Traditional Chinese medicine prescription relocation method based on heterogeneous network representation learning

Abstract

The invention discloses a traditional Chinese medicine prescription relocation method based on heterogeneous network representation learning. The method sequentially comprises the following steps: step 1, carrying out preprocessing on input data, and constructing a traditional Chinese medicine prescription heterogeneous network; step 2, according to a heterogeneous graph embedding method, learning semantic association information in the traditional Chinese medicine prescription heterogeneous network by executing a network pharmacology learning module, and acquiring embedded representations of the traditional Chinese medicine prescription and the disease; and step 3, according to the embedded representation of the traditional Chinese medicine prescription and the disease obtained in the step 2, using a deep learning recommendation algorithm to obtain an interactive influence score matrix of the two, and finally, sorting scoring matrix results to obtain a disease recommendation result of the Top@K of the traditional Chinese medicine prescription. According to the invention, the disease recommendation of the traditional Chinese medicine prescription can be obtained through intelligent calculation, manual operation is avoided, and the efficiency of traditional Chinese medicine prescription relocation is effectively improved.

Description

technical field [0001] The invention relates to a method for relocating traditional Chinese medicine prescriptions, in particular to a method for relocating traditional Chinese medicine prescriptions based on heterogeneous network representation learning. Background technique [0002] Drug repositioning aims to find new applications for existing drugs, and has the advantages of low waste rate, reduced cost and short time, which has attracted the attention of many researchers. Although there is a lot of research work on the repositioning of western medicines, in view of the characteristics of "multi-components, multi-targets, and multi-path regulation" in traditional Chinese medicine prescriptions, the repositioning method of western medicines cannot be directly applied to the repositioning of traditional Chinese medicine prescriptions. In addition, although some scholars have used network pharmacology to study the relocation of traditional Chinese medicine prescriptions, the...

AI Technical Summary

Problems solved by technology

[0003] Purpose of the invention: The purpose of the present invention is to propose a Heterogeneous Network Pharmacology Learning for Prescriptions Repositioning of Traditional Chinese Medicine based on the problem that existing feature generation methods cannot handle irrelevant or redundant generation features. , HNPL), using a heterogeneous network representation learning method

Images