DNA Sequence-Based Genome Function Prediction Model (AlphaGenome)
- Purpose: Takes DNA sequences up to 1 million bp in length as inputPredicts genomic functions at single-base resolution, including gene expression, splicing, chromatin, and 3D contacts
- Use Case: Particularly focused on predicting the effects of regulatory variants
Input: specific genomic region + variant → Predicts and visualizes the impact of variants on RNA expression, etc.
API code
AlphaGenome: AI for better understanding the genome
Introducing a new, unifying DNA sequence model that advances regulatory variant-effect prediction and promises to shed new light on genome function — now available via API.
https://deepmind.google/discover/blog/alphagenome-ai-for-better-understanding-the-genome/
Documentation
Exploring the genome with AlphaGenome — AlphaGenome
This API provides access to AlphaGenome, Google DeepMind’s unifying model for
deciphering the regulatory code within DNA sequences.
https://www.alphagenomedocs.com/
Paper
storage.googleapis.com
https://storage.googleapis.com/deepmind-media/papers/alphagenome.pdf
Huggingface (non commercial open)
AlphaGenome - a google Collection
Collection of AlphaGenome models.
https://huggingface.co/collections/google/alphagenome

Seonglae Cho