---
format: "aidr-story-markdown/v1"
id: "273a77c3517b4756dbfad3141060b37a76424454ede807556419febf90686e1a"
canonical_url: "https://aidr.today/273a77c3?lang=en"
title: "Anthropic Claude AI Doubles Protein Design Success Rate With Binders for 14 of 15 Targets"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-08-18T23:50:02.000Z"
category: "Research"
topics: ["anthropic","claude","opus","in-upkeep-spcifiques"]
source_urls: ["https://huggingnews.com/ai/update-anthropic-claude-ai-doubles-protein-design-success-rate-with-bind-531e6b50","https://x.com/AnthropicAI/status/2089842387845804246","https://x.com/AnthropicAI/status/2089842389682954621","https://x.com/AnthropicAI/status/2089842391918563599","https://x.com/AnthropicAI/status/2089842393218777151","https://x.com/AnthropicAI/status/2089842395722678689","https://x.com/rohanpaul_ai/status/2089850167302500483"]
summary: "A new batch of lab tests confirmed that Claude can autonomously run computational protein design campaigns to produce molecules that work in a laboratory setting. The AI generated 354 successful binders from 1,320 candidates, achieving hit rates between 22% and 35% and outperforming human competitors on 4 of 6 comparable targets. These results, validated independently by Adaptyv Bio and Twist Bioscience, more than double the industry standard success rate of 10% to 15% and included working binders for 14 of 15 targets. While high affinity binders are a necessary first step in drug development, they are not final drugs. Anthropic is using the experiment as a foundation to teach Claude to manage the end to end development of antibodies and small molecules. The company released a technical report and open sourced its data and prompts, identifying Opus 5 as its most capable model for life science research."
---

# Anthropic Claude AI Doubles Protein Design Success Rate With Binders for 14 of 15 Targets

> [Open the canonical story](<https://aidr.today/273a77c3?lang=en>)

**Published:** 2026-08-18T23:50:02.000Z
**Category:** Research
**Topics:** anthropic, claude, opus, in\-upkeep\-spcifiques

## Summary

A new batch of lab tests confirmed that Claude can autonomously run computational protein design campaigns to produce molecules that work in a laboratory setting\. The AI generated 354 successful binders from 1,320 candidates, achieving hit rates between 22% and 35% and outperforming human competitors on 4 of 6 comparable targets\. These results, validated independently by Adaptyv Bio and Twist Bioscience, more than double the industry standard success rate of 10% to 15% and included working binders for 14 of 15 targets\. While high affinity binders are a necessary first step in drug development, they are not final drugs\. Anthropic is using the experiment as a foundation to teach Claude to manage the end to end development of antibodies and small molecules\. The company released a technical report and open sourced its data and prompts, identifying Opus 5 as its most capable model for life science research\.

## Sources

- [Story source](<https://huggingnews.com/ai/update-anthropic-claude-ai-doubles-protein-design-success-rate-with-bind-531e6b50>)
- [Story source](<https://x.com/AnthropicAI/status/2089842387845804246>)
- [Supporting source](<https://x.com/AnthropicAI/status/2089842389682954621>)
- [Supporting source](<https://x.com/AnthropicAI/status/2089842391918563599>)
- [Supporting source](<https://x.com/AnthropicAI/status/2089842393218777151>)
- [Supporting source](<https://x.com/AnthropicAI/status/2089842395722678689>)
- [Supporting source](<https://x.com/rohanpaul_ai/status/2089850167302500483>)