关的相似分子改变。这一特征可以帮助定义预后、调整全身治疗并确定新的治疗靶点。
Prognosis of basal breast cancers is poor but heterogeneous. Medullary breast cancers (MBC) display a basal profile, but a favorable prognosis. We hypothesized that a previously published 368-gene expression signature associated with MBC might serve to define a prognostic classifier in basal cancers. We collected public gene expression and histoclinical data of 2145 invasive early breast adenocarcinomas. We developed a Support Vector Machine (SVM) classifier based on this 368-gene list in a learning set, and tested its predictive performances in an independent validation set. Then, we assessed its prognostic value and that of six prognostic signatures for disease-free survival (DFS) in the remaining 2034 samples. The SVM model accurately classified all MBC samples in the learning and validation sets. A total of 466 cases were basal across other sets. The SVM classifier separated them into two subgroups, subgroup 1 (resembling MBC) and subgroup 2 (not resembling MBC). Subgroup 1 exhibited 71% 5-year DFS, whereas subgroup 2 exhibited 50% (P = 9.93E-05). The classifier outperformed the classical prognostic variables in multivariate analysis, conferring lesser risk for relapse in subgroup 1 (HR = 0.52, P = 3.9E-04). This prognostic value was specific to the basal subtype, in which none of the other prognostic signatures was informative. Ontology analysis revealed effective immune response (IR), enhanced tumor cell apoptosis, elevated levels of metastasis-inhibiting factors and low levels of metastasis-promoting factors in the good-prognosis subgroup, and a more developed cell migration system in the poor-prognosis subgroup. In conclusion, based on this 368-gene SVM model derived from an MBC signature, basal breast cancers were classified in two prognostic subgroups, suggesting that MBC and basal breast cancers share similar molecular alterations associated with aggressiveness. This signature could help define the prognosis, adapt the systemic treatment, and identify new therapeutic targets.