Drug target relationship prediction method and device, computer equipment and storage medium

Abstract

The embodiment of the invention discloses a drug target relationship prediction method and device, computer equipment and a storage medium, and belongs to the technical field of machine learning. The method comprises the following steps: determining a target drug molecule and a target protein; obtaining a target drug identifier corresponding to the target drug molecule and a target protein identifier corresponding to the target protein; and performing interaction relationship prediction based on the target drug identifier, the target protein identifier and the knowledge graph to obtain a relationship prediction result. At least one kind of omics data is introduced, the knowledge graph is formed in combination with the known drug target interaction pair, and drug target relationship prediction is performed based on the knowledge graph, so that information sources of relationship prediction are enriched, the defect that relationship prediction is performed only by depending on known prior knowledge such as drug protein interaction is overcome, and the prediction accuracy of the correlation between the drug molecules and the proteins is improved.

Description

technical field [0001] The embodiments of the present application relate to the technical field of machine learning, and in particular to a drug-target relationship prediction method, device, computer equipment and storage medium. Background technique [0002] Drug-Target Interaction (DTI) prediction is an important research field in drug discovery, and it plays a vital role in the development of new drugs, such as virtual drug screening, new use of old drugs, and research on toxic and side effects of drugs. Due to the constraints of accuracy, throughput and cost, traditional drug target verification methods based on biological experiments are usually difficult to carry out. Therefore, predicting the interaction of drug targets through computational simulation can reduce the blindness of new drug development and reduce R&D costs. [0003] In related technologies, neural network models for predicting drug-target interactions mainly include descriptor-based drug-target interac...

AI Technical Summary

Problems solved by technology

[0004] However, the drug target prediction models based on machine learning in related technologies are extremely dependent on prior knowledge. When there is a cold start of the drug or protein, the prediction performance of the model will drop significantly.

Images