DeepSynergy: predicting anti-cancer drug synergy with Deep Learning.
DeepSynergy: predicting anti-cancer drug synergy with Deep Learning.
复制标题
DOI：
10.1093/bioinformatics/btx806
复制
发表时间：
2018-05-01
期刊：
影响因子：
--
通讯作者：
Klambauer G
中科院分区：
文献类型：
--
作者：
Preuer K;Lewis RPI;Hochreiter S;Bender A;Bulusu KC;Klambauer G
虽然药物组合疗法在癌症治疗中是一个成熟的概念，但由于组合空间的大小，鉴定新的协同组合是具有挑战性的。然而，计算方法已经成为一种时间和成本效益的方式，优先组合测试，最近可用的大规模组合筛选数据的基础上。最近，深度学习通过实现新的最先进的模型性能在许多研究领域产生了影响。然而，深度学习尚未应用于药物协同预测，这是我们在这里提出的方法，称为DeepSynergy。DeepSynergy使用化学和基因组信息作为输入信息，使用归一化策略来解释输入数据的异质性，并使用锥形层来模拟药物协同作用。DeepSynergy与其他机器学习方法进行了比较，如梯度提升机，随机森林，支持向量机和弹性网络在最大的公开可用的协同数据集上的均方误差。DeepSynergy在预测探索药物和细胞系空间内的新型药物组合方面显著优于其他方法，比第二好的方法提高了7.2%。在该任务中，DeepSynergy的测量值和预测值之间的平均Pearson相关系数为0.73。将DeepSynergy应用于这些新型药物组合的分类，导致AUC为0.90的高预测性能。此外，我们发现，当外推到未开发的药物或细胞系时，所有比较的方法都表现出较低的预测性能，我们认为这是由于数据集的大小和多样性的限制。我们设想DeepSynergy可能是选择新型协同药物组合的有价值的工具。DeepSynergy可通过www.bioinf.jku.at/software/DeepSynergy获得。 补充数据可在Bioinformatics在线获得。
While drug combination therapies are a well-established concept in cancer treatment, identifying novel synergistic combinations is challenging due to the size of combinatorial space. However, computational approaches have emerged as a time- and cost-efficient way to prioritize combinations to test, based on recently available large-scale combination screening data. Recently, Deep Learning has had an impact in many research areas by achieving new state-of-the-art model performance. However, Deep Learning has not yet been applied to drug synergy prediction, which is the approach we present here, termed DeepSynergy. DeepSynergy uses chemical and genomic information as input information, a normalization strategy to account for input data heterogeneity, and conical layers to model drug synergies. DeepSynergy was compared to other machine learning methods such as Gradient Boosting Machines, Random Forests, Support Vector Machines and Elastic Nets on the largest publicly available synergy dataset with respect to mean squared error. DeepSynergy significantly outperformed the other methods with an improvement of 7.2% over the second best method at the prediction of novel drug combinations within the space of explored drugs and cell lines. At this task, the mean Pearson correlation coefficient between the measured and the predicted values of DeepSynergy was 0.73. Applying DeepSynergy for classification of these novel drug combinations resulted in a high predictive performance of an AUC of 0.90. Furthermore, we found that all compared methods exhibit low predictive performance when extrapolating to unexplored drugs or cell lines, which we suggest is due to limitations in the size and diversity of the dataset. We envision that DeepSynergy could be a valuable tool for selecting novel synergistic drug combinations. DeepSynergy is available via www.bioinf.jku.at/software/DeepSynergy. Supplementary data are available at Bioinformatics online.
登录
查看更多内容
ASDCD：抗真菌协同药物组合数据库
影响因子：
3.7
作者：
Chen X;Ren B;Chen M;Liu MX;Ren W;Wang QX;Zhang LX;Yan GY
通讯作者：
Yan GY
影响因子：
8.6
作者：
Hinselmann G;Rosenbaum L;Jahn A;Fechner N;Zell A
通讯作者：
Zell A
影响因子：
7.5
作者：
CORTES, C;VAPNIK, V
通讯作者：
VAPNIK, V
影响因子：
2.3
作者：
Guichard, S;Arnould, S;Canal, P
通讯作者：
Canal, P
影响因子：
45.3
作者：
Hecht, J. Randolph;Mitchell, Edith;Amado, Rafael G.
通讯作者：
Amado, Rafael G.