Drug interaction prediction method based on double-view graph neural network

Through a method based on a dual-view graph neural network, combining the molecular structure and chemical substructure information of the drug, adaptively captures the key substructure of drug interactions, solving the limitations of DDI prediction in the prior art and achieving more efficient and accurate drug interaction prediction.

CN119694442APending Publication Date: 2025-03-25HENAN UNIVERSITY
4 Cites 3 Cited by

Patent Information

Application Number
CN202411791068.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-12-06
Publication Date
2025-03-25

AI Technical Summary

Technical Problem

The prior art has limitations in predicting drug-drug interactions (DDIs), such as relying on a large number of biological experiments, time-consuming, high cost and limited sensitivity and specificity.

Method used

Using a method based on a dual-view graph neural network, combining the molecular structure information and chemical substructure information of the drug, the key substructure of interaction between the two drugs is adaptively captured through the directional message delivery neural network and the graph attention network with the substructure attention mechanism, and the interaction score between each pair of substructures between the two drugs is calculated through the self-attention graph pooling layer, thereby predicting the interaction probability between the two drugs.

Benefits of technology

It improves the accuracy and robustness of drug interaction prediction, simplifies the drug development process, and provides a safer drug combination.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a drug interaction prediction method based on a double-view graph neural network, and the method comprises the steps: extracting features in a single drug view in a self-adaptive manner through a directional message passing neural network with a substructure attention mechanism, and extracting interaction features between the drug and the view through a graph attention network; and fusing to generate drug substructure features, so as to more accurately predict the interaction between drugs. And through the common attention mechanism module, drug interaction is converted into pairwise interaction between drug substructures, so that the capability of capturing drug molecular characteristics is greatly enhanced, and the prediction precision is improved. The invention can make full use of the interaction information between drugs and the interaction information of chemical substructures, studies the classification and identification problem of drug interaction prediction, and provides an efficient drug interaction prediction method.
Need to check novelty before this filing date? Find Prior Art