{"entity":{"id":"idea-reg-preregistered-ai-repurposing-scoring","kind":"idea","name":"Pre-registered, publicly scored AI ranking of repurposing candidates for cancer","aka":[],"tldr":"AI systems claim to find new uses for old drugs, but their predictions are rarely tested fairly. Publish their cancer predictions in advance and score them against trial results.","summary":"Knowledge-graph and language-model approaches to repurposing (Every Cure, funded by ARPA-H; academic systems such as those built on Hetionet and Open Targets) generate ranked lists of drug-disease pairs, but their forward-looking accuracy in oncology is unknown because predictions are published selectively after the fact. The proposal is a public benchmark: each participating system deposits time-stamped ranked predictions for defined cancer indications; a neutral body scores them annually against subsequent randomised trial results and target trial emulations, and the repurposing fund preferentially trials candidates on which independent systems agree.","asOf":"2026-09-08","links":[{"label":"Bottleneck evidence (No incentive to repurpose cheap drugs): Pantziarka et al., The Repurposing Drugs in Oncology (ReDO) Project (ecancer 2014)","url":"https://doi.org/10.3332/ecancer.2014.442"}],"tags":[],"related":["open-targets","drugbank-chembl"],"cancers":[],"sections":[],"technologies":[],"targets":[],"drugs":[],"companies":[],"institutions":[],"pathways":[],"terms":[],"trials":[],"people":[],"bottlenecks":["b-generic-repurposing","b-ai-validation"],"keyPapers":["paper-pantziarka-ecancermedicalscience"],"journals":[],"dependsOn":[],"notes":[],"hypothesis":"Candidates ranked highly by at least two independent pre-registered systems have a positive-trial rate at least twice that of candidates selected by conventional literature review.","rationale":"Prospective, pre-registered evaluation is the only way to know whether these tools add value beyond the literature they were trained on; if they do, they should direct scarce trial funding, and if they do not, that should be known.","test":"Launch the benchmark with three systems and a five-year horizon; compare the fate of top-ranked candidates with a matched set chosen by expert panel.","maturity":"early-clinical","actor":"data","cost":"small","horizonYears":4},"route":"/ideas/idea-reg-preregistered-ai-repurposing-scoring/","neighbours":{"collection":[{"id":"drugbank-chembl","kind":"collection","name":"DrugBank & ChEMBL","route":"/collections/drugbank-chembl/"},{"id":"open-targets","kind":"collection","name":"Open Targets Platform","route":"/collections/open-targets/"}],"bottleneck":[{"id":"b-ai-validation","kind":"bottleneck","name":"AI that is built but not validated or deployed","route":"/bottlenecks/b-ai-validation/"},{"id":"b-generic-repurposing","kind":"bottleneck","name":"No incentive to repurpose cheap drugs","route":"/bottlenecks/b-generic-repurposing/"}],"paper":[{"id":"paper-pantziarka-ecancermedicalscience","kind":"paper","name":"The Repurposing Drugs in Oncology (ReDO) Project","route":"/key-papers/paper-pantziarka-ecancermedicalscience/"}]}}