--- title: The Model that Taught Itself Antibodies | daily.dev description: A discussion of ESM Fold, a protein-folding foundation model that folded over 1.1 billion proteins to build a general world model of protein biology. Rather... canonical: https://daily.dev/posts/the-model-that-taught-itself-antibodies-wqmbmc5gc twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: The Model that Taught Itself Antibodies | daily.dev og:description: A discussion of ESM Fold, a protein-folding foundation model that folded over 1.1 billion proteins to build a general world model of protein biology. Rather... og:url: https://daily.dev/posts/the-model-that-taught-itself-antibodies-wqmbmc5gc og:image: https://api.daily.dev/og/posts/WQmbmc5Gc.png og:image:alt: The Model that Taught Itself Antibodies 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. # The Model that Taught Itself Antibodies **[No Priors: AI, Machine Learning, Tech, & Startups](https://daily.dev/sources/nopriorspodcast)** · 1 min read · 0 upvotes · 0 comments ## Summary A discussion of ESM Fold, a protein-folding foundation model that folded over 1.1 billion proteins to build a general world model of protein biology. Rather than being purpose-built for antibody design, protein design emerges as a byproduct of the model's general understanding of proteins, letting researchers generate antibody candidates computationally instead of screening hundreds of thousands of molecules in wet-lab experiments. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is ESMFold and how many proteins has it folded? ESMFold is an open system for scientific discovery in protein biology that predicted structures for over 1.1 billion proteins, identifying features connecting them. It functions as a general world model of protein biology, meaning it was not built specifically for antibodies or particular targets, yet protein design emerges as a capability from its general understanding. _Anyone tracking protein modeling breakthroughs can follow developments like this through daily.dev._ ### Can a general protein model generate antibodies without being specifically trained for it? Yes, protein design including antibody generation emerges as a property of a general protein world model rather than requiring a purpose-built system. This replaces laboratory workflows that screen hundreds of thousands or millions of antibody candidates through high-throughput lab experiments, allowing generation to happen computationally instead. _Researchers weighing computational versus wet-lab antibody discovery can keep up with this shift via daily.dev._ ## Similar posts on daily.dev - [You don’t need a biochemistry degree to analyze proteins](https://daily.dev/posts/you-don-t-need-a-biochemistry-degree-to-analyze-proteins-qr90yx6hv) · All Things Open · 0 upvotes · 0 comments - [How Open Science Can Help Researchers Prepare for the Next Pandemic](https://daily.dev/posts/how-open-science-can-help-researchers-prepare-for-the-next-pandemic-j2nxjuah9) · NVIDIA · 0 upvotes · 0 comments --- Tags: [#genai](https://daily.dev/tags/genai), [#biotech](https://daily.dev/tags/biotech) [View this post on daily.dev](https://daily.dev/posts/the-model-that-taught-itself-antibodies-wqmbmc5gc) ```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":"The Model that Taught Itself Antibodies","url":"https://daily.dev/posts/the-model-that-taught-itself-antibodies-wqmbmc5gc","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/the-model-that-taught-itself-antibodies-wqmbmc5gc"},"datePublished":"2026-08-19T15:29:13.593Z","dateModified":"2026-09-13T19:32:36.764Z","description":"A discussion of ESM Fold, a protein-folding foundation model that folded over 1.1 billion proteins to build a general world model of protein biology. Rather...","image":"https://i.ytimg.com/vi/yK682jTa7Dc/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/yK682jTa7Dc/sddefault.jpg","isAccessibleForFree":true,"articleSection":"No Priors: AI, Machine Learning, Tech, & Startups","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":"No Priors: AI, Machine Learning, Tech, & Startups","logo":"https://media.daily.dev/image/upload/s--Hj2kMkm_--/f_auto,q_auto/v1772391934/logos/nopriorspodcast","url":"https://daily.dev/sources/nopriorspodcast"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/the-model-that-taught-itself-antibodies-wqmbmc5gc","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"genai,biotech","timeRequired":"PT1M","video":{"@type":"VideoObject","name":"The Model that Taught Itself Antibodies","description":"A discussion of ESM Fold, a protein-folding foundation model that folded over 1.1 billion proteins to build a general world model of protein biology. Rather...","thumbnailUrl":"https://i.ytimg.com/vi/yK682jTa7Dc/sddefault.jpg","uploadDate":"2026-08-19T15:29:13.593Z","duration":"PT1M","url":"https://api.daily.dev/r/WQmbmc5Gc","embedUrl":"https://www.youtube.com/embed/yK682jTa7Dc"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"No Priors: AI, Machine Learning, Tech, & Startups","item":"https://daily.dev/sources/nopriorspodcast"},{"@type":"ListItem","position":3,"name":"The Model that Taught Itself Antibodies"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/the-model-that-taught-itself-antibodies-wqmbmc5gc#faq","mainEntity":[{"@type":"Question","name":"What is ESMFold and how many proteins has it folded?","acceptedAnswer":{"@type":"Answer","text":"ESMFold is an open system for scientific discovery in protein biology that predicted structures for over 1.1 billion proteins, identifying features connecting them. It functions as a general world model of protein biology, meaning it was not built specifically for antibodies or particular targets, yet protein design emerges as a capability from its general understanding. Anyone tracking protein modeling breakthroughs can follow developments like this through daily.dev."}},{"@type":"Question","name":"Can a general protein model generate antibodies without being specifically trained for it?","acceptedAnswer":{"@type":"Answer","text":"Yes, protein design including antibody generation emerges as a property of a general protein world model rather than requiring a purpose-built system. This replaces laboratory workflows that screen hundreds of thousands or millions of antibody candidates through high-throughput lab experiments, allowing generation to happen computationally instead. Researchers weighing computational versus wet-lab antibody discovery can keep up with this shift via daily.dev."}}]} ```