English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

Anthropic's Claude Designs Protein Binders: 14 of 15 Targets Hit in Blind Wet-Lab Validation

Forum topic · QianXun · 2026-08-23

Summary

On August 18, Anthropic published a technical report showing that its general-purpose LLMs, Claude Opus 4.8 and Mythos Preview, acting as autonomous agents orchestrating an open-source protein design toolchain (RFdiffusion, ProteinMPNN variants, ESMFold2, and roughly twenty workflows), successfully designed experimentally validated binders for 14 of 15 blind-tested targets. Of 1,320 designs, 354 were confirmed effective by independent labs, with overall hit rates of 22–35% versus a typical industry baseline of 10–15%. Validation was performed blind by Adaptyv Bio and Twist Bioscience, with model-side and testing-side separation to prevent data leakage. Notable results include a 40% hit rate on the RBX1 target (vs. 3.7% average in a human competition) and cross-species TNFα binders. Limitations include no parallel human-expert control, unverified protein structures, and confidence scores that failed to predict the two failures. Anthropic has restricted these capabilities in public Claude behind a trusted-access program due to dual-use concerns.

Anthropic's Claude Designs Protein Binders: 14 of 15 Targets Hit in Blind Wet-Lab Validation

The Event

On August 18, Anthropic released a technical report: general-purpose LLMs Claude (Opus 4.8 and Mythos Preview), acting as agents, autonomously orchestrated an entire open-source protein design toolchain — and in blind testing produced experimentally validated binders for 14 of 15 targets. Of 1,320 designs, 354 were confirmed effective by independent laboratories, with overall hit rates of 22%–35%, compared with the typical protein design campaign rate of 10%–15%.

The significance lies not just in the scores but in the shape of the result: a general-purpose language model — not a specialized structural biology model — sat in the driver's seat of an entire wet-lab pipeline.

What Claude Actually Did

A protein binder is a small protein designed to "lock onto" a target protein, blocking or altering its function — the mechanism behind many drugs. Designing tight-binding molecules is the first step in drug development, traditionally requiring expert effort of weeks to months per target.

Anthropic did not build a new model. Instead, it gave Claude access to a scientific workbench of existing tools:

  • Backbone structures from RFdiffusion and Genie 3
  • Sequences generated with ProteinMPNN variants
  • Candidates filtered and ranked with ESMFold2 and other folding predictors
  • Roughly two dozen different workflows chained together
  • A system prompt of about 16,000 words governs the process, but only about a third consists of scientific instructions; the rest covers scheduling, delegation, and budget discipline. The prompt never specifies binding sites — Claude chooses them itself. Each round has a fixed compute budget (up to $50,000 for multi-target, $10,000 for single-target).

    Humans do only four things: pick targets, write the prompt, approve infrastructure permissions, and read the final experimental data.

    Validation was blind: two independent companies, Adaptyv Bio and Twist Bioscience, synthesized and measured the designs without sharing data with each other or knowing which model/ranking produced each sequence. This separation between model provider and tester is precisely the firewall against the field's most common form of result inflation.

    Why This Matters Beyond "AI Understands Biology"

  • A general model driving a specialized pipeline. The old AI-for-biology narrative was specialized models trained on specialized data producing specialized results (AlphaFold predicts structures, RFdiffusion generates backbones). This time, a general LLM agent drove a general research workbench — meaning any lab could in principle run the full protein design stack with an agent, without maintaining a computational expert team. This reframes what frontier models are for.
  • Hit rate above industry benchmark, with hard cases. On the RBX1 target, human competition participants averaged a 3.7% hit rate, while Mythos Preview in single-target mode reached 40%, with its best design binding tighter than the competition winner. On TNFα (the difficult inflammation target behind Humira), Opus 4.8 designed multiple cross-species (human/cynomolgus monkey/mouse) binders.
  • Even reading spectra. In a second experiment, Claude was given raw NMR and LC-MS instrument files and produced results in 23 and 19 minutes; a purity measurement of 96.4% matched the lab's 96.33%. Spectra reading is a slow, repetitive part of a chemist's daily work — this "queue-clearing" capability may reach everyday workflows even faster than designing new proteins.
  • Beta-sheet design capability. Claude designed 15 confirmed binders containing at least 20% beta-strands. Beta-sheets are far harder to design than alpha-helices, which Anthropic interprets as evidence that the model can genuinely reason about protein structure.
  • Limitations to Watch (Per Anthropic Itself)

  • No parallel human-expert control; each configuration tested only once; protein structures not independently confirmed — only "binding" was verified, not shape or biological effect.
  • Real failure modes: MBP (a de novo beta-barrel not found in nature) failed across all 90 designs; BBF-14 yielded only 3 weak binders.
  • Confidence doesn't warn. Claude's own confidence scores gave no early warning for the two failing targets — a genuine gap in the method.
  • Dual-use risk. Anthropic has restricted protein design and similar capabilities from public Claude behind a trusted-access program — because an AI that "can autonomously plan and execute laboratory science" raises safety-boundary questions.
  • What to Watch

  • This is isomorphic to the parallel storyline in AI coding: the harness matters as much as the model. A general model plus good orchestration/tool-calling can beat benchmarks in specialized domains. The agent paradigm is spilling over from "writing code" to "doing science."
  • For the drug discovery industry: Twist Bioscience stock jumped after the announcement, and Canaccord argued this validates "real demand for Twist's products from frontier AI labs." High-throughput synthesis/testing demand for protein design will be amplified by AI.
  • Watch Anthropic's next step: extending Claude's capabilities toward "end-to-end drug development workflows across drug modalities."
One sentence: It's not that a specialized model won — it's that a general model, for the first time, drove a specialized pipeline into the wet lab on its own and broke through 14 of 15 doors.

Tags

#anthropic#claude#protein-design#ai-agents#drug-discovery#computational-biology#blind-validation#wet-lab-automation

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178633880