Google DeepMind Unveils AlphaGenome 2 for Cell-Specific Variant Prediction
Google DeepMind unveiled AlphaGenome 2, a model designed to predict how genetic variants affect specific cell types and states. The company says it was trained on more than 100 million individual cell profiles spanning 68 tissues and identifies nearly twice as many variants that can alter gene expression as its predecessor, though these performance claims are company-reported. Google is making the model available for non-commercial research through the AlphaGenome API, with a limited private preview for commercial research. Why it matters: AlphaGenome 2 extends AI-based genetic analysis from broader genome predictions toward cell-specific effects, giving researchers a finer-grained way to connect population genetic variants with cell biology. What do you think?
Open the headline: source, AI briefing and more →Comments
…