Radar / AI models / AlphaGenome 2

AlphaGenome 2: DeepMind's DNA model now works cell by cell

Google DeepMind released AlphaGenome 2, a model that predicts how DNA variants change gene activity in a specific human cell type or state rather than a tissue average, trained on 107M+ single-cell profiles; free for non-commercial research via the AlphaGenome API.

new launchmodels · frontierJEV traction 0.67added 2026-11-12
Open AlphaGenome 2 →View on the radar

Why it matters

The first variant-effect model conditioned on cell identity: it recovered 30% of putatively causal expression-linked variants at 90% precision on TenK10K versus 16% for AlphaGenome 1, nearly doubling recall where a variant only matters in one cell type.

What you could build with it

A genomics research team could feed its own single-cell experiment as the conditioning input and rank candidate disease variants per cell type, turning a genome-wide association hit list into a shortlist of cell-specific mechanisms to test in the lab.

Does it hold up?

Too early to judge: available today for non-commercial research via API with Colab tutorials, but all benchmark figures are DeepMind's own, it is research-only with no clinical validation, and no independent replication exists yet.

Built with AlphaGenome 2

Learn more

technical deep dive →

First spotted on article: source.

More AI models

VoiceStudio: open-source, fully-local ElevenLabs alternative for voice cloning, dubbing, and audiobooksdebpalash/VoiceStudio is a desktop app that runs voice cloning, voice design, video dubbing, dictation, transcription…models · JEV 0.75Edge0-145B: open 145B MoE that runs on a single consumer GPUEdge0 open-sourced 145B and 120B latent-MoE models derived from Qwen3.8-Flash-Next, plus an inference framework that…models · JEV 0.74Strata: run a 125B model on a gaming PCFree, MIT-licensed local inference engine that runs Qwen3.8-Flash-Next (125B MoE, about 6B active per token) on…models · JEV 0.73Google AI Edge Gallery: offline speech recognition and synthesis on-deviceGoogle added fully offline speech recognition and text-to-speech to AI Edge Gallery, with ML Kit APIs on Android and…models · JEV 0.73Soup: fine-tune an 8B LLM on a 4 GB laptop GPU from one YAML fileAn open-source CLI that fine-tunes LLMs from a single YAML file, with layer streaming that trains an 8B model on a 4…models · JEV 0.73Tencent Hunyuan Hy3: open 295B MoE with 21B active under Apache 2.0Tencent open-sourced Hy3, a 295B-parameter mixture-of-experts model with only 21B parameters active per token, under…models · JEV 0.73

Get the week's best AI launches, plus 3 ideas worth building

One email every Saturday. Ranked by traction, not hype. Free.