Ebolathon: AI agents design 140 molecules, 11 selectively block Ebola pseudovirus in lab
GabriCorso · x · 2026-10-31
Ebolathon, the fourth hackathon co-hosted by muni and onepot, produced real wet-lab results: a room of scientists and AI agents designed 140 small molecules targeting Bundibugyo ebolavirus (BDBV) — de novo designs plus repurposed anti-itch drugs.
Key numbers and workflow:
- onepot contributed a 30-billion-molecule synthesis-accessible chemical space with AI-driven automated synthesis covering execution, purification, and analytical QC
- 11 lab days later all 140 molecules were vialled; 22 days of testing yielded an 18.6% hit rate, with 11 molecules passing counterscreens and selectively inhibiting BDBV pseudovirus entry without hurting cell viability
- Boltz API, Rowan, Modal, OpenRouter, and Anyscale provided compute and tooling
Context: BDBV cases keep rising in DRC, Uganda, Kenya, and now Nigeria — 10,091 confirmed cases and 4,891 deaths as of Oct 27 (CDC, likely underreported). A rare full loop from hackathon idea to experimental validation for agent-driven drug design.
More from Research
- New paper quantifies ineffable concepts: 65 of 1,270 can never be taught to LLMs via language — sanmikoyejo · 2026-10-31
- Unsupervised Method Measures Whether LLM Messages Are Received — sanmikoyejo · 2026-10-31
- Neural net flies a drone in Acro mode from streamed game footage on a tiny board — yacineMTB · 2026-10-31
- llmlip-rs: Rust MLIP inference engine runs 6000-atom sims 17.7x faster than PyTorch MACE — CatAstro_Piyush · 2026-10-31
- AdaPRA: a process-reward agent with adaptive rubrics audits data science agents as they work — dan_fried · 2026-10-31
- AA-Omniscience v1.1 launches: Gemini 4 Carbon tops knowledge benchmark as some models drop 20+ points — ArtificialAnlys · 2026-10-31