Multi-Modal Foundation · google
AlphaGenome
Predicts DNA regulatory features, such as gene expression and TF binding, at single-nucleotide resolution.
What AlphaGenome is
AlphaGenome is a genomics model developed by Google DeepMind. It is designed to model genomic regulation by analysing DNA sequence data.
The model identifies and predicts fundamental DNA regulatory features, including gene expression, chromatin accessibility, and transcription factor (TF) binding, providing readout values at single-nucleotide resolution.
Key facts
- Resolution
- Single-nucleotide
- Application domain
- Genomics
What you can use it for
- Gene expression prediction
- Predicts gene expression levels directly from genomic DNA sequences at single-nucleotide resolution.
- Chromatin accessibility profiling
- Identifies regions of accessible chromatin across the genome from raw sequence inputs.
- Transcription factor binding site prediction
- Maps transcription factor binding events along DNA sequences at base-pair precision.
Run it here
We list this model but cannot run it yet: gated on the Hub — never run past a gate the user did not accept.
Everything on this page still applies. Running it needs a loader for this repository, not a bigger machine.
Strengths and limits
Good at
- Resolves regulatory predictions at single-nucleotide precision.
- Simultaneously models multiple modalities of genomic regulation, including gene expression, chromatin accessibility, and transcription factor binding.
Inputs and outputs
You provide
Sequence or text
A protein or nucleotide sequence, or free text — whichever this model was trained on.
You get back
Mean-pooled representation, one vector per input.
Licence
Check the licence before commercial use · other
This model is gated by its authors — its licence has to be accepted on the source repository before it will run.
Questions
Can I use AlphaGenome commercially?
Check the licence before commercial use. This model is gated by its authors — its licence has to be accepted on the source repository before it will run.
What biological features does AlphaGenome predict?
AlphaGenome predicts DNA regulatory features, specifically gene expression, chromatin accessibility, and transcription factor binding.
What is the resolution of the model's outputs?
The model generates predictions at single-nucleotide resolution.
Who created AlphaGenome?
The model was developed by Google DeepMind.
Written from AlphaGenome's own documentation (model card). Statements citing a figure that does not appear there are removed before publication. Licence and running details come from our registry.