{"schema":"postcutoff/event@1","as_of":"2026-10-21T14:07:00+02:00","url":"https://postcutoff.com/e/2026-10-20-claude-scorpion-toxin-binders/","md":"https://postcutoff.com/e/2026-10-20-claude-scorpion-toxin-binders/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2026-10-20-claude-scorpion-toxin-binders","date":"2026-10-20","date_precision":"day","short_title":"Claude designs binders against scorpion neurotoxins","deck":null,"takeaway":"On Oct 20, 2026 Anthropic's Science Blog reported that an internal Claude research model, working mostly autonomously for 64 hours, designed protein binders against five scorpion neurotoxins.","category":"science","category_label":"Science & math","importance":3,"confidence":"high","status":{"key":"pending","labels":["Event confirmed","Awaiting review"]},"sources":[{"n":1,"title":"Anthropic: How Claude designed protein binders against scorpion neurotoxins","url":"https://www.anthropic.com/research/claude-scorpion-toxin-binder-design","type":"official","group":"primary","domain":"anthropic.com"},{"n":2,"title":"Anthropic on X","url":"https://x.com/AnthropicAI/status/2112579251555721573","type":"official","group":"primary","domain":"x.com"}],"official":2,"filed":"2026-10-21","updated":"2026-10-21","orgs":["Anthropic","Citrini Research"],"title":"Anthropic: an internal Claude model mostly autonomously designed protein binders against scorpion neurotoxins; 17 of 211 hit in two labs","summary":"On Oct 20, 2026 Anthropic's Science Blog reported that an internal Claude research model, working mostly autonomously for 64 hours, designed protein binders against five scorpion neurotoxins. It produced 318,484 designs and picked 211 for testing. Two labs found that 17 bound their target at 1 µM or tighter; the best two bound the Mexican scorpion toxin Cn2 at single-digit nanomolar affinity. Neutralization was not tested, and Anthropic says it has not produced an antivenom.","key_facts":["Partners: Anthropic's Science team with Citrini Research; a test of whether Claude can help motivated non-experts tackle a health problem. Model: 'an internal research model, operating within Claude Science' (not named)","Autonomy: 64 hours, four follow-up prompts, about 24 hours unattended after the first prompt. Claude chose toxin structures (PDB, AlphaFold DB), five hotspot residues per toxin, thresholds and multi-toxin strategies, and emailed sequences to Twist Bioscience itself","Scale: 12 design tools, 318,484 designs, 553,052 design–toxin pairs co-folded and scored, ~10,000 GPU hours; 180 designs chosen by Claude plus 31 added later with its help = 211","Targets: Cn2 (Mexico), Ts1 (Brazil), AaH I and AaH II (North Africa), LqhIII (Middle East), aimed at each toxin's sodium-channel binding site","Validation: Adaptyv Bio (cell-free) and Twist Bioscience (human cells, Fc fusions), surface plasmon resonance at both. Criteria: hit in both labs, KD ≤ 1 µM, no binding to off-target CLEC12A. 17/211 passed (Cn2 7, AaH II 4, AaH I 4, LqhIII 2); single-toxin designs 11/60 (~18%). No multi-toxin design passed for more than one toxin","Leads: Cn2-B1 and Cn2-B2, single-digit nM at both labs; competition experiments suggest they bind at or near the site of the LR antibody, reported to neutralize Cn2 in mice","Caveats (Anthropic): tested only against recombinant toxins, not venom-purified ones; no in vitro or in vivo neutralization; 'we do not claim to have produced an antivenom'. All 211 designs and data released on Hugging Face","Reviewers quoted: Susana Vázquez Torres (CNIO) called it a promising first step; Timothy P. Jenkins (DTU) said binding 'is no longer the main bottleneck'","Context: >1.2M scorpion stings and >3,250 deaths a year, mostly children; Anthropic's X post had ~1.38M views (fxtwitter, Oct 21)"],"key_numbers":[],"tags":["protein-design","biology","claude","agents","neglected-diseases","antivenom","ai-for-science"],"science":{"field":"biology","subfield":"protein design","problem":"Binders against scorpion α- and β-neurotoxins (Cn2, Ts1, AaH I, AaH II, LqhIII) as a step toward cheaper antivenoms","result":"17 of 211 AI-chosen designs bound their toxin (KD ≤ 1 µM) in two independent labs; two Cn2 binders at single-digit nM. No multi-toxin binder; neutralization untested.","open_since":"","ai_system":["Claude (internal research model","Claude Science)"],"human_role":"AI-led with light supervision: four follow-up prompts over 64 hours; humans ran wet-lab tests via Adaptyv Bio and Twist Bioscience and supervised analysis","verification":{"key":"none","label":"Unverified claim","text":"Lab-validated binding (SPR at two labs); no neutralization or peer review"},"status":"pending","shock":""},"body_md":"## What happened\n\nAnthropic and Citrini Research let an internal Claude model run a protein-design campaign against five scorpion toxins with little human\ninput, then had the chosen designs made and tested by two commercial labs. About 8% of all designs, and about 18% of single-toxin designs,\nbound their targets, a hit rate the authors call typical for protein design. The attempt to make one binder that catches several toxins\nfailed.\n\n## Why it matters\n\nIt is one of the first published cases of a frontier lab's model running a wet-lab-validated design campaign mostly by itself, with data\nreleased for checking. It also shows the limits: binding is not neutralization, and the hardest goal (a broad binder) was not reached.\nAnthropic chose a project with clear medical value, while its CEO also points to bio misuse risk as a reason for strict biology safeguards.","disputed":[{"label":"Verification","text":"Lab-validated binding (SPR at two labs); no neutralization or peer review","sources":[]}],"related":[{"id":"2026-10-15-llm-discovered-quantum-circuits-harvard-anthropic-mythos","url":"https://postcutoff.com/e/2026-10-15-llm-discovered-quantum-circuits-harvard-anthropic-mythos/","date":"2026-10-15","date_precision":"day","short_title":"Harvard–Anthropic team (with Mikhail Lukin) uses Claude Mythos 5 in an evolutionary search to beat state-of-the-art quantum circuits on seven of eight tasks","deck":null,"takeaway":"An LLM-plus-evaluator search, starting from blank programs, cut Toffoli-times-qubit costs by 4× to 39× for quantum arithmetic subroutines and found a new reversible design for modular inversion.","category":"science","category_label":"Science & math","importance":3,"confidence":"medium","status":{"key":"partly","labels":["Partly confirmed"]},"sources":3,"official":3,"filed":"2026-10-16","updated":"2026-10-16","orgs":["Harvard University","Anthropic","QuEra Computing"]}],"people":[],"posts":[{"id":"x-anthropicai-2112579251555721573","title":"“New on our Science Blog: designing protein binders against scorpion neurotoxins.…”","url":"https://postcutoff.com/p/x-anthropicai-2112579251555721573/"}],"videos":[],"models":[],"changes":[{"date":"2026-10-21","type":"filed","text":"Created"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-10-21","run":null,"sources_read":null,"updated":"2026-10-21","human_review":null,"version":null},"gaps":[{"model_id":"gpt-6-astra","name":"GPT-6 Astra","cutoff":"2026-04","days_after":173,"in_training_data":false},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":112,"in_training_data":false},{"model_id":"gemini-4-argon","name":"Gemini 4 Argon","cutoff":"2026-03","days_after":203,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":142,"in_training_data":false}],"short_url":null}