ideasIdea
An open knowledge graph linking trials, results, biomarkers, drugs and recommendations
Build a public, machine-readable map connecting every cancer trial to its results, the drugs and biomarkers involved, and the guideline recommendations it supports, with a source for every link.
Evidence in oncology is scattered across registries, papers, labels and guidelines with no shared identifiers. An open knowledge graph (trial identifiers, PICO elements, structured results, drug and biomarker ontologies, guideline recommendations, provenance for each edge) would let software answer 'what is the evidence for drug X in population Y' reproducibly. OncoKB, CIViC, Open Targets and ClinicalTrials.gov are partial graphs; the proposal funds their federation under open licences with a governance body and curation incentives.
Hypothesis
An open evidence graph will reduce the time to compile the evidence base for a guideline question from weeks of manual review to hours, and will be adopted as the backbone of at least three decision-support products within three years.
Rationale
Open Targets and Wikidata show that open, federated knowledge graphs with provenance attract community curation and become infrastructure; oncology's clinical evidence layer lacks one.
What would test it
Build the graph for two diseases from existing open sources; have guideline panels use it for one update cycle and measure time saved and errors found versus manual review.
Maturity
early clinical
Who has to act
philanthropy
Cost to try
Medium ($1M to $50M)
Years to first evidence
3
Bottlenecks it attacks
- Knowledge reaches practice too slowly · Knowledge diffusion is slow: it takes years for a proven result to change what most patients receive, and no one can keep up with the literature.
- Data silos · Records, scans, genomes and outcomes sit in separate systems that cannot talk. Every patient's experience is lost to the next.