{"slug": "claude-ai-raises-new-safety-questions-as-it-autonomously-designs-lab-validated", "title": "Claude AI Raises New Safety Questions as It Autonomously Designs Lab-Validated Protein Binders", "summary": "Claude AI, developed by Anthropic, autonomously designed 1,320 protein binders, of which 354 were lab-validated, achieving a 26.8% average hit rate across 14 of 15 targets, according to Adaptyv Bio. The system, using Claude Science, reached an 80% hit rate against TREM2 and outperformed winners from five of six previous Adaptyv Bio competitions on binding affinity, though Anthropic cautioned that 'protein binders are not drugs.' Former pharmaceutical executive Martin Shkreli criticized the results as 'not impressive work,' citing weak affinities and lack of intracellular targets.", "body_md": "# Claude AI Raises New Safety Questions as It Autonomously Designs Lab-Validated Protein Binders\n\n## Claude designed protein binders that worked in lab tests, but the results do not prove AI can create medicine\n\nClaude AI designed 1,320 protein binders and sent them into an automated lab pipeline, where 354 were confirmed to bind their intended targets, raising fresh questions about how far AI can now go on its own in biological design.\n\nThe work, led by Adaptyv Bio using [Anthropic's Claude models](https://www.ibtimes.co.uk/ai-revolution-medical-research-discovery-1814516), effectively showed an AI system assembling and running much of a protein-design workflow, with humans and lab robots handling only the physical experiments.\n\nThe system achieved a 26.8% average hit rate, with successful binders across 14 of 15 targets. One target produced no binders, and another was excluded due to low-quality measurements.\n\nThe setup used Claude Science, Anthropic's research platform, which connects a general-purpose model to specialist tools for protein structure prediction and design. Anthropic supplied an initial expert-written protocol. Claude then used available tools to generate, evaluate and refine designs before sequences were sent for lab testing.\n\nAdaptyv Bio converted sequences into DNA, produced the proteins and measured binding. It reported a 95% expression success rate.\n\n## What the Lab Tests Showed\n\nPerformance varied sharply by target. Claude reached an 80% hit rate against TREM2, up from 38.3% in a prior Adaptyv Bio competition. The strongest designs also outperformed winners from five of six previous competitions on binding affinity.\n\nFor 15-PGDH, the best Claude binder measured 33.4 nanomolar versus 1.7 micromolar previously. For RBX1, it was 3.9 nanomolar versus 25.7 nanomolar. Adaptyv Bio said the results would have won five of its six past protein-design competitions and described the system as operating at an expert level when using existing design tools.\n\nThe comparison is internal to Adaptyv Bio's competitions and does not reflect pharmaceutical industry benchmarks.\n\n## Shkreli Questions the Value\n\nMartin Shkreli, the former pharmaceutical executive, criticised the significance of the results. 'This is not impressive work,' he said, arguing the reported affinities were weak for peptide binders. He also questioned the lack of intracellular targets.\n\n'These aren't useful probe molecules because none of them are intracellular,' he said. 'If I needed an extracellular probe, that's what a monoclonal antibody is for.' He added that existing antibody fragments could often serve the same function without designing new binders.\n\nHis comments underline a key gap: binding a target is not the same as producing a useful drug candidate. Anthropic makes the same distinction.\n\n'Protein binders are not drugs,' the company said, describing them as an early step toward therapeutics that still require extensive optimisation and testing.\n\n## How Autonomous Was Claude's Design Loop?\n\nThe main technical result is not just the lab validation, but how much of the design process was automated.\n\nAdaptyv Bio said Claude combined general reasoning with specialist protein-design tools in an automated workflow.\n\nThe model interpreted objectives, generated candidates and iterated using computational feedback. The system reflects what Adaptyv Bio calls an 'agentic science loop': AI generates designs, selects candidates and feeds results back into further design cycles.\n\nClaude did not perform physical lab work. DNA synthesis, protein production and measurements were handled by automated systems and human operators. But a large portion of the computational design loop was executed by the model itself.\n\n## A Binder Is Not a Medicine\n\nThe results do not show drug discovery. A protein binder is only an early-stage component. Any therapeutic candidate must still pass through optimisation for stability, selectivity, safety, delivery and pharmacokinetics.\n\nThis experiment measured binding only. It did not assess whether any molecule could function as a drug. Anthropic has said its longer-term goal is to extend Claude across more stages of drug development, including antibodies and small molecules.\n\n## Where the Safety Concerns Begin\n\nThe experiment does not demonstrate a biological threat, nor does it show autonomous drug creation. It does show that an AI system can assemble existing biological design tools into a working pipeline that produces experimentally validated molecules.\n\nThat shifts the question from whether AI can design proteins to how much of the design process it can automate. In conventional workflows, researchers make repeated decisions across target selection, design strategy and iteration.\n\nIn this case, Claude handled much of that computational layer after receiving initial instructions. The physical lab remains a constraint. So do synthesis, testing and downstream development.\n\nThe study suggests that parts of the expertise required for protein design can now be embedded in an AI-driven system. It showed that Claude could autonomously orchestrate existing protein-design tools and produce candidates that were later validated in the laboratory.\n\nIt did not show that the system can independently discover a drug or complete the wider development process. [Questions over the use of increasingly autonomous AI in biological research](https://www.ibtimes.co.uk/ai-incidents-highlight-growing-concerns-over-control-safety-1812912) remain open.\n\n© Copyright IBTimes 2025. All rights reserved.", "url": "https://wpnews.pro/news/claude-ai-raises-new-safety-questions-as-it-autonomously-designs-lab-validated", "canonical_source": "https://www.ibtimes.co.uk/ai-driven-protein-design-claude-breakthrough-1815432", "published_at": "2026-08-20 21:06:18+00:00", "updated_at": "2026-08-20 21:14:07.089111+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-research", "ai-agents", "ai-safety"], "entities": ["Anthropic", "Claude AI", "Adaptyv Bio", "Claude Science", "Martin Shkreli", "TREM2", "15-PGDH", "RBX1"], "alternates": {"html": "https://wpnews.pro/news/claude-ai-raises-new-safety-questions-as-it-autonomously-designs-lab-validated", "markdown": "https://wpnews.pro/news/claude-ai-raises-new-safety-questions-as-it-autonomously-designs-lab-validated.md", "text": "https://wpnews.pro/news/claude-ai-raises-new-safety-questions-as-it-autonomously-designs-lab-validated.txt", "jsonld": "https://wpnews.pro/news/claude-ai-raises-new-safety-questions-as-it-autonomously-designs-lab-validated.jsonld"}}