{"data":{"id":2344,"lang":"en","title":"Google DeepMind Releases AlphaGenome Atlas, a Map of 9 Billion Possible DNA Mutations","summary":"DeepMind's new AlphaGenome Atlas predicts the molecular effects of all 9 billion possible single-letter DNA mutations in a free 1-petabyte database.","category":"science","category_label":"Science","published_at":"2026-09-09T22:01:55Z","updated_at":"2026-09-09T22:01:55Z","url":"https://techtools.cz/tools/news/article/2344-google-deepmind-releases-alphagenome-atlas-a-map-of-9-billion-possible-dna","api_url":"https://techtools.cz/news-api/v1/articles/2344?lang=en","markdown_url":"https://techtools.cz/news-api/v1/articles/2344.md?lang=en","image_url":"https://lh3.googleusercontent.com/QgfG84W6jCtJ-CUm9zL1nLLNGTSqdCu-aQwKh-XmOQ-b-elP5oFEYEJpYi6lHRp0Ybzrh_OKHngAgv3L1lPoz8FM3FWoqGh-RnFuOgKKC-aL0sf8-No=w1440-h810-n-nu","word_count":153,"reading_time_minutes":1,"sources":[{"url":"https://deepmind.google/blog/alphagenome-atlas-a-predictive-map-of-every-possible-dna-letter-change-in-the-human-genome/","domain":"deepmind.google"},{"url":"https://siliconangle.com/2026/09/08/google-deepminds-alphagenome-atlas-maps-all-9-billion-possible-human-dna-changes/","domain":"siliconangle.com"}],"translation":{"lang":"cs","id":2417,"title":"Google DeepMind zveřejnil AlphaGenome Atlas, mapu 9 miliard možných mutací DNA","url":"https://techtools.cz/tools/news/clanek/2417-google-deepmind-zverejnil-alphagenome-atlas-mapu-9-miliard-moznych-mutaci-dna","api_url":"https://techtools.cz/news-api/v1/articles/2417?lang=cs"},"content":"Google DeepMind has released the AlphaGenome Atlas, a free public database that predicts the molecular effects of all 9 billion possible single-letter changes to human DNA. The dataset spans more than 1 petabyte, over 30 times larger than DeepMind's AlphaFold protein database.\n\nThe Atlas predicts how each mutation affects gene regulation across hundreds of human and mouse cell types and tissues, and introduces a new AlphaGenome Variant Impact (AVI) score that ranks how significant a variant is likely to be, covering both protein-coding and non-coding regions of the genome. Testing all 9 billion variants in a lab would be practically impossible, so the computational predictions let researchers narrow down candidates fast.\n\nEarly collaborators used the tool to identify mutations linked to epileptic encephalopathy and found 22% more genetic associations in protein studies than previous methods. The Atlas is available for free via a web portal and API, with additional access through Google Cloud."}}