Google’s Atlas of the human genome could pave the way for new treatments
Google DeepMind launches AlphaGenome Atlas, a catalog of predicted molecular effects for roughly nine billion single-letter DNA changes across the human genome.
Google DeepMind unveiled AlphaGenome Atlas, a roughly 1-petabyte dataset predicting how each of about nine billion possible single-nucleotide variants affects molecular biology, including non-coding regions that regulate gene behavior. It builds on the AlphaGenome model released in 2025 and adds a Variant Impact Score (AVI) to help researchers rank variants. The catalog is available for noncommercial research via a web portal, the Antigravity platform, and the AlphaGenome interface, with commercial access on Google Cloud planned.
- Extends predictions beyond protein-coding mutations to regulatory, non-coding genome regions
- Variant Impact Score ranks which of ~9 billion variants warrant closer study
- Builds on DeepMind's AlphaGenome and AlphaMissense from the AlphaFold lineage
- Commercial use will be offered through Google Cloud; free for noncommercial research
- Vendors
- GoogleGoogle Cloud
- Organizations
- Google DeepMindIsomorphic Labs
- AI models
- AlphaGenomeAlphaMissense
From the original article
3 min read at theverge.com
Google DeepMind has unveiled an AI tool that its scientists claim could help unravel the mysteries of the human genome and transform our understanding of biology, accelerating scientific research and ultimately paving the way for new treatments for diseases.
By Robert Hart · theverge.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.