Tothill Richard W, Kowalczyk Adam, Rischin Danny, Bousioutas Alex, Haviv Izhak, van Laar Ryan K, Waring Paul M, Zalcberg John, Ward Robyn, Biankin Andrew V, Sutherland Robert L, Henshall Susan M, Fong Kwun, Pollack Jonathan R, Bowtell David D L, Holloway Andrew J
Ian Potter Centre for Cancer Genomics and Predictive Medicine, Department of Haematology and Medical Oncology, Peter MacCallum Cancer Centre, St. Andrew's Place, East Melbourne, Victoria, Australia.
Cancer Res. 2005 May 15;65(10):4031-40. doi: 10.1158/0008-5472.CAN-04-3617.
Gene expression profiling offers a promising new technique for the diagnosis and prognosis of cancer. We have applied this technology to build a clinically robust site of origin classifier with the ultimate aim of applying it to determine the origin of cancer of unknown primary (CUP). A single cDNA microarray platform was used to profile 229 primary and metastatic tumors representing 14 tumor types and multiple histologic subtypes. This data set was subsequently used for training and validation of a support vector machine (SVM) classifier, demonstrating 89% accuracy using a 13-class model. Further, we show the translation of a five-class classifier to a quantitative PCR-based platform. Selecting 79 optimal gene markers, we generated a quantitative-PCR low-density array, allowing the assay of both fresh-frozen and formalin-fixed paraffin-embedded (FFPE) tissue. Data generated using both quantitative PCR and microarray were subsequently used to train and validate a cross-platform SVM model with high prediction accuracy. Finally, we applied our SVM classifiers to 13 cases of CUP. We show that the microarray SVM classifier was capable of making high confidence predictions in 11 of 13 cases. These predictions were supported by comprehensive review of the patients' clinical histories.
基因表达谱分析为癌症的诊断和预后提供了一种有前景的新技术。我们已应用这项技术构建了一个临床稳健的原发部位分类器，最终目的是将其应用于确定原发灶不明癌症（CUP）的起源。使用单个cDNA微阵列平台对代表14种肿瘤类型和多种组织学亚型的229个原发性和转移性肿瘤进行分析。该数据集随后用于支持向量机（SVM）分类器的训练和验证，使用13类模型时准确率达89%。此外，我们展示了将五类分类器转化为基于定量PCR的平台。通过选择79个最佳基因标记，我们生成了一个定量PCR低密度阵列，可用于检测新鲜冷冻和福尔马林固定石蜡包埋（FFPE）组织。随后，使用定量PCR和微阵列生成的数据用于训练和验证具有高预测准确性的跨平台SVM模型。最后，我们将SVM分类器应用于13例CUP病例。我们发现微阵列SVM分类器能够对13例中的11例做出高置信度预测。这些预测得到了对患者临床病史的全面回顾的支持。
