A protein-protein interaction extraction approach based on deep neural network
A protein-protein interaction extraction approach based on deep neural network
复制标题
一种基于深度神经网络的蛋白质-蛋白质相互作用提取方法
DOI：
10.1504/ijdmb.2016.076534
复制
发表时间：
2016-01-01
影响因子：
0.3
通讯作者：
Gao, Song
中科院分区：
文献类型：
--
作者：
Zhao, Zhehuan;Yang, Zhihao;Gao, Song
蛋白质蛋白质相互作用（PPI）从生物医学文献中提取信息有助于揭示生物过程的分子机制。机器学习方法一直是PPI提取区域中最受欢迎的方法。但是，这些方法仍然基于工程功能，这意味着他们的性能也很大程度上取决于适当的功能选择，这仍然是一项与技能有关的任务。本文提出了一种基于神经网络的深度方法，可以通过无监督的表示方法自动学习复杂和抽象的特征。该方法首先采用自动编码器的培训算法来初始化深层神经网络的参数。然后，使用背部传播的梯度下降方法用于训练这种深层多层神经网络模型。五个公共PPI CORPORA的实验结果表明，我们的方法比多层神经网络可以取得更好的性能：在两个“最艰难的操控性” Corpor和Bioinfer上，前者的表现优于后者，而F-的改进为3.10和2.89个百分点。得分分别。此外，与APG的性能比较还验证了我们方法的有效性。
Protein-Protein Interactions (PPIs) information extraction from biomedical literature helps unveil the molecular mechanisms of biological processes. Machine learning methods have been the most popular ones in PPI extraction area. However, these methods are still feature engineering-based, which means that their performances are also heavily dependent on the appropriate feature selection which is still a skill-dependent task. This paper presents a deep neural network-based approach which can learn complex and abstract features automatically from unlabelled data by unsupervised representation learning methods. This approach first employs the training algorithm of auto-encoders to initialise the parameters of a deep multilayer neural network. Then the gradient descent method using back propagation is applied to train this deep multilayer neural network model. Experimental results on five public PPI corpora show that our method can achieve better performance than can a multilayer neural network: on two 'toughest handling' corpora AImed and BioInfer, the former outperforms the latter with the improvements of 3.10 and 2.89 percentage units in F-score, respectively. In addition, the performance comparison with APG also verifies the effectiveness of our method.