▎ 摘　　要

NOVELTY - Method comprises collecting known drug target interaction data, drug chemical structure information, target amino acid sequence information and target protein graphene oxide information. Drug chemical structure similarity and drug Gaussian interaction spectrum profile similarity are obtained. A non-linear multi-source data fusion model is established. A drug target double-layer network model is constructed. A drug target network structure disturbance model is established. Potential drug target interaction is predicted. A final result is obtained. USE - Drug target interaction prediction method based on multi-source data fusion and network structure disturbance. ADVANTAGE - The method enables capturing drug target network link generation mechanism rule to identify potential drug target interaction. The method enables predicting drug target interaction based on multi-source data fusion link disturbance in a feasible and efficient manner. The method enables realizing precise medical treatment.