Drug repurposing
Drug repurposing is the investigation or use of an existing drug for a therapeutic indication different from its original use.
Build AI Drug Discovery Pipelines
Drug repurposing is the identification of new therapeutic uses for an existing drug outside its original medical indication.
- How it is used
- Uses unsupervised learning to identify candidate therapeutic uses for existing compounds from high-dimensional screening and drug-library data.
- How deep it goes
- Explains clinical motivation and a fingerprint-to-SOM workflow, but stops short of clinical validation and therapeutic confirmation.
- Examples
- Uses minoxidil, COVID Moonshot screening data, Drug Repurposing Hub compounds, and retrospective SOM hits as examples.
- What you can do after
- Apply Morgan fingerprints and self-organizing maps to prioritize existing compounds for experimental repurposing studies.
Read how Build AI Drug Discovery Pipelines explains drug repurposing →
Knowledge Graphs and LLMs in Action
Drug repurposing is the investigation of an existing drug for a new therapeutic use.
- How it is used
- Uses biomedical knowledge graphs to rank possible new treatments for diseases using existing drugs.
- How deep it goes
- Explains motivation, graph schema, metapath features, DWPC calculations, and model objectives without detailing full model training.
- Examples
- Uses Hetionet, metformin, type 2 diabetes mellitus, and metapaths through genes, anatomy, and pathways.
- What you can do after
- Evaluate candidate drug–disease treatments by engineering metapath features and querying path counts and DWPC scores.
Read how Knowledge Graphs and LLMs in Action explains drug repurposing →
Also covered in
What to know first
- molecular targetA molecular target is a biological molecule whose activity or binding is modulated by a drug or other compound.
- recommender systemA recommender system is a computational system that predicts, selects, or ranks items, content, or actions for users based on available information.
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 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.
- 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.
- knowledge graphused by · A knowledge graph is a graph-structured representation of entities and their semantically meaningful relationships, often including associated attributes or facts.
Questions about drug repurposing
What is drug repurposing?
Drug repurposing is the investigation or use of an existing drug for a therapeutic indication different from its original use.
Which Manning books explain drug repurposing?
Build AI Drug Discovery Pipelines and Knowledge Graphs and LLMs in Action.
What should I know before learning drug repurposing?
Manning books that teach drug repurposing usually introduce clinical trial, molecular target and recommender system first.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.

