Integration of multiple types of genetic markers for neuroblastoma may contribute to improved prediction of the overall survival.
Integration of multiple types of genetic markers for neuroblastoma may contribute to improved prediction of the overall survival.
复制标题
DOI：
10.1186/s13062-018-0222-9
复制
发表时间：
2018-09-20
期刊：
影响因子：
5.5
通讯作者：
Rudnicki WR
中科院分区：
文献类型：
--
作者：
Polewko-Klim A;Lesiński W;Mnich K;Piliszek R;Rudnicki WR
现代实验技术提供的数据集包含数万种潜在的分子和遗传标记，可用于改善医学诊断。以前的研究用三种不同的实验方法对同一组神经母细胞瘤患者进行了研究，以检查是否用拷贝数变异的信息增强基因表达谱可以改善患者生存的预测。我们提出了基于综合交叉验证协议的方法，包括交叉验证循环内的特征选择和使用机器学习的分类。我们还使用四种不同的特征选择方法测试结果对特征选择过程的依赖性。利用基于信息熵选择的特征的模型略好于使用t检验获得的特征的模型。遗传变异和基因表达数据之间的协同作用是可能的，但尚未得到证实。对于基于组合数据集构建的模型，已经观察到机器学习模型的预测能力略有增加，但具有统计学意义。它被发现，同时使用袋外估计和交叉验证进行一组变量。然而，当模型在包括交叉验证循环内的特征选择的完整交叉验证程序内构建时，改进较小且不显著。在内部和外部交叉验证中观察到模型性能之间的良好相关性，证实了拟定方案和结果的稳健性。我们已经开发了一种用于构建预测机器学习模型的协议。该协议可以提供对未知数据的模型性能的鲁棒估计。它特别适合于小数据集。我们已经应用该协议开发神经母细胞瘤的预后模型，使用拷贝数变异和基因表达的数据。我们已经证明，结合这两种信息来源可以提高模型的质量。然而，增加是小的，并且需要更大的样本来减少由于过拟合而产生的噪声和偏差。本文由Lan Hu、Tim Beissbarth和Dimitar Vassilev审阅。
Modern experimental techniques deliver data sets containing profiles of tens of thousands of potential molecular and genetic markers that can be used to improve medical diagnostics. Previous studies performed with three different experimental methods for the same set of neuroblastoma patients create opportunity to examine whether augmenting gene expression profiles with information on copy number variation can lead to improved predictions of patients survival. We propose methodology based on comprehensive cross-validation protocol, that includes feature selection within cross-validation loop and classification using machine learning. We also test dependence of results on the feature selection process using four different feature selection methods. The models utilising features selected based on information entropy are slightly, but significantly, better than those using features obtained with t-test. The synergy between data on genetic variation and gene expression is possible, but not confirmed. A slight, but statistically significant, increase of the predictive power of machine learning models has been observed for models built on combined data sets. It was found while using both out of bag estimate and in cross-validation performed on a single set of variables. However, the improvement was smaller and non-significant when models were built within full cross-validation procedure that included feature selection within cross-validation loop. Good correlation between performance of the models in the internal and external cross-validation was observed, confirming the robustness of the proposed protocol and results. We have developed a protocol for building predictive machine learning models. The protocol can provide robust estimates of the model performance on unseen data. It is particularly well-suited for small data sets. We have applied this protocol to develop prognostic models for neuroblastoma, using data on copy number variation and gene expression. We have shown that combining these two sources of information may increase the quality of the models. Nevertheless, the increase is small and larger samples are required to reduce noise and bias arising due to overfitting. This article was reviewed by Lan Hu, Tim Beissbarth and Dimitar Vassilev.
登录
查看更多内容
影响因子：
48
作者：
Huber W;Carey VJ;Gentleman R;Anders S;Carlson M;Carvalho BS;Bravo HC;Davis S;Gatto L;Girke T;Gottardo R;Hahne F;Hansen KD;Irizarry RA;Lawrence M;Love MI;MacDonald J;Obenchain V;Oleś AK;Pagès H;Reyes A;Shannon P;Smyth GK;Tenenbaum D;Waldron L;Morgan M
通讯作者：
Morgan M
影响因子：
4.5
作者：
Chicco D
通讯作者：
Chicco D
影响因子：
11
作者：
Esposito MR;Aveic S;Seydel A;Tonini GP
通讯作者：
Tonini GP
影响因子：
3
作者：
Kursa MB
通讯作者：
Kursa MB
影响因子：
6.4
作者：
Coco, Simona;Theissen, Jessica;Tonini, Gian Paolo
通讯作者：
Tonini, Gian Paolo