AlphaGenome 2: trained on 100M+ profiles across 68 tissues, 2x mutation detection
GoogleDeepMind · x · 2026-11-11
DeepMind shared details on AlphaGenome 2: analyzing whole tissue is like a blurry image—individual cell signals get lost. Trained on 100M+ profiles across 68 tissues, the model focuses on one cell type at a time and spots nearly twice as many gene-regulating mutations as its predecessor.
More from Research
- CypherGuard fixes structurally wrong LLM Cypher queries, hitting 88.5% on CypherBench — JeremyCMorgan · 2026-11-12
- PufferLib 5.0 trains a Rubik's Cube solver at 8.8M SPS on a single 12GB GPU — haydendevs · 2026-11-11
- 10-line deterministic polynomial-time primality test relies on OpenAI's recent quasi-GRH result, making AKS obsolete — fortnow · 2026-11-11
- WSP Weight Edits Shown Equivalent to Constrained Activation Steering on Qwen — kastnerkyle · 2026-11-11
- codec.audio benchmarks neural audio codecs on noisy in-the-wild speech; MOSS tops — kastnerkyle · 2026-11-11
- Sparse Rewiring owl-persona eval vs full SFT released with weights, data, code — maxsloef · 2026-11-11