Thedinga Kristina, Herwig Ralf
Department of Computational Molecular Biology, Max-Planck-Institute for Molecular Genetics, Ihnestrasse 63-73, 14195 Berlin, Germany.
iScience. 2021 Dec 11;25(1):103617. doi: 10.1016/j.isci.2021.103617. eCollection 2022 Jan 21.
Predicting cancer survival from molecular data is an important aspect of biomedical research because it allows quantifying patient risks and thus individualizing therapy. We introduce XGBoost tree ensemble learning to predict survival from transcriptome data of 8,024 patients from 25 different cancer types and show highly competitive performance with state-of-the-art methods. To further improve plausibility of the machine learning approach we conducted two additional steps. In the first step, we applied pan-cancer training and showed that it substantially improves prognosis compared with cancer subtype-specific training. In the second step, we applied network propagation and inferred a pan-cancer survival network consisting of 103 genes. This network highlights cross-cohort features and is predictive for the tumor microenvironment and immune status of the patients. Our work demonstrates that pan-cancer learning combined with network propagation generalizes over multiple cancer types and identifies biologically plausible features that can serve as biomarkers for monitoring cancer survival.
从分子数据预测癌症存活率是生物医学研究的一个重要方面，因为它能够量化患者风险，从而实现治疗的个性化。我们引入XGBoost树集成学习方法，以根据来自25种不同癌症类型的8024名患者的转录组数据预测存活率，并展示出与最先进方法相比极具竞争力的性能。为了进一步提高机器学习方法的合理性，我们又进行了另外两个步骤。第一步，我们应用泛癌训练，并表明与癌症亚型特异性训练相比，它能显著改善预后。第二步，我们应用网络传播并推断出一个由103个基因组成的泛癌存活网络。该网络突出了跨队列特征，并且对患者的肿瘤微环境和免疫状态具有预测性。我们的工作表明，泛癌学习与网络传播相结合能够推广到多种癌症类型，并识别出生物学上合理的特征，这些特征可作为监测癌症存活率的生物标志物。
