primekg

Drug repurposing candidates are found by querying a biomedical knowledge graph for direct drug-disease associations. You can retrieve a disease's context summary to compile associated drugs, genes, and phenotypes, generating evidence-backed hypotheses for new uses.

Network pharmacology mapping works by retrieving direct associations between molecular targets and diseases within a biomedical knowledge graph. You locate a gene or drug node, pull its neighborhood to inspect relationship types, and trace paths to clinical disease outcomes.

Yes, you can query disease-gene associations locally using pandas. The system relies on local CSV-based knowledge graph access, allowing you to search nodes, retrieve neighbors, and summarize disease contexts directly without external API dependencies.

The best way to interpret phenotype-to-disease relationships is by querying a knowledge graph for direct associations. You can generate a disease context summary to compile associated phenotypes and related diseases, supporting precision medicine and mechanism interpretation.

To retrieve direct drug and gene associations, run a disease context summary workflow using the specific disease name. This queries the knowledge graph to compile associated genes, drugs, phenotypes, and related diseases in one shot using the disease name.