receipt
REC-4881 produced a median 43% reduction in total polyp burden among 12 efficacy-evaluable patients.Results, Week 13 AssessmentRecursion: Positive Phase 1b/2 Results from Ongoing REC-4881 TUPELO Trial (GlobeNewswire, 8 December 2025, via AAP) · aap.com.au
Because Recursion's AI screen pointed a shelved Takeda drug at familial adenomatous polyposis, 12 evaluable patients in the open-label TUPELO trial had a median 43% reduction in total polyp burden after 12 weeks.
receipt
REC-4881 produced a median 43% reduction in total polyp burden among 12 efficacy-evaluable patients.Results, Week 13 AssessmentRecursion: Positive Phase 1b/2 Results from Ongoing REC-4881 TUPELO Trial (GlobeNewswire, 8 December 2025, via AAP) · aap.com.au
Recursion reports that REC-4881, an oral MEK1/2 inhibitor it in-licensed from Takeda after its AI-driven phenotypic screen linked MEK1/2 inhibition to APC loss, reduced total polyp burden in patients with familial adenomatous polyposis in the phase 2 portion of the single-arm TUPELO trial.
Sources
- primaryRecursion: Positive Phase 1b/2 Results from Ongoing REC-4881 TUPELO Trial (GlobeNewswire, 8 December 2025, via AAP)aap.com.au
Editor's notes
verify: the release gives a data cutoff (25 November 2025) but no period when patients were treated, so achieved dates and the window grade are left empty. verify: a later Recursion update (November 2026, reported by trade press; Recursion's own page could not be read) gives 47% median reduction in 15 patients; this entry uses only the December 2025 release that was read. verify: the AI's role is in choosing the indication; the drug itself was developed by Takeda.
History
- Added by the backfill run.
Verification
- Drafted by
- Anthropic
claude-sonnet-5-5 - Verified by
- OpenAI
gpt-6.1-sol· pass - How sure
- Speculative
- Source 0 is a press release, not a study, a registry record, or an official report.
- Not dated yet (The dated test fails because the data cutoff does not establish when the reported patient benefits occurred.).
- Record
- data/verifications/recursion-rec-4881-fap-tupelo-polyp-burden/2026-11-20.json · The company release supports a median 43% reduction in polyp burden in 12 evaluable patients after 12 weeks, with 75% showing reductions against baseline. It establishes AI's role in selecting the drug but provides neither an isolated AI comparison nor calendar dates for the observed benefits.
Two models from different vendors read the primary source independently; this entry is published because they agreed on every receipt and every grade. It is marked speculative: The source is a press release, a news report, or the organisation's own announcement, or the benefit has not yet been measured against anything or dated, or the two checking models disagreed on a grade. Every number is still quoted from the source, and both checking models support it. The models grading an AI registry have an interest in the answer. Cross-vendor checking and the receipts on this page are how the registry handles that, not a claim to have removed it. How the gate works · Dispute this entry
Cite this entry
“Because Recursion's AI screen pointed a shelved Takeda drug at familial adenomatous polyposis, 12 evaluable patients in the open-label TUPELO trial had a median 43% reduction in total polyp burden after 12 weeks.” Because of AI, updated Nov 20, 2026. https://becauseofai.org/entry/recursion-rec-4881-fap-tupelo-polyp-burden@misc{becauseofai_recursion_rec_4881_fap_tupelo_polyp_burden,
title = {Because Recursion's AI screen pointed a shelved Takeda drug at familial adenomatous polyposis, 12 evaluable patients in the open-label TUPELO trial had a median 43% reduction in total polyp burden after 12 weeks.},
howpublished = {\url{https://becauseofai.org/entry/recursion-rec-4881-fap-tupelo-polyp-burden}},
note = {Because of AI registry, updated Nov 20, 2026},
year = {2026}
}