Google DeepMind Unveils AlphaGenome 2 to Predict How DNA Variants Affect Individual Cell Types

At a glance

Google DeepMind has released AlphaGenome 2, a model that predicts how DNA sequences and their variations act in specific human cell types. Because the same DNA is read differently in different cells, the model could help researchers find the cellular causes of disease.

Key points

1. 1

   The earlier model looked at averages across tissues, while the new one predicts effects in detailed cell types such as heart muscle cells and immune cells.

2. 2

   The model now takes one condition at a time, such as a tissue, cell type, or state, as input.

3. 3

   It identifies nearly twice as many variants that change gene expression as the previous state-of-the-art model.

4. 4

   It was trained on more than 100 million individual cell profiles across 68 tissues.

Why it matters

Knowing which cells a disease-causing DNA variant affects could speed up drug development and research on rare diseases.

Also reported by

• The VergeGoogle’s AlphaGenome 2 zooms in on the cellular roots of disease
• Unite.AIGoogle DeepMind의 AlphaGenome 2, 세포 상태별 변이 효과 예측
• 사이언스모니터구글 딥마인드 ‘알파게놈 2’ 공개…유형별 DNA 변이 효과 예측
• DongA Science1년 반 걸리는 실험 30분 만에…구글 딥마인드, '알파게놈2' 공개