Eutectic Prediction Method and Application Based on Three-Dimensional Substructure-Intermolecular Interaction Network

CN115394372BActive Publication Date: 2026-05-26EAST CHINA UNIV OF SCI & TECH

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
EAST CHINA UNIV OF SCI & TECH
Filing Date
2022-07-21
Publication Date
2026-05-26

AI Technical Summary

Technical Problem

Existing eutectic prediction methods ignore the three-dimensional structural information of compounds, resulting in low efficiency and insufficient success rate in eutectic development, and the experimental screening process consumes a lot of resources and time.

Method used

A co-crystallization prediction model based on a three-dimensional substructure-intermolecular interaction network is constructed, integrating the three-dimensional structural information of the compound and the intermolecular interaction network, and using a weighted third-order path algorithm to evaluate the probability of co-crystallization ligands.

Benefits of technology

It improves the efficiency and success rate of eutectic development, reduces the blindness and waste of resources in experimental screening, provides accurate eutectic ligand recommendations, and has good predictive performance and generalization ability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115394372B_ABST
    Figure CN115394372B_ABST
Patent Text Reader

Abstract

This invention discloses a method and application for cocrystal prediction based on a three-dimensional substructure-intermolecular interaction network, including constructing an intermolecular interaction network, constructing a compound-three-dimensional substructure network, constructing a three-dimensional substructure-intermolecular interaction network, and constructing a prediction model based on a weighted network algorithm. The introduction of the three-dimensional substructure allows the prediction model to use the compound's three-dimensional structural information for cocrystal prediction, and the weighted network method enables the prediction model to distinguish between different types of connections within the network. Using this prediction method for cocrystal design and preparation can significantly reduce trial-and-error experiments in cocrystal screening, thereby saving experimental resources and reducing waste of manpower and resources. Applying this prediction method in practice yielded an isoimperatorin-salicylic acid cocrystal, which effectively improved the drug's water solubility. This invention's prediction method can predict cocrystal ligands for drugs or other types of compounds, providing guidance for cocrystal development.
Need to check novelty before this filing date? Find Prior Art