收录解读
- 分级：`颠覆性` - 正式标题：`Advancing regulatory variant effect prediction with AlphaGenome` - 原文：`2026-01-28-LS1_AlphaGenome-Advancing_regulatory_variant_effect_prediction_with_AlphaGenome.html` - 抽取：`extracted.md`
## 重写摘要
AlphaGenome 的核心突破，在于把以往碎片化的“一个任务一个基因组模型”整合成统一的序列到功能基础模型。它一次输入 1 Mb DNA 序列，能在单碱基分辨率上同时预测表达、转录起始、染色质可及性、组蛋白修饰、转录因子结合、染色质接触图以及剪接等多种模态，并覆盖 5,930 个人类轨迹和 1,128 个小鼠轨迹。论文报告它在 26 项变异效应评测中匹配或超过现有最强外部模型中的 25 项。
这不是单一指标的提升，而是把“非编码调控变异解释”从多个割裂模型拼装，推进到一个统一底座上。更关键的是，作者展示它能同时跨模态给出变异效应评分，并较准确地重建临床相关致病机制，例如 TAL1 附近非编码变异的调控作用。这使它开始接近真正的“调控基因组基础模型”。
## 为什么重要
如果 AlphaFold 重塑了静态结构预测，AlphaGenome 代表的是对“暗基因组”调控逻辑的系统级推进。它对疾病机制解析、变异致病性评估、合成调控元件设计和下游实验优先级排序都可能产生平台级影响。
## 局限
它仍然主要是预测模型，不等于完整因果证明。对跨个体、跨环境和更复杂多组学条件下的泛化边界，仍需要更严格的外部验证。当前目录里保留的是 Nature 正文 HTML，未保留完整 PDF。
原始摘要
Deep learning models that predict functional genomic measurements from DNA sequences are powerful tools for deciphering the genetic regulatory code. Existing methods involve a trade-off between input sequence length and prediction resolution, thereby limiting their modality scope and performance . We present AlphaGenome, a unified DNA sequence model, which takes as input 1 Mb of DNA sequence and predicts thousands of functional genomic tracks up to single-base-pair resolution across diverse modalities. The modalities include gene expression, transcription initiation, chromatin accessibility, histone modifications, transcription factor binding, chromatin contact maps, splice site usage and splice junction coordinates and strength. Trained on human and mouse genomes, AlphaGenome matches or exceeds the strongest available external models in 25 of 26 evaluations of variant effect prediction. The ability of AlphaGenome to simultaneously score variant effects across all modalities accurately recapitulates the mechanisms of clinically relevant variants near the TAL1 oncogene . To facilitate broader use, we provide tools for making genome track and variant effect predictions from sequence.