Case study: Benchmarking Claude’s protein designs in the wet lab | Adaptyv Bio<br>Services<br>BlogTeamCareersAPIProteinbaseDocsBook a meetingTest your proteinsSign in to Foundry
←Back to BlogCase study: Benchmarking Claude’s protein designs in the wet lab<br>August 19, 2026case study
/Article
/TL;DR<br>-The Anthropic team used Claude in Claude Science to design protein binders against 16 targets and sent them to our lab.<br>-We ran all the binding experiments in our automated wet lab, going from digital protein sequence, to DNA, expressed proteins, then measurement and quality control.<br>-Out of 1,320 designs, 354 bound their target, giving Claude an average hit rate of 26.8%. Only a single target yielded 0 binders.<br>-Compared to the results of our Protein Design Competitions, Claude’s designs had noticeably higher success rates and would have won 5 out 6, yielding tighter binders.<br>-At the end of the post we expand more on how we think about the future of agentic science, protein design and the long all road to curing all diseases.
Show less<br>The promise of bioengineering is to design new biological tools: diagnostics that help us detect diseases, antibodies that can destroy cancers, new vaccines to protect against viruses. To build those tools, AI will ultimately need to interact with the physical world and not just with a static dataset.<br>The next phase of AI in biology is an agentic science loop: an AI system that can reason over scientific knowledge, use specialised tools to design thousands of molecules, send those designs into an automated wet-lab, and learn from the resulting data.<br>Three layers need to work together:<br>Generalist models to interpret a scientific goal, plan a campaign, and orchestrate workflows.<br>Specialist models and tools to perform tasks such as protein structure prediction and protein design models.<br>Automated wet labs to turn digital designs into measurements from the physical world.<br>In this post, we showcase how Anthropic benchmarked Claude Mythos Preview and Opus 4.8 at designing novel protein binders that we tested in our automated wet lab. Overall, Claude models showed expert level skill at protein design, matching or exceeding human experts on many tasks. Together with the Anthropic team, we’re releasing the actual protein sequences Claude designed as well as the experimental data on Proteinbase, the open protein data platform.
How to test AI-designed proteins in the real world<br>At Adaptyv, we have built an automated, AI-native wet lab for turning protein designs into experimental data.<br>Instead of scientists in lab coats pipetting samples in tiny tubes one by one, we have built automated workcells that run the same experiments many times faster and cheaper.<br>Human protein designers and agents can access the lab via our web platform and API to send digital protein sequences for wet lab validation on different assays.<br>Our platform automatically processes the protein sequences (a string of amino acids) and converts it into a special DNA sequence that encodes the biological instructions for how to create the specific protein. This digital DNA sequence is then turned into an actual physical DNA molecule in the lab by assembling the DNA building blocks one by one. Next, cell-free protein synthesis takes the machinery a cell uses to read DNA and build proteins (ribosomes, enzymes, amino acids, an energy supply) and runs it with no cell around it. This is done using automated robots able to pipette incredibly small amounts of liquid really fast and at high-throughput.
At this point we have now made physical proteins in the lab from the digital AI-designed sequence. But we haven’t yet tested if the protein actually performs well at what it was designed to do. Proteins are the molecular machinery of all of life and can do many different things: digesting the food we eat, breaking down harmful molecules and making ones that we need to survive, generating energy in our cells, cutting and editing DNA, and a million other things.<br>Here, we’re testing binders: proteins that should stick to one target and nothing else. Most antibody cancer drugs are binders. So are the reagents in a pregnancy test and the capture molecules in most diagnostics. The “sticking strength” of the protein binder to its target can be measured with special instruments, giving us a so called K_D value. A lower K_D means a better binder, higher affinity binder, an often desirable property when developing new therapeutics. At Adaptyv, we run these specialized instruments with our own software to process all raw data to obtain clean K_D values against a wide range of target proteins that are relevant for therapeutic, diagnostic, and research applications.<br>Behind this simple input-output interface is a complex experimental process: many reagents, instruments, protocols and measurements must be coordinated and verified. At Adaptyv we package that complexity into an automated, quality-controlled workflow that answers a biological question...