--- title: DeepMind's New AI Just Cracked The Code Of Life | daily.dev description: An interview with a DeepMind scientist explores AlphaGenome, a machine learning model that predicts the effects of genome variation at base-pair resolution... canonical: https://daily.dev/posts/deepmind-s-new-ai-just-cracked-the-code-of-life-ppgl9bjhl twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: DeepMind's New AI Just Cracked The Code Of Life | daily.dev og:description: An interview with a DeepMind scientist explores AlphaGenome, a machine learning model that predicts the effects of genome variation at base-pair resolution... og:url: https://daily.dev/posts/deepmind-s-new-ai-just-cracked-the-code-of-life-ppgl9bjhl og:image: https://api.daily.dev/og/posts/pPgl9bjHL.png og:image:alt: DeepMind's New AI Just Cracked The Code Of Life 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. # DeepMind's New AI Just Cracked The Code Of Life **[Two Minute Papers](https://daily.dev/sources/twoninutepapers)** · 33 min read · 0 upvotes · 0 comments ## Summary An interview with a DeepMind scientist explores AlphaGenome, a machine learning model that predicts the effects of genome variation at base-pair resolution across a 1-million base-pair context window, something no prior model (including its predecessor, Enformer) could achieve at that scale. It matched or beat the best comparison model in 25 of 26 variant effect benchmarks. The team also released AlphaGenome Atlas, a precomputed dataset of predicted effects for all possible single nucleotide variations across the human genome, 30 times larger than the AlphaFold database, free for non-commercial use with open model weights. The discussion covers transfer learning from training on both human and mouse genomes, the AlphaGenome Variant Impact Score for prioritizing variants, and future directions like cell and organism simulation. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is AlphaGenome and what does it predict? AlphaGenome is a DeepMind machine learning model that predicts the effects of genome variation, such as single nucleotide changes, on molecular phenotypes like gene expression and splicing. It operates at base-pair resolution across a 1-million base-pair context window, the first model to combine that resolution with such a large window, and matched or beat the strongest comparison model in 25 of 26 variant effect benchmarks. _Researchers evaluating genomics AI tools can follow model comparisons and benchmark results on daily.dev._ ### What is AlphaGenome Atlas and how big is it compared to the AlphaFold database? AlphaGenome Atlas is a precomputed, petabyte-scale dataset covering the predicted effects of all roughly 9 billion possible single nucleotide variations across the human genome. It is 30 times the size of the AlphaFold protein structure database and is made freely available to the scientific community for non-commercial research, including fine-tuning with released model weights. _Developers tracking large-scale open scientific datasets can follow AI-for-science releases on daily.dev._ ### Is AlphaGenome free to use and are the model weights available? Yes, AlphaGenome is free for non-commercial use, following the same approach DeepMind took with AlphaFold 1 and AlphaFold 2. The model weights are publicly available so academic researchers can use and fine-tune the model for their own genomics research. _Developers evaluating open-weight scientific models can keep track of new releases on daily.dev._ ## Similar posts on daily.dev - [AlphaGenome Decodes DNA's Hidden Secrets](https://daily.dev/posts/alphagenome-decodes-dna-s-hidden-secrets-5ltqipgdj) · IEEE Spectrum · 0 upvotes · 0 comments - [AI trained on bacterial genomes produces never-before-seen proteins](https://daily.dev/posts/ai-trained-on-bacterial-genomes-produces-never-before-seen-proteins-ltjcbudlu) · Ars Technica · 1 upvotes · 0 comments - [Google DeepMind & DOE Partner on Genesis: AI for Science](https://daily.dev/posts/google-deepmind-doe-partner-on-genesis-ai-for-science-uy9lvpota) · DeepMind · 0 upvotes · 0 comments - [Google I/O showed how the path for AI-driven science is shifting](https://daily.dev/posts/google-i-o-showed-how-the-path-for-ai-driven-science-is-shifting-p08sxf2im) · MIT Technology Review · 0 upvotes · 0 comments --- Tags: [#ai](https://daily.dev/tags/ai), [#machine-learning](https://daily.dev/tags/machine-learning) [View this post on daily.dev](https://daily.dev/posts/deepmind-s-new-ai-just-cracked-the-code-of-life-ppgl9bjhl) ```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":"DeepMind's New AI Just Cracked The Code Of Life","url":"https://daily.dev/posts/deepmind-s-new-ai-just-cracked-the-code-of-life-ppgl9bjhl","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/deepmind-s-new-ai-just-cracked-the-code-of-life-ppgl9bjhl"},"datePublished":"2026-10-07T13:45:57.104Z","dateModified":"2026-10-07T14:39:16.113Z","description":"An interview with a DeepMind scientist explores AlphaGenome, a machine learning model that predicts the effects of genome variation at base-pair resolution...","image":"https://i.ytimg.com/vi/Wkaw03p3BrM/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/Wkaw03p3BrM/sddefault.jpg","isAccessibleForFree":true,"articleSection":"Two Minute Papers","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":"Two Minute Papers","logo":"https://media.daily.dev/image/upload/s--8KXsSJ5q--/f_auto/v1711188923/logos/twoninutepapers","url":"https://daily.dev/sources/twoninutepapers"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/deepmind-s-new-ai-just-cracked-the-code-of-life-ppgl9bjhl","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai,machine-learning","timeRequired":"PT33M","video":{"@type":"VideoObject","name":"DeepMind's New AI Just Cracked The Code Of Life","description":"An interview with a DeepMind scientist explores AlphaGenome, a machine learning model that predicts the effects of genome variation at base-pair resolution...","thumbnailUrl":"https://i.ytimg.com/vi/Wkaw03p3BrM/sddefault.jpg","uploadDate":"2026-10-07T13:45:57.104Z","duration":"PT33M","url":"https://api.daily.dev/r/pPgl9bjHL","embedUrl":"https://www.youtube.com/embed/Wkaw03p3BrM"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Two Minute Papers","item":"https://daily.dev/sources/twoninutepapers"},{"@type":"ListItem","position":3,"name":"DeepMind's New AI Just Cracked The Code Of Life"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/deepmind-s-new-ai-just-cracked-the-code-of-life-ppgl9bjhl#faq","mainEntity":[{"@type":"Question","name":"What is AlphaGenome and what does it predict?","acceptedAnswer":{"@type":"Answer","text":"AlphaGenome is a DeepMind machine learning model that predicts the effects of genome variation, such as single nucleotide changes, on molecular phenotypes like gene expression and splicing. It operates at base-pair resolution across a 1-million base-pair context window, the first model to combine that resolution with such a large window, and matched or beat the strongest comparison model in 25 of 26 variant effect benchmarks. Researchers evaluating genomics AI tools can follow model comparisons and benchmark results on daily.dev."}},{"@type":"Question","name":"What is AlphaGenome Atlas and how big is it compared to the AlphaFold database?","acceptedAnswer":{"@type":"Answer","text":"AlphaGenome Atlas is a precomputed, petabyte-scale dataset covering the predicted effects of all roughly 9 billion possible single nucleotide variations across the human genome. It is 30 times the size of the AlphaFold protein structure database and is made freely available to the scientific community for non-commercial research, including fine-tuning with released model weights. Developers tracking large-scale open scientific datasets can follow AI-for-science releases on daily.dev."}},{"@type":"Question","name":"Is AlphaGenome free to use and are the model weights available?","acceptedAnswer":{"@type":"Answer","text":"Yes, AlphaGenome is free for non-commercial use, following the same approach DeepMind took with AlphaFold 1 and AlphaFold 2. The model weights are publicly available so academic researchers can use and fine-tune the model for their own genomics research. Developers evaluating open-weight scientific models can keep track of new releases on daily.dev."}}]} ```