Ministry of Education Key Laboratory of Bioinformatics, Research Department of Bioinformatics, Beijing National Research Center, Information Science and Technology, Center for Synthetic and Systems Biology.
Department of Automation, Tsinghua University, Beijing 100084, China.
Bioinformatics. 2020 Dec 30;36(Suppl_2):i911-i918. doi: 10.1093/bioinformatics/btaa822.
Accurate prediction of cancer drug response (CDR) is challenging due to the uncertainty of drug efficacy and heterogeneity of cancer patients. Strong evidences have implicated the high dependence of CDR on tumor genomic and transcriptomic profiles of individual patients. Precise identification of CDR is crucial in both guiding anti-cancer drug design and understanding cancer biology.
In this study, we present DeepCDR which integrates multi-omics profiles of cancer cells and explores intrinsic chemical structures of drugs for predicting CDR. Specifically, DeepCDR is a hybrid graph convolutional network consisting of a uniform graph convolutional network and multiple subnetworks. Unlike prior studies modeling hand-crafted features of drugs, DeepCDR automatically learns the latent representation of topological structures among atoms and bonds of drugs. Extensive experiments showed that DeepCDR outperformed state-of-the-art methods in both classification and regression settings under various data settings. We also evaluated the contribution of different types of omics profiles for assessing drug response. Furthermore, we provided an exploratory strategy for identifying potential cancer-associated genes concerning specific cancer types. Our results highlighted the predictive power of DeepCDR and its potential translational value in guiding disease-specific drug design.
DeepCDR is freely available at https://github.com/kimmo1019/DeepCDR.
Supplementary data are available at Bioinformatics online.
由于药物疗效的不确定性和癌症患者的异质性，准确预测癌症药物反应 (CDR) 具有挑战性。有强有力的证据表明，CDR 高度依赖于个体患者的肿瘤基因组和转录组谱。精确识别 CDR 在指导抗癌药物设计和理解癌症生物学方面都至关重要。
在这项研究中，我们提出了 DeepCDR，它整合了癌细胞的多组学谱，并探索了药物的内在化学结构，以预测 CDR。具体来说，DeepCDR 是一个混合图卷积网络，由一个统一的图卷积网络和多个子网组成。与之前的研究不同，这些研究对药物的手工制作特征进行建模，DeepCDR 自动学习药物中原子和键之间拓扑结构的潜在表示。广泛的实验表明，在各种数据设置下，DeepCDR 在分类和回归设置中的表现均优于最先进的方法。我们还评估了不同类型的组学谱对评估药物反应的贡献。此外，我们提供了一种探索性策略，用于识别与特定癌症类型相关的潜在癌症相关基因。我们的结果强调了 DeepCDR 的预测能力及其在指导针对特定疾病的药物设计方面的潜在转化价值。
DeepCDR 可在 https://github.com/kimmo1019/DeepCDR 上免费获得。
补充数据可在生物信息学在线获得。
