Compound combination screening method based on anti-parasitic infection key genes

Abstract

The invention discloses a compound combination screening method based on anti-parasitic infection key genes, which comprises the following steps of: 1, preprocessing biological data, constructing a single-layer difference interaction network for each individual infected by parasites, connecting gene nodes corresponding to a plurality of single-layer networks constructing a multi-layer gene interaction network, realizing fusion of multiple networks, calculating scores of genes in each layer of network by using a PageRank algorithm of the multi-layer network, and sorting and screening key genes by using average scores of corresponding same genes in all layers; and 2, designing a multi-objective optimization function model based on the key genes, known FDA approved compounds and a target gene set of each compound, and obtaining a better compound combination by using a multi-objective optimization algorithm. According to the invention, the time efficiency of screening the compound combination for resisting parasitic infection can be improved, and a better compound combination can be screened out.

Description

technical field [0001] The invention belongs to the field of biological information mining, in particular to a compound combination screening method based on key genes of anti-parasitic infection. Background technique [0002] The action of a single compound on a single gene target will not have a large effect against parasitic infection, and may even activate other factors that cause the compound to lose its effect or produce adverse reactions. Two or more compounds are often used in combination to achieve the purpose of enhancing the anti-parasitic infection effect or reducing adverse reactions. Compared with traditional single-component, single-gene-targeted compounds, the compound combination has the characteristics of multiple components and multiple gene targets, which can be more effective against parasitic infection. [0003] Existing methods for screening compound combinations mainly involve high-throughput screening and machine learning. The disadvantages of the t...

AI Technical Summary

Problems solved by technology

In the face of a large number of compounds, there is a problem of combinatorial explosion, and the efficiency of screening compound combinations is low and consumes huge manpower, material and financial resources;

[0005] 2. Machine learning refers to the training of models based on similar weights or other properties of compounds. Model training requires a large amount of known compound combination data as the basis, but the current public compound combination data is limited, which is not conducive to model training

Images