Google DeepMind 发布 AlphaGenome 2：单细胞类型聚焦训练，突变识别翻倍
DeepMind 把 AlphaGenome 升级到 2 代，训练数据覆盖 68 种组织和超过 1 亿条测序数据，这次专门按细胞类型分别建模，找出的基因调控突变比上代多近一倍。做基因组学或精准医疗研究的团队应该会感兴趣，比旧版分辨率高一档。
Google DeepMind 推出 AlphaGenome 2，模型基于 100M+ 个跨 68 种组织的测序数据进行训练。
新版本的核心变化是按单一细胞类型分别建模，而不是一次性处理整个组织样本。这一策略让模型识别调控基因开关的突变数量接近上一代的两倍。
团队将整体组织的信号比作模糊图像：能看清整体轮廓，却丢失单个像素内部的变化细节。此前版本 AlphaGenome 已用于基因组功能注释，新版将同样的预测框架收紧到细胞类型粒度。
对基因组学研究者而言，这意味着在区分致病调控突变与良性变异时获得更高分辨率的计算工具。
Looking at a whole tissue at once is like looking at a blurry image: you get the visuals, but miss what’s happening inside individual pixels. Trained on 100M+ profiles across 68 tissues, AlphaGenome 2 focuses on one cell type at a time, spotting nearly twice as many mutations that turn genes on and off as our previous model.📊 20 ⚡
This report is categorized under AITOP's "Models" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include AlphaGenome 2, Google DeepMind, 基因组学, 多模态.
Source attribution: curated from Google DeepMind (@GoogleDeepMind).
