DeepMind published AlphaGenome, a long‑sequence DNA model that predicts regulatory activity and the effects of noncoding variants across up to one million base pairs. The Nature paper shows AlphaGenome can infer molecular properties—gene starts/stops, splicing, RNA production and chromatin accessibility—much faster and across larger contexts than prior models. DeepMind touts AlphaGenome’s utility for prioritizing rare regulatory variants, guiding target discovery, and designing synthetic regulatory sequences. Academic reviewers have already begun using AlphaGenome as a benchmark for variant‑effect prediction in regulatory genomics. The model’s release accelerates adoption of foundation models in genomics and raises questions about integrating AI predictions into target validation pipelines, regulatory submissions, and clinical variant interpretation workflows.