Google DeepMind Releases AlphaGenome Atlas
Recorded: Sept. 8, 2026, 3:08 p.m.
| Original | Summarized |
Introducing AlphaGenome Atlas Skip to main content AlphaGenome Atlas: a high-resolution map of human DNA Innovation & AI Products & platforms Company news Feed Newsletter Back Innovation & AI Models & Research Google DeepMind Google Research Google Labs Gemini models Quantum computing See all Products Developer tools Gemini app Gemini Notebook See all Infrastructure & cloud Global network Google Cloud See all Technology Safety & Security Health See all Learn more: Google DeepMind blog Google Research blog Google Developers blog Google Cloud blog Back Products & platforms Products Search Maps Chrome Google Health Google Workspace Learning & Education Shopping See all Platforms Android Google Play Wear OS See all Devices Pixel Google Nest Fitbit Chromebooks See all Learn more: Google Ads & Commerce blog Waze blog Back Company news Outreach & initiatives Creating opportunity Safety & security Google.org Public policy Sustainability Health See all Leadership Sundar Pichai, CEO More authors See all Inside Google Around the globe Life at Google See all Learn more: Google Security blog Innovation & AI Innovation & AI Models & Research Google DeepMind Google Research Google Labs Gemini models Quantum computing See all Products Developer tools Gemini app Gemini Notebook See all Infrastructure & cloud Global network Google Cloud See all Technology Safety & Security Health See all Learn more: Google DeepMind blog Google Research blog Google Developers blog Google Cloud blog Products & platforms Products & platforms Products Search Maps Chrome Google Health Google Workspace Learning & Education Shopping See all Platforms Android Google Play Wear OS See all Devices Pixel Google Nest Fitbit Chromebooks See all Learn more: Google Ads & Commerce blog Waze blog Company news Company news Outreach & initiatives Creating opportunity Safety & security Google.org Public policy Sustainability Health See all Leadership Sundar Pichai, CEO More authors See all Inside Google Around the globe Life at Google See all Learn more: Google Security blog Feed AlphaGenome Atlas: a high-resolution map of human DNA Share x.com Copy link [] Preferences Global (English) Africa (English) Australia (English) Brasil (Português) Canada (English) Canada (Français) Česko (Čeština) Deutschland (Deutsch) España (Español) France (Français) Greece (Ελληνικά) India (English) Indonesia (Bahasa Indonesia) Ireland (English) Italia (Italiano) 日本 (日本語) 대한민국 (한국어) Latinoamérica (Español) Malaysia (Melayu) الشرق الأوسط وشمال أفريقيا (اللغة العربية) MENA (English) Nederlands (Nederland) New Zealand (English) Polska (Polski) Portugal (Português) România (Română) Sverige (Svenska) ประเทศไทย (ไทย) Türkiye (Türkçe) 台灣 (中文) Links Images RSS feed x.com Copy link Newsletter Breadcrumb Home Innovation & AI Models & research Google DeepMind AlphaGenome Atlas: a high-resolution map of human DNA Sep 08, 2026 x.com Copy link AlphaGenome Atlas is the most comprehensive catalogue of how genetic mutations affect molecular biology. Pushmeet Kohli Žiga Avsec Share x.com Copy link The human genome is made of about 3 billion base pairs of DNA — but much of it remains a mystery. Scientists understand the 2% of the human genome that codes for proteins relatively well, but have only limited knowledge of the remaining 98%. Our AlphaGenome model has already shown how single changes in these non-coding DNA regions can disrupt molecular processes like protein production, but the bigger picture remained unclear.Today, we're introducing AlphaGenome Atlas, a database that predicts the effects of every possible single nucleotide variant in the human genome. We used the AlphaGenome AI model to pre-calculate the regulatory impact of all 9 billion single-letter genetic changes, resulting in a massive, 1-petabyte dataset. Our new Atlas helps scientists rapidly query this vast information.To help researchers rapidly navigate this, the Atlas introduces the AlphaGenome Variant Impact (AVI) score. This single, easy-to-use score combines predictions for both coding and non-coding regions, allowing researchers to quickly prioritize the most promising avenues for research without sifting through thousands of data points.Empowering researchers to solve biological mysteriesAlphaGenome Atlas is already acting as a powerful augmentation partner for the scientific community, accelerating research in areas like:Rare genomic variations: At the Broad Institute, Laura Covill and her team used the AVI score to prioritize variants for unsolved rare disease research. The tool highlighted a critical variant in the DNM1 gene, predicting that it created an incorrect splice site. This provided crucial supporting evidence to successfully solve the case.Complex traits: Identifying rare, non-coding variants linked to complex traits is difficult due to statistical noise. Dr. Gareth Hawkes applied AlphaGenome Atlas to data from 54,000+ UK Biobank participants. By grouping variants based on predicted molecular effects, he uncovered 22% more non-coding genetic associations. Focusing on the top 1% of impactful variants, he identified 19 genetic regions linked to body mass index (BMI), directing the next stage of targeted research.Opening access to researchers and biologists worldwideAlphaGenome Atlas is available today through an intuitive website portal that requires zero coding skills, democratizing access for clinical researchers and biologists worldwide. This is part of our ongoing commitment to accelerate genomic discovery and science, for everyone.AlphaGenome Atlas provides grounded genomic insights that will accelerate the pace of biological discovery.Read more on the Google DeepMind blog. Posted in: Google DeepMind Related stories Google DeepMind Backing 16 green AI projects in Asia-Pacific By Google DeepMind Introducing WeatherNext 3, our most advanced and accurate global weather AI model By AI The latest AI news we announced in August 2026 By Google DeepMind Ask a Scientist: How do researchers use AI to predict a cyclone? By Gemini models What does “full-stack” AI actually mean? By Gemini models Omni experts share what excites them most about the model. By Privacy Terms Help More of Google Google Products About the Blog Global (English) Africa (English) Australia (English) Brasil (Português) Canada (English) Canada (Français) Česko (Čeština) Deutschland (Deutsch) España (Español) France (Français) Greece (Ελληνικά) India (English) Indonesia (Bahasa Indonesia) Ireland (English) Italia (Italiano) 日本 (日本語) 대한민국 (한국어) Latinoamérica (Español) Malaysia (Melayu) الشرق الأوسط وشمال أفريقيا (اللغة العربية) MENA (English) Nederlands (Nederland) New Zealand (English) Polska (Polski) Portugal (Português) România (Română) Sverige (Svenska) ประเทศไทย (ไทย) Türkiye (Türkçe) 台灣 (中文) |
AlphaGenome Atlas is introduced as a comprehensive database serving as a high-resolution map of the human DNA, providing insights into how genetic mutations affect molecular biology. The model leverages the AlphaGenome AI to predict the effects of every possible single nucleotide variant within the human genome. This process involved pre-calculating the regulatory impact of all nine billion single-letter genetic changes, resulting in an enormous one petabyte dataset designed to allow scientists to rapidly query this extensive information. To facilitate navigation through this vast dataset, the Atlas incorporates the AlphaGenome Variant Impact (AVI) score, which functions as a singular, easily utilized metric combining predictions for both coding and non-coding genomic regions. This scoring mechanism enables researchers to quickly prioritize the most promising directions for investigation without needing to sift through thousands of data points. The impact of the AlphaGenome Atlas is demonstrated through its role as an augmentation partner for the scientific community in several critical areas. For research into rare genomic variations, Laura Covill and her team at the Broad Institute utilized the AVI score to prioritize variants relevant to unsolved rare disease research, successfully highlighting a critical variant in the DNM1 gene that predicted an incorrect splice site, thereby providing crucial supporting evidence. Furthermore, the Atlas aids in the study of complex traits by addressing the difficulty statistical noise presents when identifying rare, non-coding variants. Dr. Gareth Hawkes applied AlphaGenome Atlas to data from over 54,000 UK Biobank participants and successfully uncovered twenty-two percent more non-coding genetic associations. By focusing on the top one percent of impactful variants, he was able to identify nineteen genetic regions linked to body mass index, which effectively directed subsequent targeted research efforts. AlphaGenome Atlas is being made accessible globally through an intuitive website portal that requires no coding skills, ensuring democratization of access for clinical researchers and biologists worldwide. This initiative underscores a commitment to accelerating genomic discovery by providing grounded insights. The platform represents Google DeepMind’s effort to deliver this knowledge, emphasizing the acceleration of biological discovery through advanced data modeling and accessibility. |