
AlphaGenome
DeepMind's DNA sequence model — 1M base pairs, 11 modalities at once.
About
AlphaGenome, launched by Google DeepMind on June 25, 2025, is a large-scale deep-learning system that predicts how DNA segments regulate gene expression and how single-nucleotide variants disrupt that regulation. It accepts up to one million base pairs of sequence and produces thousands of quantitative predictions across 11 modalities — gene expression, splicing, chromatin accessibility, histone marks, transcription factor binding, and 3D genome contacts — outperforming the best alternative models in 22 of 24 evaluated genome tracks. A September 2026 Atlas release precomputed predictions for all 9 billion possible human single-nucleotide variants.
Limitations: the API is free for non-commercial use only, with commercial access via Google Cloud listed as coming soon; predicting effects of mutations on genes more than 100,000 base pairs away remains difficult. Trained on human and mouse data, with untested effectiveness on other organisms.
Specs
Context window
Pricing
Free quota
API access
Weights
Released
Benchmarks
Provider-reported unless a source says otherwise. Benchmarks are marketing-adjacent by nature — treat them as directional.
Use cases
Trust score — 9/10
Scored 9/10 (verified tier, metrics-v1). Evidence: Verified via vendor site/docs/GitHub and reputable coverage, wave 63; Trending score 88/100 from researcher assessment.