Claude Gains Protein Design Skills, Succeeds on 14 of 15 Targets
karsten_kreis · x · 2026-08-20
Claude has acquired new protein design capabilities. By orchestrating open-source models like RFdiffusion and ESMFold2, it successfully designed de novo protein binders against 14 out of 15 targets, with high success rates and affinities validated by Adaptyv and Twist Bioscience. The project integrates innovations from Biohub, ByteDance, UW, EPFL, and others.
Related event: Anthropic Says Claude Designed Protein Binders for 14 of 15 Targets(46 posts)→
More from Apps
- VibeWar Launches: A Pay-to-Rank Battlefield for Vibecoded Apps — jonathan_wilke · 2026-08-21
- How to sell AI agents: Distribution and commission model — gogeta7124 · 2026-08-21
- 7 prompts to make AI writing sound more human and natural — nikola_mr64990 · 2026-08-21
- Built a local design canvas for agents to draw on via MCP, enabling Figma-like capabilities — _IruaDev · 2026-08-21
- tldraw intern ships: clustering on-canvas comments without measuring a thing — max__drake · 2026-08-21
- Mid-Tier Models Are Now Good Enough for Most Tasks — intellectronica · 2026-08-21