Comparison of RNA-seq and microarray-based models for clinical endpoint prediction.
Comparison of RNA-seq and microarray-based models for clinical endpoint prediction.
复制标题
RNA-seq 和基于微阵列的临床终点预测模型的比较。
DOI：
10.1186/s13059-015-0694-1
复制
发表时间：
2015-06-25
期刊：
影响因子：
12.3
通讯作者：
Fischer M
中科院分区：
文献类型：
--
作者：
Zhang W;Yu Y;Hertwig F;Thierry-Mieg J;Zhang W;Thierry-Mieg D;Wang J;Furlanello C;Devanarayan V;Cheng J;Deng Y;Hero B;Hong H;Jia M;Li L;Lin SM;Nikolsky Y;Oberthuer A;Qing T;Su Z;Volland R;Wang C;Wang MD;Ai J;Albanese D;Asgharzadeh S;Avigad S;Bao W;Bessarabova M;Brilliant MH;Brors B;Chierici M;Chu TM;Zhang J;Grundy RG;He MM;Hebbring S;Kaufman HL;Lababidi S;Lancashire LJ;Li Y;Lu XX;Luo H;Ma X;Ning B;Noguera R;Peifer M;Phan JH;Roels F;Rosswog C;Shao S;Shen J;Theissen J;Tonini GP;Vandesompele J;Wu PY;Xiao W;Xu J;Xu W;Xuan J;Yang Y;Ye Z;Dong Z;Zhang KK;Yin Y;Zhao C;Zheng Y;Wolfinger RD;Shi T;Malkas LH;Berthold F;Wang J;Tong W;Shi L;Peng Z;Fischer M
基因表达谱在癌症研究中被广泛应用于识别生物标志物以预测临床终点。由于RNA-seq为基于转录组的应用提供了一个强大的工具，超越了微阵列的局限性，我们试图在MAQC-III/SEQC研究中系统地评估基于RNA-seq和基于微阵列的分类器的性能，以神经母细胞瘤为模型进行临床终点预测。我们使用RNA-seq和44k芯片从498个原发性神经母细胞瘤中生成基因表达谱。通过RNA-seq对神经母细胞瘤转录组的表征显示，超过48,000个基因和200,000个转录本在这种恶性肿瘤中表达。我们还发现，RNA-seq在临床遗传神经母细胞瘤亚群中提供了比微阵列更详细的转录物表达模式信息。为了系统地比较RNA-seq和基于微阵列的模型在预测临床终点方面的能力，我们将队列随机分为训练组和验证组，并针对六个不同可预测性的临床终点开发了360个预测模型。对可能影响模型性能的因素的评估表明，预测准确性受临床终点的性质影响最大，而技术平台（RNA-seq vs.微阵列）、RNA-seq数据分析管道和特征水平（基因、转录本、外显子连接水平）对模型的性能没有显著影响。我们证明，RNA-seq在确定癌症转录组学特征方面优于微阵列，而RNA-seq和基于微阵列的模型在临床终点预测方面表现相似。我们的研究结果可能对指导未来基于基因表达的预测模型的发展及其在临床实践中的应用有价值。本文的在线版本（doi:10.1186/s13059-015-0694-1）包含补充材料，可供授权用户使用。
Gene expression profiling is being widely applied in cancer research to identify biomarkers for clinical endpoint prediction. Since RNA-seq provides a powerful tool for transcriptome-based applications beyond the limitations of microarrays, we sought to systematically evaluate the performance of RNA-seq-based and microarray-based classifiers in this MAQC-III/SEQC study for clinical endpoint prediction using neuroblastoma as a model. We generate gene expression profiles from 498 primary neuroblastomas using both RNA-seq and 44 k microarrays. Characterization of the neuroblastoma transcriptome by RNA-seq reveals that more than 48,000 genes and 200,000 transcripts are being expressed in this malignancy. We also find that RNA-seq provides much more detailed information on specific transcript expression patterns in clinico-genetic neuroblastoma subgroups than microarrays. To systematically compare the power of RNA-seq and microarray-based models in predicting clinical endpoints, we divide the cohort randomly into training and validation sets and develop 360 predictive models on six clinical endpoints of varying predictability. Evaluation of factors potentially affecting model performances reveals that prediction accuracies are most strongly influenced by the nature of the clinical endpoint, whereas technological platforms (RNA-seq vs. microarrays), RNA-seq data analysis pipelines, and feature levels (gene vs. transcript vs. exon-junction level) do not significantly affect performances of the models. We demonstrate that RNA-seq outperforms microarrays in determining the transcriptomic characteristics of cancer, while RNA-seq and microarray-based models perform similarly in clinical endpoint prediction. Our findings may be valuable to guide future studies on the development of gene expression-based predictive models and their implementation in clinical practice. The online version of this article (doi:10.1186/s13059-015-0694-1) contains supplementary material, which is available to authorized users.