Searchable database of AlphaGenome predicted effects for every possible single-nucleotide change in the human genome.
Updated EU status checked Last shown
Sources: creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
AlphaGenome Atlas is a Google DeepMind resource that collects predictions from the AlphaGenome model for single-letter (single-nucleotide) variants across the human genome. According to a creator summary, it covers more than 9 billion possible variants and amounts to roughly 1 PB of data.
Each variant carries an impact score. The same summary reports that using these scores found about 22% more genetic associations in UK Biobank data than the comparison it describes. The database is described as publicly searchable.
The resource is aimed at researchers in genetics and genomics who want to look up the predicted regulatory effect of a variant without running the model themselves. It is a research resource, not a consumer product. Details on the interface, access method, licensing and exact release date could not be verified from official pages, so the information here rests on a single secondary description.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Database of AlphaGenome predictions for every possible single-letter human DNA mutation (over 9 billion variants, ~1 PB). Includes an impact score and found 22% more genetic associations in UK Biobank data. Publicly searchable.
Closest neighbours by meaning, not just by category.
App · Google
Google suite of science tools whose "science skills" connect Gemini to 30+ life science databases such as UniProt and AlphaFold.
Model · Google DeepMind
Google DeepMind and Isomorphic Labs' model predicting structures of proteins, nucleic acids, ligands and their complexes.
Model · Hugging Face
Open 14.8B language model from Hugging Face that reads raw DNA in chat and answers in English, built on Qwen3-14B.
Research · OpenAI
OpenAI, PerturbAI and Scripps Research run thousands of GPT-Rosalind agents in parallel to analyze brain-cell gene data.
Model · Google DeepMind
Plant genomic language model from Living Models, trained on 320 plant species and paired with Gemma 4 for crop genetics.
Model · Google DeepMind
Google DeepMind diffusion pipeline for de novo enzyme design by motif scaffolding, with open code and downloadable weights.