The invention discloses a
medicine relocation system and method based on a
quantum graph Fourier
convolution network. The method comprises the following steps: integrating proteins, genes, microorganisms, metabolites, drugs, diseases and multi-source associated information of the proteins, the genes, the microorganisms, the metabolites, the drugs, the diseases to construct a heterogeneous biological information network and a local subgraph network; the method comprises the following steps: innovatively designing a
quantum graph Fourier
convolution network, extracting spectrum characteristics and
topological information of
protein,
gene,
microorganism,
metabolite,
medicine and
disease nodes from a heterogeneous biological information network, updating
medicine and
disease node information, and obtaining discriminative characteristic representation; a multi-layer sensor is used for learning and depicting medicine-
disease joint feature representation, and then the unknown
curative effect of the medicine is predicted. According to the method,
data mining and knowledge discovery are carried out based on the multi-source heterogeneous biological information network, the
quantum Fourier graph convolutional network is innovatively used for modeling the multi-source heterogeneous
biological network, high-order semantic dependence and a
global structure mode between drugs and diseases can be effectively extracted, the performance of a
drug relocation prediction system is improved, and the
system is suitable for large-scale popularization and application. And the method has good expandability and practical application prospects.