Chu Thang, Nguyen Thuy Trang, Hai Bui Duong, Nguyen Quang Huy, Nguyen Tuan
IEEE/ACM Trans Comput Biol Bioinform. 2023 Mar-Apr;20(2):1065-1072. doi: 10.1109/TCBB.2022.3206888. Epub 2023 Apr 3.
Previous models have shown that learning drug features from their graph representation is more efficient than learning from their strings or numeric representations. Furthermore, integrating multi-omics data of cell lines increases the performance of drug response prediction. However, these models have shown drawbacks in extracting drug features from graph representation and incorporating redundancy information from multi-omics data. This paper proposes a deep learning model, GraTransDRP, to better drug representation and reduce information redundancy. First, the Graph transformer was utilized to extract the drug representation more efficiently. Next, Convolutional neural networks were used to learn the mutation, meth, and transcriptomics features. However, the dimension of transcriptomics features was up to 17737. Therefore, KernelPCA was applied to transcriptomics features to reduce the dimension and transform them into a dense presentation before putting them through the CNN model. Finally, drug and omics features were combined to predict a response value by a fully connected network. Experimental results show that our model outperforms some state-of-the-art methods, including GraphDRP and GraOmicDRP.
先前的模型表明，从药物的图形表示中学习药物特征比从其字符串或数字表示中学习更有效。此外，整合细胞系的多组学数据可提高药物反应预测的性能。然而，这些模型在从图形表示中提取药物特征以及合并多组学数据中的冗余信息方面存在缺陷。本文提出了一种深度学习模型GraTransDRP，以更好地表示药物并减少信息冗余。首先，利用图变换器更有效地提取药物表示。接下来，使用卷积神经网络来学习突变、甲基化和转录组学特征。然而，转录组学特征的维度高达17737。因此，在将转录组学特征输入CNN模型之前，应用核主成分分析（KernelPCA）对其进行降维并将其转换为密集表示。最后，通过全连接网络将药物和组学特征结合起来预测反应值。实验结果表明，我们的模型优于一些先进的方法，包括GraphDRP和GraOmicDRP。
