{"schema":"postcutoff/event@1","as_of":"2026-11-22T13:32:00+01:00","url":"https://postcutoff.com/e/2026-08-18-claude-protein-binders-wet-lab/","md":"https://postcutoff.com/e/2026-08-18-claude-protein-binders-wet-lab/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":"2026-08-18-claude-protein-binders-wet-lab","date":"2026-08-18","date_precision":"day","short_title":"Claude autonomously designs protein binders that work in the lab against 14 of 15 targets","deck":null,"takeaway":"On Aug 18, 2026 Anthropic reported that Claude (Mythos Preview and Opus 4.8), running autonomously in Claude Science, designed de novo protein binders against 15 targets and produced confirmed binders for 14 of them in outside wet-lab tests by Adaptyv Bio and Twist Bioscience.","category":"science","category_label":"Science & math","importance":4,"confidence":"high","status":{"key":"confirmed","labels":["Result confirmed"]},"sources":[{"n":1,"title":"Anthropic: How Claude is accelerating protein design and analytical chemistry","url":"https://www.anthropic.com/research/Claude-accelerates-protein-design","type":"official","group":"primary","domain":"anthropic.com"},{"n":2,"title":"The Next Web: Anthropic says Claude designed working protein binders, and beat human experts on some","url":"https://thenextweb.com/news/anthropic-claude-protein-design-chemistry","type":"press","group":"press","domain":"thenextweb.com"},{"n":3,"title":"Dataconomy: Claude designed protein binders for 14 of 15 targets","url":"https://dataconomy.com/2026/08/20/claude-ai-protein-binders-14-of-15-targets/","type":"press","group":"press","domain":"dataconomy.com"},{"n":4,"title":"pharmaphorum: Claude Science outperforms experts in protein binder task","url":"https://pharmaphorum.com/news/claude-science-outperforms-experts-protein-binder-task","type":"press","group":"press","domain":"pharmaphorum.com"}],"official":1,"filed":"2026-09-30","updated":"2026-10-07","orgs":["Anthropic","Adaptyv Bio","Twist Bioscience"],"title":"Claude autonomously designs protein binders that work in the lab against 14 of 15 targets","summary":"On Aug 18, 2026 Anthropic reported that Claude (Mythos Preview and Opus 4.8), running autonomously in Claude Science, designed de novo protein binders against 15 targets and produced confirmed binders for 14 of them in outside wet-lab tests by Adaptyv Bio and Twist Bioscience. Hit rates were 22.6–35.1%, against the 10–15% typical of protein design campaigns. The same post showed Opus 5 processing raw NMR and LC-MS files in about 25 minutes, matching a contract lab's results.","key_facts":["354 confirmed binders from 1,320 designs, against 14 of 15 targets (30 designs requested per target)","Hit rates: Mythos Preview 26.7% and Opus 4.8 22.6% in multi-target mode (48 h, up to 12,500 H100 hours); Mythos Preview 35.1% in single-target mode (24 h, up to 2,500 H100 hours per target). Anthropic cites 10–15% as typical","Wet-lab production and testing done independently by Adaptyv Bio and Twist Bioscience","High-affinity binders against at least six targets; binders matching or exceeding the best reported affinity against at least four","RBX1: Mythos Preview reached a 40% hit rate vs 3.7% among Adaptyv competition participants; its top design outperformed the winning entry (245 designs entered)","Opus 4.8, not Mythos Preview, succeeded on the hard target TNFα, including binders cross-reactive to human, cynomolgus monkey and mouse TNFα","Failures: no confirmed binder against maltose-binding protein (0 of 90 designs); only three modest binders against the de novo β-barrel BBF-14","Humans only granted access approvals and monitored infrastructure after the initial prompt; prompts and all in vitro and in silico data released","Chemistry test: Opus 5 in Claude Science returned processed NMR and LC-MS results in 23 and 19 minutes from raw vendor files; purity 96.4% vs the lab's 96.33%. It decoded an undocumented LC-MS format, checked against all 2,664 scans","Protein design and other dual-use biology stay blocked in generally available Claude Fable 5; Anthropic said an access program for scientists was a top priority"],"key_numbers":[],"tags":["ai-for-science","biology","protein-design","agents","wet-lab","claude-science","chemistry"],"science":{"field":"biology","subfield":"protein design","problem":"De novo design of protein minibinders against benchmark and novel targets (incl. Adaptyv BenchBB, 15-PGDH, GDF-8, RBX1, TNFα)","result":"Binders confirmed in the wet lab for 14 of 15 targets; 354 binders from 1,320 designs; overall hit rates 22.6–35.1%, several binders exceeding the best published affinities.","open_since":"","ai_system":["Claude Mythos Preview","Claude Opus 4.8","Claude Science"],"human_role":"Humans chose the targets, wrote the prompt and ran the infrastructure; Claude ran the design campaign autonomously; outside labs ran the wet-lab validation","verification":{"key":"expert","label":"Expert-checked","text":"Independent wet-lab testing by Adaptyv Bio and Twist Bioscience; company technical report, not peer-reviewed"},"status":"confirmed","shock":"A general-purpose model orchestrating existing open-source tools matched or beat top human protein design competition entries.","kind":"other"},"body_md":"## What happened\n\nAnthropic ran a multi-arm binder design campaign in Claude Science. Claude chose binding sites on each target, orchestrated open-source\nstructure-design, sequence-design and co-folding models, ran several rounds of in silico optimization and screened candidates. After the\nfirst prompt nobody gave it scientific guidance. Adaptyv Bio and Twist Bioscience then made and tested the designs. Anthropic described the\n354 binders as a sizeable addition to public de novo binder data. By comparison, it counted about 770 binders from 5,700 designs across 40\ntargets in the two largest existing public collections.\n\nThe post also tested a generally available model, Opus 5, on routine analytical chemistry. Working only from a contract lab's raw instrument\nfiles, it reproduced the lab's NMR and purity results. It also proposed the same heavy-water follow-up test that the lab had run on its own.\n\n## Why it matters\n\nIt was among the first wet-lab-validated demonstrations of a general-purpose LLM agent running a whole protein design campaign at or above\nexpert level. It was the basis for Anthropic's later work to make the pipeline cheaper (Sept 17) and for its Life Sciences Verification Program.\nThe results are the company's own, and the hit-rate comparisons use Anthropic's baseline figures. Anthropic says it will characterize the\nbinders further to confirm hit rates and affinities.","disputed":[],"related":[{"id":"2026-09-23-claude-discovers-novel-enzyme-system","url":"https://postcutoff.com/e/2026-09-23-claude-discovers-novel-enzyme-system/","date":"2026-09-23","date_precision":"day","short_title":"Claude agents discover a novel CRISPR-like enzyme system","deck":"Anthropic reveals its own biology wet lab","takeaway":"It is an example of massively parallel agent search yielding a biologically novel finding endorsed by a leading domain expert.","category":"science","category_label":"Science & math","importance":4,"confidence":"high","status":{"key":"disputed","labels":["Disputed"]},"sources":16,"official":4,"filed":"2026-09-29","updated":"2026-11-17","orgs":["Anthropic"]},{"id":"2026-09-17-claude-biomolecular-modeling-speedups","url":"https://postcutoff.com/e/2026-09-17-claude-biomolecular-modeling-speedups/","date":"2026-09-17","date_precision":"day","short_title":"Claude speeds up 30+ open-source biology models about 4x and folds 10,000+ token complexes on one GPU node","deck":null,"takeaway":"Expert engineers normally need weeks per model to make such optimizations, and the work rarely transfers between models.","category":"science","category_label":"Science & math","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":7,"official":5,"filed":"2026-09-30","updated":"2026-09-30","orgs":["Anthropic","Adaptyv Bio"]},{"id":"2026-06-30-claude-science","url":"https://postcutoff.com/e/2026-06-30-claude-science/","date":"2026-06-30","date_precision":"day","short_title":"Anthropic launches Claude Science, an AI workbench for researchers","deck":null,"takeaway":"It was Anthropic's first dedicated vertical product for science, a precursor to its wet lab and the Model Hardware Standard.","category":"product","category_label":"Products","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":4,"official":2,"filed":"2026-09-29","updated":"2026-09-30","orgs":["Anthropic"]},{"id":"2026-06-09-claude-fable-5-mythos-5","url":"https://postcutoff.com/e/2026-06-09-claude-fable-5-mythos-5/","date":"2026-06-09","date_precision":"day","short_title":"Anthropic releases Claude Fable 5 and Claude Mythos 5","deck":"First generally available Mythos-class model","takeaway":"This was the first time the class of model Anthropic had withheld in April (Mythos Preview) became available to the public.","category":"model-release","category_label":"Model releases","importance":5,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":7,"official":5,"filed":"2026-09-29","updated":"2026-09-29","orgs":["Anthropic"]},{"id":"2024-09-05-alphaproteo","url":"https://postcutoff.com/e/2024-09-05-alphaproteo/","date":"2024-09-05","date_precision":"day","short_title":"AlphaProteo designs high-affinity protein binders","deck":"Including the first AI-designed VEGF-A binder","takeaway":"High one-shot success rates cut the months of screening normally needed to find a binder.","category":"science","category_label":"Science & math","importance":3,"confidence":"medium","status":{"key":"confirmed","labels":["Result confirmed"]},"sources":2,"official":1,"filed":"2026-09-29","updated":"2026-09-29","orgs":["Google DeepMind"]},{"id":"2023-07-11-rfdiffusion-protein-design","url":"https://postcutoff.com/e/2023-07-11-rfdiffusion-protein-design/","date":"2023-07-11","date_precision":"day","short_title":"RFdiffusion: diffusion models design new proteins that work in the lab","deck":null,"takeaway":"It became the workhorse of AI protein design, underlying AI antivenoms, antibodies and enzymes.","category":"science","category_label":"Science & math","importance":4,"confidence":"high","status":{"key":"confirmed","labels":["Result confirmed"]},"sources":3,"official":3,"filed":"2026-09-29","updated":"2026-09-29","orgs":["University of Washington Institute for Protein Design"]}],"people":[],"posts":[],"videos":[],"models":[],"changes":[{"date":"2026-10-07","type":"edit","text":"Science block: kind: other (not a long-open problem; listed with other AI science results, not in the open-problems count)"},{"date":"2026-09-30","type":"filed","text":"Created (the post had not been cited)"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-09-30","run":null,"sources_read":null,"updated":"2026-10-07","human_review":null,"version":{"date":"2026-10-07"}},"gaps":[{"model_id":"gpt-6-2-astra","name":"GPT-6.2 Astra","cutoff":"2026-05","days_after":79,"in_training_data":false},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":49,"in_training_data":false},{"model_id":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","cutoff":"2026-03","days_after":140,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":79,"in_training_data":false}],"short_url":"https://postcutoff.com/s/claude-autonomously-designs"}