CGBVS-DNN: Prediction of Compound-protein Interactions Based on Deep Learning
CGBVS-DNN: Prediction of Compound-protein Interactions Based on Deep Learning
复制标题
DOI：
10.1002/minf.201600045
复制
发表时间：
2017-01-01
影响因子：
3.6
通讯作者：
Okuno, Yasushi
中科院分区：
文献类型：
--
作者：
Hamanaka, Masatoshi;Taneishi, Kei;Okuno, Yasushi
化合物-蛋白质相互作用的计算预测作为计算机筛选的第一步，对药物设计具有重要意义。我们以前提出了基于化学基因组学的虚拟筛选（CGBVS），它通过使用支持向量机（SVM）预测CPI。然而，CGBVS在使用超过一百万个CPI数据集进行训练时存在问题，因为SVM需要计算时间和计算机内存的指数增长。为了解决这个问题，我们提出了CGBVS-DNN，其中我们使用深度神经网络，一种深度学习技术，而不是SVM。深度学习不需要一次学习所有输入数据，因为网络可以用小批量训练。实验结果表明，CGBVS-DNN优于原始CGBVS，具有25万个CPI。交叉验证结果表明，CGBVS-DNN的准确率达到98.2%（s
Computational prediction of compound-protein interactions (CPIs) is of great importance for drug design as the first step in in-silico screening. We previously proposed chemical genomics-based virtual screening (CGBVS), which predicts CPIs by using a support vector machine (SVM). However, the CGBVS has problems when training using more than a million datasets of CPIs since SVMs require an exponential increase in the calculation time and computer memory. To solve this problem, we propose the CGBVS-DNN, in which we use deep neural networks, a kind of deep learning technique, instead of the SVM. Deep learning does not require learning all input data at once because the network can be trained with small mini-batches. Experimental results show that the CGBVS-DNN outperformed the original CGBVS with a quarter million CPIs. Results of cross-validation show that the accuracy of the CGBVS-DNN reaches up to 98.2% (s