Data Integration Using Tensor Decomposition for The Prediction of miRNA-Disease Associations
首发时间:2021-05-24
Abstract:Dysfunction of miRNAs has an important relationship with diseases by impacting their target genes. Identifying disease-related miRNAs is of great significance to prevent and treat diseases. Integrating information of genes related miRNAs and/or diseases in calculational methods for miRNA-disease association studies is meaningful because of the complexity of biological mechanisms. Therefore, it is helpful to integrate multi-type data for identifying pathogenic miRNAs. In this paper, a novel data fusion method based on tensor decomposition is proposed, termed TDMDA, for the prediction of potential miRNA-disease associations. First, a three-order association tensor was constructed to express the associations of miRNA-disease pairs, the associations of miRNA-gene pairs, and the associations of gene-disease pairs simultaneously. Then, a method based on tensor decomposition is applied to fuse multiple data and reconstruct the association tensor for predicting miRNA-disease associations. The fused data includes biological similarity information and adjacency information. The performance of TDMDA is compared with other advanced methods under 5-fold cross-validations. The experimental results indicate the TDMDA is a competitive method.
keywords: Bioinformatics pathogenic miRNAs association prediction tensor decomposition data integration
点击查看论文中文信息
基于张量分解的数据融合方法用于miRNA-疾病关联预测
摘要:miRNA功能失调通过影响靶基因的表达而进而影响疾病。识别与疾病相关的miRNA对预防和治疗疾病具有重要意义。由于生物机制的复杂性,将与miRNA和/或疾病相关的基因信息整合到miRNA-疾病关联研究的计算方法中是有意义的。因此,整合多种类型的数据有助于寻找潜在的致病性miRNA。本文提出了一种基于张量分解的数据融合方法,TDMDA,用于预测潜在的miRNA-疾病关联。首先,本文构建了一个三阶关联张量用于同时表示miRNA-疾病对的关联信息,miRNA-基因对的关联信息和基因-疾病对的关联信息。然后,本文采用基于张量分解的方法融合多种数据,重构用于预测miRNA-疾病关联程度的关联张量,融合的数据有生物学相似性信息和邻接信息。在5折交叉验证实验中,将TDMDA的性能与其他先进方法进行了对比。实验结果表明,TDMDA是一种具有竞争力方法。
基金:
引用
No.****
同行评议
勘误表
基于张量分解的数据融合方法用于miRNA-疾病关联预测
评论
全部评论0/1000