Reading more of a DNA change's consequences
AlphaGenome is a unified DNA-sequence model that takes up to 1 Mb of DNA and predicts thousands of functional genomic tracks, including gene expression, splicing, chromatin features, transcription-factor binding, and contact maps.
- Maturity
- Demonstrated, stage 3 of 4
- Support
- 1 source · paper
- Evidence detail
- How we know ↓
Most observed human genetic variation is non-coding, and interpreting its possible biological effects remains difficult.
Existing sequence-to-function methods traded off input sequence length against prediction resolution and often covered only selected biological modalities.
A deep-learning model jointly predicts many molecular genomic measurements and scores the likely effect of a sequence variant across those modalities.
What was shown, and what wasn’t
Shown
In the paper's external variant-effect evaluations, AlphaGenome matched or exceeded the strongest available external models in 25 of 26 evaluations; it also recapitulated mechanisms of clinically relevant variants near the TAL1 oncogene.
Not shown · limits
- The model predicts molecular effects; it does not diagnose a patient, establish causal disease mechanisms, or prove a treatment works.
- Training and evaluation draw on existing human and mouse experimental datasets.
- The paper describes non-commercial API access, not universal clinical availability.
Bright editorial interpretation
Researchers may be able to generate more integrated hypotheses about how a DNA variant changes gene regulation.
Still open
Which predictions validate in disease-relevant tissues and individuals?
Can use of the model improve rare-disease interpretation or therapeutic development prospectively?
How we know1 source · checked 2026-09-07 · no corrections
Original sources
Institutions: Google DeepMind
- Maturity
- Demonstrated
- Source published
- 2026-01-28
- Captured
- 2026-09-07
- Last source review
- 2026-09-07
- Editorial method
- AI-assisted source review
Bright compared this account with the linked original and supporting sources and kept reported, budgeted, projected, and observed claims distinct. Bright did not independently audit the underlying records.
Maturity describes the tested or operational setting. Confidence describes support for the particular claim; one does not determine the other.
Revision & correction history
2026-09-07 · Researchers may be able to generate more integrated hypotheses about how a DNA variant changes gene regulation.
No corrections recorded.
Keep exploring
Explore the shared question in another setting. These connections do not imply replication.