Parvizi Poorya, Azuaje Francisco, Theodoratou Evropi, Luz Saturnino
Annu Int Conf IEEE Eng Med Biol Soc. 2020 Jul;2020:5304-5307. doi: 10.1109/EMBC44109.2020.9176165.
Integration of multi-omics and pharmacological data can help researchers understand the impact of drugs on dynamic biological systems. Network-based approaches to such integration explore the interaction of different cellular components and drugs. However, with ever-increasing amounts of data, processing these high-dimensional biological networks requires powerful tools. We investigate whether network embeddings can address this problem by providing an effective method for dimensionality reduction in drug-related networks. A neural network-based embedding method is employed to encode protein-protein, protein-disease, drug-drug and drug-disease networks for the prediction of novel drug-target interactions. We found that drug-target interaction prediction using embeddings of heterogeneous networks as input features performs comparably to state-of-the-art methods, exhibiting an area under the ROC curve of 84%, outperforming methods such as BLM-NII and NetLapRLS, and coming very close to the best performing network methods such as HNM, CMF and DTINet. These encouraging results suggest that further investigation of this approach is warranted.
多组学和药理学数据的整合有助于研究人员了解药物对动态生物系统的影响。基于网络的整合方法探索不同细胞成分与药物之间的相互作用。然而，随着数据量的不断增加，处理这些高维生物网络需要强大的工具。我们研究网络嵌入是否可以通过提供一种有效的药物相关网络降维方法来解决这个问题。采用基于神经网络的嵌入方法对蛋白质-蛋白质、蛋白质-疾病、药物-药物和药物-疾病网络进行编码，以预测新的药物-靶点相互作用。我们发现，使用异质网络嵌入作为输入特征的药物-靶点相互作用预测与现有方法表现相当，ROC曲线下面积为84%，优于BLM-NII和NetLapRLS等方法，并且非常接近HNM、CMF和DTINet等表现最佳的网络方法。这些令人鼓舞的结果表明，有必要对这种方法进行进一步研究。
