--- title: Measuring AI’s capability to accelerate biological... description: OpenAI used GPT-5 in a controlled wet lab setting to autonomously optimize a molecular cloning protocol, achieving a 79x improvement in cloning efficiency over... canonical: https://daily.dev/posts/measuring-ai-s-capability-to-accelerate-biological-research-in-the-wet-lab-18ifyxys1 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Measuring AI’s capability to accelerate biological research in the wet lab | daily.dev og:description: OpenAI used GPT-5 in a controlled wet lab setting to autonomously optimize a molecular cloning protocol, achieving a 79x improvement in cloning efficiency over... og:url: https://daily.dev/posts/measuring-ai-s-capability-to-accelerate-biological-research-in-the-wet-lab-18ifyxys1 og:image: https://api.daily.dev/og/posts/18IFyxYS1.png og:image:alt: Measuring AI’s capability to accelerate biological research in the wet lab og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Measuring AI’s capability to accelerate biological research in the wet lab **[OpenAI](https://daily.dev/sources/openai)** · 14 min read · 0 upvotes · 1 comments ## Summary OpenAI used GPT-5 in a controlled wet lab setting to autonomously optimize a molecular cloning protocol, achieving a 79x improvement in cloning efficiency over the baseline HiFi Gibson assembly. The model proposed a novel enzymatic mechanism called RAPF-HiFi, combining RecA recombinase and phage T4 gp32 protein in a way not previously used together in molecular biology methods. A separate one-shot optimization of the bacterial transformation step yielded an additional 30x efficiency gain through a simple cell concentration technique. The work was conducted in partnership with biosecurity startup Red Queen Bio, with a robotic system also tested to automate protocol execution. OpenAI frames this as an early demonstration of AI-accelerated science while acknowledging biosecurity implications and the need for safeguards. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How much did GPT-5 improve the efficiency of a molecular cloning protocol in a real wet lab experiment? GPT-5 improved end-to-end cloning efficiency 79-fold in a controlled wet-lab evaluation built with biosecurity startup Red Queen Bio. Working from a HiFi/Gibson assembly baseline, the model proposed batches of reactions over multiple rounds, with human scientists only executing protocols and uploading results, and no human guidance beyond clarifying questions. _Anyone tracking how far AI agents can go beyond code can follow lab-science experiments like this on daily.dev._ ### What novel enzymatic mechanism did GPT-5 discover for improving Gibson assembly cloning? GPT-5 devised RAPF-HiFi, a procedure that adds RecA recombinase from E. coli and phage T4 gp32 single-stranded DNA-binding protein to a standard HiFi/Gibson assembly reaction. Gp32 smooths and detangles single-stranded DNA ends while RecA guides matching strands together at 37°C, before returning to 50°C to complete assembly, boosting efficiency over 2.5-fold on top of baseline HiFi gains. _Readers following novel AI-generated scientific mechanisms can keep up with cases like this on daily.dev._ ### What simple change to bacterial transformation protocols gave the biggest efficiency gain in GPT-5's cloning experiments? Pelleting chemically competent E. coli cells, removing half the supplied volume, and resuspending them before adding DNA, all at 4°C, was the most effective of 13 AI-proposed one-shot transformation modifications, boosting transformation efficiency more than 30-fold. This was unexpected because high-efficiency competent cells are typically considered fragile and such concentrated handling is usually avoided. _Developers curious how AI-proposed lab protocol tweaks get validated can follow similar experiments on daily.dev._ ## Community discussion Top comments from developers on daily.dev. **@mariacristinacapizzi** · 0 upvotes > Fluorescence western blot, blocking with BSA ## Similar posts on daily.dev - [GPT-5 lowers the cost of cell-free protein synthesis](https://daily.dev/posts/gpt-5-lowers-the-cost-of-cell-free-protein-synthesis-vdmrdblpi) · OpenAI · 1 upvotes · 0 comments - [New AI model could cut the costs of developing protein drugs](https://daily.dev/posts/new-ai-model-could-cut-the-costs-of-developing-protein-drugs-9vcfez1es) · MIT News · 1 upvotes · 0 comments - [OpenAI Says AI Agents May Make Great Quantum Lab Assistants](https://daily.dev/posts/openai-says-ai-agents-may-make-great-quantum-lab-assistants-b9lzehzq9) · The Quantum Insider · 0 upvotes · 0 comments - [Co-Scientist](https://daily.dev/posts/co-scientist-eih1hhppo) · DeepMind · 0 upvotes · 0 comments --- Tags: [#gpt](https://daily.dev/tags/gpt) [View this post on daily.dev](https://daily.dev/posts/measuring-ai-s-capability-to-accelerate-biological-research-in-the-wet-lab-18ifyxys1) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Measuring AI’s capability to accelerate biological research in the wet lab","url":"https://daily.dev/posts/measuring-ai-s-capability-to-accelerate-biological-research-in-the-wet-lab-18ifyxys1","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/measuring-ai-s-capability-to-accelerate-biological-research-in-the-wet-lab-18ifyxys1"},"datePublished":"2026-07-09T18:39:30.207Z","dateModified":"2026-09-13T19:51:23.743Z","description":"OpenAI used GPT-5 in a controlled wet lab setting to autonomously optimize a molecular cloning protocol, achieving a 79x improvement in cloning efficiency over...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/06c12721380a3207817ce586a1c5a83d?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/06c12721380a3207817ce586a1c5a83d?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"OpenAI","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"OpenAI","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/984b3632316f4afaa3d5213d5c64fe65","url":"https://daily.dev/sources/openai"},"commentCount":1,"discussionUrl":"https://daily.dev/posts/measuring-ai-s-capability-to-accelerate-biological-research-in-the-wet-lab-18ifyxys1","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":1}],"keywords":"gpt","timeRequired":"PT14M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"OpenAI","item":"https://daily.dev/sources/openai"},{"@type":"ListItem","position":3,"name":"Measuring AI’s capability to accelerate biological research in the wet lab"}]} {"@context":"https://schema.org","@type":"WebPage","@id":"https://daily.dev/posts/measuring-ai-s-capability-to-accelerate-biological-research-in-the-wet-lab-18ifyxys1","comment":[{"@type":"Comment","text":"Fluorescence western blot, blocking with BSA","datePublished":"2026-08-07T18:04:31.231Z","url":"https://daily.dev/posts/18IFyxYS1#c-B52wz7crV","author":{"@type":"Person","name":"Mariacristina Capizzi","url":"https://daily.dev/mariacristinacapizzi","image":"https://lh3.googleusercontent.com/a/ACg8ocKBkscOam_4fjz2dO0o0btI-sakV37LkBBEiXdKtUYY73viBg=s96-c"}}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/measuring-ai-s-capability-to-accelerate-biological-research-in-the-wet-lab-18ifyxys1#faq","mainEntity":[{"@type":"Question","name":"How much did GPT-5 improve the efficiency of a molecular cloning protocol in a real wet lab experiment?","acceptedAnswer":{"@type":"Answer","text":"GPT-5 improved end-to-end cloning efficiency 79-fold in a controlled wet-lab evaluation built with biosecurity startup Red Queen Bio. Working from a HiFi/Gibson assembly baseline, the model proposed batches of reactions over multiple rounds, with human scientists only executing protocols and uploading results, and no human guidance beyond clarifying questions. Anyone tracking how far AI agents can go beyond code can follow lab-science experiments like this on daily.dev."}},{"@type":"Question","name":"What novel enzymatic mechanism did GPT-5 discover for improving Gibson assembly cloning?","acceptedAnswer":{"@type":"Answer","text":"GPT-5 devised RAPF-HiFi, a procedure that adds RecA recombinase from E. coli and phage T4 gp32 single-stranded DNA-binding protein to a standard HiFi/Gibson assembly reaction. Gp32 smooths and detangles single-stranded DNA ends while RecA guides matching strands together at 37°C, before returning to 50°C to complete assembly, boosting efficiency over 2.5-fold on top of baseline HiFi gains. Readers following novel AI-generated scientific mechanisms can keep up with cases like this on daily.dev."}},{"@type":"Question","name":"What simple change to bacterial transformation protocols gave the biggest efficiency gain in GPT-5's cloning experiments?","acceptedAnswer":{"@type":"Answer","text":"Pelleting chemically competent E. coli cells, removing half the supplied volume, and resuspending them before adding DNA, all at 4°C, was the most effective of 13 AI-proposed one-shot transformation modifications, boosting transformation efficiency more than 30-fold. This was unexpected because high-efficiency competent cells are typically considered fragile and such concentrated handling is usually avoided. Developers curious how AI-proposed lab protocol tweaks get validated can follow similar experiments on daily.dev."}}]} ```