{"slug": "claude-hit-93-percent-on-de-novo-protein-binders-across-15", "title": "Claude hit 93 percent on de novo protein binders across 15", "summary": "Anthropic's Claude AI model achieved a 93% success rate in designing functional de novo protein binders for 14 of 15 targets, with wet-lab validation by Adaptyv Bio and Twist Bioscience, according to a report. The result, if confirmed, represents a significant improvement over typical single-digit to low-teens success rates of existing de novo pipelines like RFdiffusion and Chroma, though missing details on affinity thresholds and target classes limit direct comparisons.", "body_md": "# Claude hit 93 percent on de novo protein binders across 15\n\n[Claude](/en/tags/claude/)designed functional binders for 14 of 15 targets — validated by Adaptyv Bio and Twist Bioscience, not internal benchmarks — is the kind of result that forces a rethink of where LLM-driven protein engineering actually sits right now. Most published de novo pipelines using RFdiffusion or Chroma report single-digit to low-teens success rates per design round. A 93 percent hit rate, if the denominator and affinity thresholds hold up, isn't incremental. It's a category shift.\n\n## What the benchmark actually tells us\n\nThe human expert wrote the prompt. That's the prompt engineering layer everyone skips over when they talk about \"autonomous\" design. Claude didn't hallucinate a binder from scratch; it executed a well-specified design strategy encoded in natural language. The real leverage here is that a domain expert can now compress weeks of Rosetta scripting, MD relaxation, and manual filtering into a single prompt iteration loop. That's the AI workflow acceleration — not the model magically knowing physics.\n\nAdaptyv and Twist doing the wet-lab validation is the critical piece. Self-reported metrics in this space have been unreliable for years. Third-party synthesis and assay data, even without disclosed KD values, raises the evidence bar significantly. Still, the missing numbers matter: candidates per target, affinity cutoffs, target classes (enzymes? PPIs? allosteric sites?), and whether any designs failed expression or solubility screens. Without those, comparison to state-of-the-art diffusion models stays speculative.\n\n## Where the bottleneck moves next\n\nIf this reproduces, the constraint shifts from *design* to *functional validation*. High-throughput synthesis and binding assays are already scalable. The next wall is cellular context: does the binder inhibit, activate, or just occupy? Does it fold in vivo? Anthropic didn't claim cellular data, and they shouldn't have — but that's where the real drug discovery friction lives.\n\n## What I'm watching\n\n- A technical report with target identities, candidate counts per target, and affinity distributions\n- Independent labs replicating the prompt strategy on held-out target sets\n- Whether the same prompt template generalizes across target classes or overfits the test set\n\nThe prompt itself — if Anthropic releases it — becomes a more valuable artifact than any single binder sequence. It encodes a design heuristic that can be stress-tested, modified, and benchmarked against diffusion baselines. That's the real open science contribution here.\n\n[Next Reasoning prefills might be a sign of benchmark distillation →](/en/threads/6811/)", "url": "https://wpnews.pro/news/claude-hit-93-percent-on-de-novo-protein-binders-across-15", "canonical_source": "https://promptcube3.com/en/threads/6945/", "published_at": "2026-08-19 16:43:51+00:00", "updated_at": "2026-08-19 17:58:51.241500+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-research"], "entities": ["Anthropic", "Claude", "Adaptyv Bio", "Twist Bioscience", "RFdiffusion", "Chroma"], "alternates": {"html": "https://wpnews.pro/news/claude-hit-93-percent-on-de-novo-protein-binders-across-15", "markdown": "https://wpnews.pro/news/claude-hit-93-percent-on-de-novo-protein-binders-across-15.md", "text": "https://wpnews.pro/news/claude-hit-93-percent-on-de-novo-protein-binders-across-15.txt", "jsonld": "https://wpnews.pro/news/claude-hit-93-percent-on-de-novo-protein-binders-across-15.jsonld"}}