Google DeepMind precomputes 9 billion DNA variants to speed disease research

AlphaGenome maps 9B DNA variants

Google DeepMind has released the AlphaGenome Atlas, a public repository of precomputed predictions for all 9 billion possible single-letter changes to a reference human genome. Built with the AlphaGenome AI model, the Atlas offers a no-code interface and a new single-number impact score, letting scientists quickly assess whether a variant is likely to matter. The roughly 1-petabyte dataset could accelerate fundamental biology and treatment development, though experts caution the score may oversimplify complex genetic effects.