A trustworthy semantic knowledge network linking data-driven cell phenotypes to diseases and drugs

NLM-CKN links single-cell cell phenotypes to disease genes and drugs by integrating evidence across 88 datasets, covering 10 human organs and 2,585 cell sets.

• Why it matters: Genetic studies identify disease genes, but the cellular contexts where their proteins act are often unclear, and much single-cell knowledge stays trapped in separate datasets and papers.
• What they did: The project builds reproducible workflows for 2,585 cell sets and 5,139 selectively expressed genes, maps cell sets to Cell Ontology using experimental evidence, and loads triple assertions into ArangoDB with provenance.
• The result: Network topology analysis is used to infer cellular contributions to disease pathogenesis, therapeutic intervention contexts, and drug-repurposing hypotheses.

AI summary of the abstract · may contain errors · not medical advice · read the paper.