google-deepmind/alphagenome

What it solves

AlphaGenome is designed to decipher the regulatory code within DNA sequences. It addresses the challenge of predicting how changes in DNA (variants) affect biological functions, providing a state-of-the-art approach to regulatory variant effect prediction.

How it works

It is a multimodal model that analyzes DNA sequences up to 1 million base pairs in length. It provides predictions at single base-pair resolution for various functional outputs, including:

• Gene expression
• Splicing patterns
• Splicing patterns
• Chromatin features
• Contact maps

Who it’s for

Researchers and scientists working in genomics and bioinformatics who need to perform small to medium-scale analyses of genomic regions or variants.

Highlights

• Multimodal Predictions: Predicts multiple diverse functional genomic outputs simultaneously.
• High Resolution: Delivers predictions at single base-pair resolution for most outputs.
• Large Sequence Window: Capable of analyzing sequences up to 1 million base pairs.
• Client Library: Includes a Python API, visualization tools for matplotlib, and tutorials to help users integrate the model into their research.