Method for predicting miRNA-disease association relationship based on graph neural network

Abstract

The invention provides a method for predicting a miRNA-disease association relationship based on a graph neural network. The method comprises the following implementation steps: acquiring miRNA-disease association data; constructing a miRNA-disease association network; acquiring a sample data set and a label data set; extracting an h-order closed subgraph of each miRNA-disease node pair; acquiring a node feature matrix of each h-order closed sub-graph; obtaining a training sample set, a training sample label data set and a predicted sample set; building a graph neural network; performing iterative training on the graph neural network; and obtaining a miRNA-disease associated prediction result. According to the method, the graph structure feature information is learned from the miRNA-disease association network by using the graph neural network, so that the problem of low prediction accuracy in the prior art is solved, the miRNA-disease association prediction accuracy is improved under the condition of not using similarity data, and the method can be used for predicting potential miRNA-disease association.

Description

technical field [0001] The invention belongs to the technical field of biological information, and relates to a method for predicting miRNA-disease correlation, in particular to a graph neural network-based prediction method for miRNA-disease correlation. Background technique [0002] miRNA is a class of non-coding single-stranded RNA molecules composed of 20-25 nucleotides. microRNA can participate in a wide range of important biological processes and play the role of feedback mechanism, such as cell division, differentiation, apoptosis, cell cycle regulation, inflammation and stress response. Disregulation of miRNA (including expression disorder, function increase or decrease mutation, epigenetic silencing, etc.) often leads to abnormal biological levels in the human body and leads to the occurrence of many diseases. Therefore, identifying disease-associated miRNAs can improve human understanding of complex diseases. [0003] Using the method of biological experiments to...

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to overcome the deficiencies of the above-mentioned prior art, and propose a miRNA-disease correlation prediction method based on graph neural network, which is used to solve the technical problem of low prediction accuracy existing in the prior art

Images