Fusion network drug target relationship prediction method based on network enhancement and graph regularization

Abstract

The invention discloses a fusion network drug target relationship prediction method based on network enhancement and graph regularization. The method comprises the following steps of modeling a drug similar network and a protein similar network by using an undirected graph model; performing enhancement processing on the modeled drug similar network and protein similar network by using a network enhancement method based on three-order neighborhood random walk; extracting the enhanced similar network by using a similar matrix decomposition model with graph regularities to respectively obtain a drug network feature representation and a protein network feature representation; and training the prediction model, and inputting the drug network feature representation and the feature representationvector of the protein network into the trained prediction model to obtain a prediction value of the association probability of the drug target pair. According to the method, the global connection relationship between molecules can be better captured, the noise can be effectively suppressed, and robustness is higher when the molecular network data with different scales and different noise degreesare used for prediction.

Description

technical field [0001] The invention relates to the technical field of systems biology, and more specifically, to a method for predicting drug-target relationship in a fusion network based on network enhancement and graph regularization. Background technique [0002] Drug target identification is an important method in modern drug development. With the accumulation of a large amount of omics data by high-throughput technology, the use of machine learning methods to fuse multiple information and find drugs or proteins with similar functions has become an important means of drug target identification. The starting point for identifying drug-target associations through drug or protein similarity is that similar drugs tend to act on similar targets, and similar target proteins are more likely to bind similar drugs. The fusion model can integrate different information such as the chemical structure of the drug, drug efficacy, drug-disease association, protein sequence structure,...

AI Technical Summary

Problems solved by technology

[0007] In order to overcome the defects of incomplete extraction of molecular information in the network drug target relationship prediction method in the prior art, and the large noise of biological data affects the low prediction accuracy, the present invention provides a fusion network drug target based on network enhancement and graph regularization Relationship Prediction Methods

Images