Anthropic's Claude models autonomously designed and ranked protein binders for 15 targets, with Carterra's HT-SPR platforms validating a 3.9 nM binder in weeks, not months. The collaboration demonstrates the potential of AI and high-throughput analysis in accelerating drug discovery.
TL;DR
- Anthropic's Claude models autonomously designed and ranked protein binders for 15 targets.
- Carterra's HT-SPR platforms validated a 3.9 nM binder in weeks, not months.
- The collaboration showcases the potential of AI and high-throughput analysis in accelerating drug discovery.
What happened
Anthropic reported that its Claude models autonomously ran de novo protein binder design campaigns against 15 challenging targets. The models researched each target, selected epitopes, ran open-source design tools, and delivered ranked designs per target with no human input.
Anthropic sent the protein designs to Twist Bioscience and Adaptyv Bio for analysis. Both companies used Carterra HT-SPR platforms to generate binding kinetics and affinity data at scale.
The study demonstrated that Anthropic generated functional binders with hit rates exceeding prior methods in a matter of days, rather than the weeks or months it would take a human specialist.
Why it matters
This collaboration creates enormous opportunities for drug developers by moving the bottleneck from protein design to wet lab experimental analysis.
Carterra's HT-SPR technologies overcome this bottleneck, enabling large-scale affinity and kinetics binding data to be generated in days instead of the months required historically.
The ability to measure tens of thousands of binding interactions in a short period of time changes the landscape of drug development, allowing for more efficient and effective preclinical-relevance studies.
Key facts
- Anthropic's Claude models autonomously designed and ranked protein binders for 15 targets.
- Carterra's HT-SPR platforms validated a 3.9 nM binder in weeks, not months.
- The study demonstrated that Anthropic generated functional binders with hit rates exceeding prior methods in a matter of days.
- Carterra's array-based approach compresses complex experiments into a small number of unattended runs, consuming as little as 1% of the sample required by traditional systems.
- Anthropic compared Claude's best RBX1 binder to the winner of an earlier open design competition, with Claude's design measuring 3.9 nM versus 45 nM for the previous winner.
- The study was published on August 18, 2026, according to Anthropic's report.
Context
Protein design is a key step in the early stages of a drug discovery campaign. Traditionally, this process has been time-consuming and labor-intensive, requiring human specialists to design and validate protein binders.
The collaboration between Anthropic and Carterra demonstrates the potential of AI and high-throughput analysis in accelerating drug discovery. By automating the design process and validating binders at scale, drug developers can bring new therapies to market more quickly and efficiently.
This study highlights the importance of integrating AI and experimental validation in the drug discovery process. As AI models continue to improve, the need for high-throughput analysis platforms like Carterra's HT-SPR will become increasingly important.
