How deeply does Knowledge Graphs and LLMs in Action cover drug repurposing?

Explains motivation, graph schema, metapath features, DWPC calculations, and model objectives without detailing full model training.

Drug repurposing

As explained in Knowledge Graphs and LLMs in Action

Drug repurposing is the investigation of an existing drug for a new therapeutic use.

Drug repurposing investigates an existing drug for a new therapeutic use. It reduces the time, cost, and failure risk of developing treatments by reusing evidence from toxicology, preclinical models, clinical trials, and post-release surveillance. section 4.3

A knowledge-graph repurposing workflow proceeds through these stages:

Assemble a heterogeneous graph connecting compounds, diseases, genes, pathways, biological processes, anatomy, symptoms, side effects, and pharmacological classes. section 4.3
Represent each compound–disease pair with metapaths of lengths two to four, including binding, gene association, pathway participation, and anatomy relationships. section 10.2.2
Count paths and calculate degree-weighted path counts such as DWPC, reducing the influence of highly connected nodes. section 10.2.2
Train a machine-learning model to translate network connectivity into a probability that a compound treats a disease. section 10.2.2

Metformin and type 2 diabetes

A Cypher query matches metformin to type 2 diabetes mellitus through the Compound–binds–Gene–associates–Disease metapath, counts matching paths, and returns the path count and DWPC. Longer alternatives can traverse anatomy or biological pathways.

How Knowledge Graphs and LLMs in Action covers it

Cover of Knowledge Graphs and LLMs in Action

liveBook manning.com

Read Knowledge Graphs and LLMs in Action on liveBook Get the book at manning.com

Related concepts

link predictionuses · Link prediction is a graph-learning task that estimates whether a connection exists or may occur between nodes, often by scoring candidate links.
bipartite graphuses · A bipartite graph is a graph whose vertices can be partitioned into two disjoint sets, with edges only between the sets.
graph neural networkuses · A graph neural network is a neural-network model that learns representations or predictions from graph-structured data by combining information from connected entities.
graph databaseuses · A graph database is a database system that represents data as entities and their relationships, typically using nodes and edges, and supports queries over that structure.
knowledge graphused by · A knowledge graph is a graph-structured representation of entities and their semantically meaningful relationships, often including associated attributes or facts.

This explainer was generated by Manning's knowledge graph from the text of Knowledge Graphs and LLMs in Action. The section links point to the parts of the book it draws on.