结合图自动编码器和结构化注意力机制的miRNA-疾病关联预测方法

Structural Attention Mechanism Auto-encoder for miRNA-disease Association Prediction

MicroRNA(miRNA)-疾病关联预测的研究有助于人类进行疾病预防、诊断和治疗等,许多研究人员开发出了基于图自动编码器的miRNA-疾病关联预测方法,然而大多数编码器方法在对中心节点编码的时候并没有考虑到邻居节点之间的差异。因此,本文提出一种结合图自动编码器和结构化注意力机制的miRNA-疾病关联预测方法(SAAE)。SAAE模型使用基于图神经网络的编码器,该编码器采用多个编码层堆叠的方式以探索多阶邻居的信息。为了将中心节点与邻居节点不同权重的特征信息进行融合并捕获节点在图中的高阶结构信息,引进结构化注意力机制对图节点的原始信息进行编码,以生成新的特征信息。随后,通过解码器进行解码,解码后的特征信息使用随机森林算法挖掘miRNA和疾病节点之间的潜在联系。实验结果表明,SAAE在5倍交叉验证的曲线下的平均面积为94.53%。此外,本文还进行了关于肾脏肿瘤和肺部肿瘤的2个案例研究,验证了SAAE预测的有效性。

Research on MicroRNA(miRNA)-disease association prediction is helpful for human disease prevention,diagnosis and treatment,etc.Many researchers have developed miRNA-disease association prediction methods based on graph autoencoder.However,most of the auto-encoder methods do not consider the difference between neighbor nodes when coding the central node.Therefore,this paper proposes a new method called structural attention mechanism auto-encoder for miRNAdisease association prediction(SAAE).The SAAE model uses an encoder based on graph neural network,which uses multiple coding layers to explore the information of multi-order neighbors.In order to fuse the feature information of the central node and the neighbor node with different weights and capture the structure information of the node in the graph,the structured attention mechanism is introduced in the coding layer to encode the original information of the graph node to generate new feature informa⁃tion.Subsequently,the decoding is performed by a decoder,and the decoded feature information is mined for potential associa⁃tions between miRNA and disease nodes using a random forest algorithm.The experimental results show that the average area un⁃der the curve of SAAE under five-fold cross validation is 94.53%.In addition,two case studies on kidney tumors and lungtumors were conducted to verify the validity of SAAE prediction.