Large-scale benchmark study of survival prediction methods using multi-omics data.
Large-scale benchmark study of survival prediction methods using multi-omics data.
复制标题
使用多组学数据进行生存预测方法的大规模基准研究。
DOI：
10.1093/bib/bbaa167
复制
发表时间：
2021-05-20
影响因子：
9.5
通讯作者：
Boulesteix AL
中科院分区：
文献类型：
--
作者：
Herrmann M;Probst P;Hornung R;Jurinovic V;Boulesteix AL
多组学数据，即包含不同类型高维分子变量的数据集，越来越多地被用于各种疾病的研究。然而，多组学数据在预测疾病结果（如生存时间）方面的有用性仍然存在问题。目前还不清楚哪种方法最适合推导这种预测模型。我们的目标是通过使用真实数据的大规模基准研究来给出这些问题的一些答案。来自机器学习和统计学的不同预测方法应用于来自数据库“癌症基因组图谱”（TCGA）的18个多组学癌症数据集（35至1000个观察值，多达10万个变量）。考虑的结果是（删减的）生存时间。对基于增强、惩罚回归和随机森林的11种方法进行了比较，包括考虑组学变量组结构的方法和不考虑组学变量组结构的方法。Kaplan-Meier估计和仅使用临床变量的Cox模型作为参考方法。采用多次5倍交叉验证对两种方法进行比较。Uno的c指数和综合Brier分数作为绩效指标。结果表明，考虑多组学结构的方法具有稍好的预测性能。考虑到这种结构可以保护低维组的预测信息-特别是临床变量-在预测过程中不被利用。此外，只有块森林方法平均优于Cox模型，而且仅略优于Cox模型。这表明，作为我们研究的副产品，在考虑的TCGA研究中，用于预测目的的多组学数据的效用是有限的。联系：moritz.herrmann@stat.uni-muenchen.de， +49 89 2180 3198补充信息：补充数据可在生物信息学在线简报中获得。所有的分析都可以使用Github上免费提供的R代码来重现。
Multi-omics data, that is, datasets containing different types of high-dimensional molecular variables, are increasingly often generated for the investigation of various diseases. Nevertheless, questions remain regarding the usefulness of multi-omics data for the prediction of disease outcomes such as survival time. It is also unclear which methods are most appropriate to derive such prediction models. We aim to give some answers to these questions through a large-scale benchmark study using real data. Different prediction methods from machine learning and statistics were applied on 18 multi-omics cancer datasets (35 to 1000 observations, up to 100 000 variables) from the database ‘The Cancer Genome Atlas’ (TCGA). The considered outcome was the (censored) survival time. Eleven methods based on boosting, penalized regression and random forest were compared, comprising both methods that do and that do not take the group structure of the omics variables into account. The Kaplan–Meier estimate and a Cox model using only clinical variables were used as reference methods. The methods were compared using several repetitions of 5-fold cross-validation. Uno’s C-index and the integrated Brier score served as performance metrics. The results indicate that methods taking into account the multi-omics structure have a slightly better prediction performance. Taking this structure into account can protect the predictive information in low-dimensional groups—especially clinical variables—from not being exploited during prediction. Moreover, only the block forest method outperformed the Cox model on average, and only slightly. This indicates, as a by-product of our study, that in the considered TCGA studies the utility of multi-omics data for prediction purposes was limited. Contact: moritz.herrmann@stat.uni-muenchen.de, +49 89 2180 3198 Supplementary information: Supplementary data are available at Briefings in Bioinformatics online. All analyses are reproducible using R code freely available on Github.
登录
查看更多内容
影响因子：
4
作者：
Boulesteix, Anne-Laure;Strobl, Carolin
通讯作者：
Strobl, Carolin
影响因子：
3
作者：
Couronné R;Probst P;Boulesteix AL
通讯作者：
Boulesteix AL
影响因子：
9.5
作者：
Castaldi, Peter J.;Dahabreh, Issa J.;Ioannidis, John P. A.
通讯作者：
Ioannidis, John P. A.
DOI：
10.1093/bioinformatics/btu279
发表时间：
2014-06-15
期刊：
Bioinformatics (Oxford, England)
影响因子：
--
作者：
Bernau C;Riester M;Boulesteix AL;Parmigiani G;Huttenhower C;Waldron L;Trippa L
通讯作者：
Trippa L
临床基因组模型的生存预测 - 一项比较研究。
影响因子：
3
作者：
Bøvelstad HM;Nygård S;Borgan O
通讯作者：
Borgan O