question · intermediate · partly written
Has any top prediction from a public biomedical graph been tested prospectively?
No prospective test of a top prediction from Hetionet, PrimeKG, SPOKE or the Translator graphs was found.
What was searched and found more
The Rephetio authors close by saying additional studies will be needed to test the predictions; 3,394 candidates sit above 1% probability. A screen of 27 citing papers by abstract found none testing a Rephetio top prediction (not all read in full). A 2026 preprint reporting that 6 of its top 14 predictions are confirmed checked old indications against current labels, and its own limitations say a random split was used for drug-indication prediction while its abstract says temporal; it is not peer reviewed and is not clinical impact. The Translator review states it did not provide evidence of clinical benefit. 12
Reported, not yet replicated
The one documented proprietary case more
BenevolentAI's graph flagged baricitinib for 2019-nCoV; the letter was written by company staff and states it is not medical advice. Whether the graph was needed is untested; later trial figures were not opened here and are unverified. 3
Reported, not yet replicated
Still open here
- Is there a systematic tally of prospectively confirmed knowledge-graph predictions? None was found. Google Scholar and one journal page were not reachable, so "none found" is not "none exists".
Not yet written: Observation, Hypotheses, What is missing, What is known, What is not, What would settle it, Who works on it.
Linked from
Sources
- Himmelstein DS, Lizee A, Hessler C, et al.. Systematic integration of biomedical knowledge prioritizes drugs for repurposing. eLife 6:e26726 (2017). paper; opened 2026-11-18 all records citing this
- Biomedical Data Translator Consortium. Progress toward a universal biomedical data translator. Clinical and Translational Science (2022). paper; opened 2026-11-18 all records citing this
- Richardson P, et al.. Baricitinib as potential treatment for 2019-nCoV acute respiratory disease. The Lancet (2020). paper; opened 2026-11-18 all records citing this
Where it sits on the map
History of this record (5)
This record has been changed 5 times, on the dates below. The note kept against each change is written for the people who maintain the atlas, in their own shorthand, so it is not shown here; it is in the record itself.
- Kind
- big-open
- Register
- open-question
- Status
- partly written
- Last updated
- 2026-11-19
- Record
- content/questions/has-any-public-graph-prediction-been-tested-prospectively.json