{"id":607372,"date":"2026-05-27T22:17:27","date_gmt":"2026-05-27T22:17:27","guid":{"rendered":"https:\/\/www.newsbeep.com\/uk\/607372\/"},"modified":"2026-05-27T22:17:27","modified_gmt":"2026-05-27T22:17:27","slug":"move-over-alphafold-open-source-model-predicts-shape-of-1-billion-proteins","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/uk\/607372\/","title":{"rendered":"Move over, AlphaFold: open source model predicts shape of 1 billion proteins"},"content":{"rendered":"

\"A<\/p>\n

The AI tool designed binders against Cytotoxic T-lymphocyte-associated protein 4 (CTLA-4). Credit: Molekuul\/Science Photo Library<\/p>\n

The known protein universe just got a lot bigger. A newly released artificial-intelligence tool has generated an atlas of more than one billion predicted protein structures and billions more protein sequences.<\/p>\n

The database, known as the ESM Atlas, was unveiled today by researchers at the Chan Zuckerberg Initiative\u2019s Biohub, a biomedical institute created in San Francisco, California, by Facebook founder Mark Zuckerberg and his wife, physician and educator Priscilla Chan.<\/p>\n

The atlas eclipses the AlphaFold Database<\/a> of predicted protein structures by more than 800 million entries, and a previous ESM Atlas<\/a> by some 300 million.<\/p>\n

The predictions were made using ESMFold2, an AI model that Biohub says surpasses the performance of AlphaFold3, the latest version of Google DeepMind\u2019s system and other protein-structure prediction AIs. The atlas is described in a preprint released today1<\/a>.<\/p>\n

\u201cWhat this atlas does is it shows the totality of protein biology and especially the parts that are most unknown,\u201d says Biohub science head Alex Rives, who led the effort. \u201cWe think it\u2019s going to be a really powerful substrate for the discovery of new biology.\u201d<\/p>\n

Other scientists are impressed with the results, especially that ESMFold2 is fully open source. But the Biohub model enters an increasingly crowded field, in which competing open-source and proprietary protein models are making gains at breakneck speed.<\/p>\n

Antibody predictions<\/p>\n

ESMFold2 is based on a \u2018protein language\u2019 model that Rives\u2019s team unveiled in 2024, which was trained on billions of proteins from across the tree of life. It includes \u2018metagenomic\u2019 sequences from soil, ocean and other environments, which are absent from the AlphaFold database of predicted protein structures.<\/p>\n

Rives\u2019 team say ESMFold2 outperforms existing methods, including AlphaFold3, at determining the correct structure of complexes of interacting proteins \u2013 including antibody molecules binding to their antigen molecular targets.<\/p>\n

\"\"<\/p>\n

AlphaFold is running out of data \u2014 so drug firms are building their own version<\/p>\n

<\/a><\/p>\n

In the preprint, the researchers describe how they used ESMFold2 to design new antibodies and other proteins that can strongly attach to proteins implicated in cancers and immunological conditions. When created and tested in the lab, a high proportion of the designs worked as predicted.<\/p>\n

Rives\u2019s team used the tool to create an atlas containing 1.1 billion predicted protein structures as well as information on the sequences of 6.8 billion proteins. Most of these come metagenomic sequences that had been only poorly characterized. Rives hopes that the atlas \u2014 which will be freely accessible \u2014 will help scientists to make connections between the known and unknown parts of the protein universe. Using the atlas, the researchers found structural similarities between CRISPR microbial defence proteins and a gene-editing protein identified in a soil fungus in 2023 and found in other eukaryotic species.<\/p>\n

Supplementary database<\/p>\n","protected":false},"excerpt":{"rendered":"The AI tool designed binders against Cytotoxic T-lymphocyte-associated protein 4 (CTLA-4). Credit: Molekuul\/Science Photo Library The known protein…\n","protected":false},"author":2,"featured_media":607373,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[5],"tags":[3252,84,170910,59,4230,11376,4231,5395,90,56,54,55],"class_list":["post-607372","post","type-post","status-publish","format-standard","has-post-thumbnail","category-business","tag-biotechnology","tag-business","tag-databases","tag-gb","tag-humanities-and-social-sciences","tag-machine-learning","tag-multidisciplinary","tag-proteomics","tag-science","tag-uk","tag-united-kingdom","tag-unitedkingdom"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts\/607372","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/comments?post=607372"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts\/607372\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/media\/607373"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/media?parent=607372"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/categories?post=607372"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/tags?post=607372"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}