AI News/Wire summary
AlphaGenome 2 predicts how DNA variants act in specific human cell types
Key points
- Conditional model predicts DNA effects for one tissue, cell type or state at a time, trained on over 107 million cell profiles.
- On the TenK10K immune dataset, it identified 30% of causal variants versus 16% for the original AlphaGenome fine-tuned on single-cell data.
- Available now for non-commercial research via the AlphaGenome API; commercial access is in private preview.
Why it matters for marketers: Content and research teams can test variant effects in disease-relevant cell types, and can request community use-case spotlights by 30 November.
Summary by the Z Media news desk, from the outlets' reporting. Read the full stories at the source.
Read the original
Google DeepMind: AlphaGenome 2: Deciphering how cells read DNA to better understand disease
More coverage
Related on Z Media
- Anthropic ships Fable 5.2 to all users, cuts prices and claims benchmark leadOur brief, via Anthropic, 6 days ago
- Anthropic reportedly presses ahead with IPO despite market jittersOur brief, via Anthropic, 5 days ago
- Google launches Gemini 4 Hydrogen, a faster model for everyday coding and agentsvia Google DeepMind, 2 days ago
- Google puts Gemini 4 Hydrogen into Search worldwide, with more visual answers and wider linkingOur brief, via Google AI, 2 days ago
- Google makes Gemini 4 Carbon widely available and previews agent swarmsOur brief, via Google DeepMind, 4 days ago
- Meta lets Muse users turn commands into mini apps called SpacesOur brief, via TechCrunch, 6 days ago