Google DeepMind 发布 AlphaGenome 2,可预测 DNA 突变对特定细胞的影响
DeepMind 的 AlphaGenome 2 升级了基因组突变预测:能 zoom 到单一细胞类型,而不是像初代那样混合整块组织,捕捉调控突变的量差不多翻倍,还能靠少量样本泛化到没见过的细胞。做遗传研究、精准医疗的人可以关注,这是 AlphaFold 路线在基因组学上的延续。
Google DeepMind 发布了 AlphaGenome 2,这是一个升级版的 AI 模型,用于预测单个 DNA 突变会在某一特定类型的细胞中产生什么作用。相比初代 AlphaGenome,新模型能聚焦于单一细胞类型,而旧版本则是将整个组织的数据混合在一起进行预测。
在具体能力上,AlphaGenome 2 捕捉调控基因表达水平(上调或下调基因)的突变数量接近初代的 2 倍。它还能通过实验室的少量样本,对从未见过的细胞类型进行预测。
NEW: Google DeepMind released AlphaGenome 2, its upgraded AI model that predicts what a DNA mutation does in one specific kind of cell. What changed from the first AlphaGenome: - Zooms in on one kind of cell, where the original blended a whole tissue together - Catches nearly 2x the mutations that dial a gene up or down - Works on kinds of cells it has never seen, using a small sample from a lab
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, Google DeepMind, 基因突变预测, 生物信息.
Source attribution: curated from The Rundown AI (@therundownai).