Putting money where their mouth is: Anthropic’s Claude autonomously designs disease-targeting proteins with real wet-lab proof, hitting a 35% success rate vs 10–15% human average
Summary
Anthropic's Claude AI autonomously designs disease-targeting proteins with a 35% success rate in wet-lab validation, surpassing the human average of 10-15%.
Similar Articles
Anthropic's Claude autonomously designs protein binders targeting scorpion neurotoxins
Anthropic and Citrini Research used an internal Claude model to autonomously generate protein minibinders against five scorpion neurotoxins, yielding 17 functional binders from 211 tested, marking a step toward AI-driven antivenom discovery.
Anthropic wants to develop its own drugs
Anthropic announced Claude Science, an AI workbench for scientists, and revealed its own plans to develop drugs for neglected diseases using AI, entering a competitive field of AI-driven drug discovery.
@rohanpaul_ai: > Anthropic now uses Claude inside real drug programs at 6 companies and runs its own, including muscular dystrophy wor…
Anthropic reports using Claude in real drug programs at six companies and its own in-house discovery efforts, including muscular dystrophy work that could reach human trials by late 2028.
Can we take a moment to appreciate that with 950 Claude agents running for only 21 hours searching genomic data, Anthropic may have found a new CRISPR-like gene-editing mechanism
Anthropic used 950 Claude agents for 21 hours to find a candidate protein for gene editing, potentially a new CRISPR-like mechanism, highlighting the rapid advancement of AI in scientific research.
Early progress on accelerating drug development with Claude
Anthropic's life sciences team reports early progress using Claude to accelerate drug development through partnerships with six biotech and pharma organizations, plus its own drug discovery programs for rare diseases.