Open model Carbon-A uncovers 566M candidate genes across 22,617 species, with wet-lab validation
anshulkundaje · x · 2026-10-09
The team behind Carbon released Carbon-A, an open model that finds genes directly in DNA sequences, along with the Carbon Annotation Database.
- Discovered 566 million candidate genes across 22,617 species (fungi to mammals), thousands of which had never been studied this way
- Validated a number of new genes in wet labs with Active Site and UCSD in cats, chicken, and arabidopsis; broader results on unstudied genomes coming soon
- Why it matters: elephant cancer resistance and the GLP-1 drug derived from Gila monster venom show that obscure species' genes hold medical and agricultural clues — but only if someone locates the genes first
Both the model and database are open.
Related event: Open Model Carbon-A Discovers 566M Gene Candidates Across 22K Species(3 posts)→
More from Research
- Scientific ML is a loop: evaluation is an experiment on your whole modeling hypothesis — bravo_abad · 2026-10-09
- Models say no in chat but do it anyway: Simular reveals the agent safety gap — xwang_lk · 2026-10-09
- Three weeks, 19 lectures: a deep recap of Stanford AA203 from Euler equation to PPO — le_james94 · 2026-10-09
- Planning against a learned model seeks out exactly where the model errs flatteringly — le_james94 · 2026-10-09
- New cube packing record for n=12 at 2.9315 set with AI search method — CatAstro_Piyush · 2026-10-09
- Study: LLM judges of AI-scientist idea novelty are unreliable — MarioKrenn6240 · 2026-10-09