Disease-microorganism association prediction system based on projection and comparative learning

Abstract

The invention provides a disease-microorganism association prediction system based on projection and comparative learning, and the system comprises a data obtaining module which is configured to obtain disease and microorganism parameter data; the unweighted projection module is configured to perform unweighted projection on a bipartite network constructed according to the parameter data to obtain a disease-disease association and a disease-microorganism association; the feature extraction module is configured to obtain disease features according to disease-disease association and disease association graph comparative learning, and obtain microorganism features according to disease-microorganism association and microorganism association graph comparative learning; the association prediction module is configured to obtain a disease-microorganism association prediction result according to the disease characteristics, the microorganism characteristics and a preset full-connection network model; according to the invention, based on projection and graph mutual information comparison learning, faster and more accurate prediction of disease-microorganism association is realized.

Description

technical field [0001] The invention relates to the technical field of disease, in particular to a disease-microbe association prediction system based on projection and contrast learning. Background technique [0002] The statements in this section merely provide background art related to the present invention and do not necessarily constitute prior art. [0003] The microbes that colonize the human body have a crucial impact on human health, and the discovery of disease-associated microbes will facilitate the discovery of biomarkers and drugs. However, clinical trials of disease-microbe associations are time-consuming, laborious, and expensive, and there are few methods for predicting potential microbe-disease associations. [0004] Traditional disease-microbe association (Disease-Microbe Association, DMA) detection methods are observed through a large number of clinical trials. Not only is it costly and time-consuming, it is sometimes impossible to achieve. At present, ...

AI Technical Summary

Problems solved by technology

[0008] (3) Compared with the unknown associations of disease microorganisms, there are relatively few known associations, that is, the disease-microbe association network is relatively sparse, which has an extremely adverse impact on the prediction of DMA

Images