Multi-source information medicine screening method based on knowledge graph

Abstract

The invention belongs to the technical field of medicine screening, and discloses a multi-source information medicine screening method based on a knowledge graph, which comprises the following steps of: fusing multisource heterogeneous data sources; optimizing a molecular structure; optimizing a scoring process architecture; carrying out molecular docking and scoring; constructing a knowledge graph entity; constructing a knowledge graph entity association relationship; screening retrieval. According to the method, optimized three-dimensional molecular structures, scored and screened molecularinformation and other information are organized into the knowledge graph, and loop retrieval is performed in the knowledge graph, so that drug screening is more efficient and higher in accuracy.

Description

technical field [0001] The invention belongs to the technical field of drug screening, in particular to a multi-source information drug screening method based on a knowledge graph. Background technique [0002] The knowledge graph is essentially a semantic network, a graph-based data structure consisting of nodes (Point) and edges (Edge). In the knowledge graph, each node represents an "entity" that exists in the real world, and each edge is a "relationship" between entities. Knowledge graphs are the most effective representation of relationships. In layman's terms, a knowledge graph is a relational network obtained by connecting all different types of information (Heterogeneous Information). The knowledge graph provides the ability to analyze problems from the perspective of "relationship". The application field of knowledge graph is constantly expanding and the effect achieved is amazing. [0003] Multi-source heterogeneous data means that the data describing the same ...

AI Technical Summary

Problems solved by technology

[0006] 1. Traditional docking methods based on receptors or ligands only consider the structural information of the target and the compound, ignoring the non-structural information and the extended information between the ligands, resulting in the accuracy of the docking results and reliability is greatly reduced

[0007] 2. When there are many molecules, it is difficult to select molecules according to the docking score

For high-throughput virtual screening, it is often possible to generate a large number of screening results. Using a single feature for screening, the corresponding time cost is too high and the accuracy is not high. Therefore, for a large number of screening results obtained, how to further screen efficiently becomes a question

[0008] 3. The existing virtual screening method only generates a scoring result, which is only used in this screening stage and is not strongly related to the subsequent steps of drug development

Images