AuraTracer智迹闻
中文

EVENT DOSSIER

DeepMind releases AlphaGenome Atlas: Free access to 1PB of human genome data with 9 billion variations predictions

2026-09-09 08:00 Models 🔥 47.2 heat score
2sources
1days unfolding
47.2heat score
6mentions
SummaryAI generated

On September 8, 2026, Google DeepMind officially launched the AlphaGenome Atlas platform. Based on the AlphaGenome model, it pre-calculated the molecular impacts of approximately 9 billion single-base mutations in the human reference genome. This dataset covers a size of 1PB, more than 30 times larger than the AlphaFold database. It is available for non-commercial use and academic institutions, and an AVI mutation impact score has been introduced to assist genetic research. Currently, external research teams have significantly improved detection efficiency using this platform in the localization of mutations causing rare diseases and population genetics analysis. Google plans to launch a commercial version in the future, but experts point out that predicted results do not directly equate to conclusions about pathogenicity, and the model’s ability to cover complex processes such as long-distance regulation remains limited.

Related eventsRELATED EVENTS
Key entitiesKEY ENTITIES
Broad InstituteBroad Research InstituteExeter University, UKGREGoR ConsortiumGoogle DeepMindNature

Coverage · reports per dayLANGUAGE SPLIT

Entity relations
Broad Institute × GREGo…1Broad Institute × Googl…1Broad Institute × Nature1GREGoR Consortium × Goo…1GREGoR Consortium × Nat…1Google DeepMind × Nature1

Integrated timelineUNIFIED TIMELINE

  1. 2026-09-09

    一口气算完90亿种DNA变化,谷歌用AI破解罕见病

    当地时间 9 月 8 日,谷歌 DeepMind 发布人类基因组预测平台 AlphaGenome Atlas,可预测人类基因组中约 90 亿种单字母 DNA 变化。该平台基于 AlphaGenome 模型预先计算变异分子影响,形成规模达 …

    2 reports

SignalsSIGNALS

Keyword heat
  • Google DeepMind2
  • Nature1
  • Broad Institute1
  • GREGoR Consortium1
  • Broad Research Institute1
  • Exeter University, UK1

All reports (2)SOURCES

新浪科技 zh 2026-09-09 08:00

人类基因组的90亿种基因变异,DeepMind全算了一遍,1PB数据免费开放

Google DeepMind 基于 AlphaGenome 模型,免费开放了包含人类参考基因组中超过 90 亿种单碱基变异预测结果的 AlphaGenome Atlas 数据集,规模达约 1 PB。该数据集支持非商业用途查询,并配套推出 AVI 变异影响分数以辅助遗传学研究中的变异筛选与排序。研究团队通过模型蒸馏及 GPU 优化完成了此次大规模预计算。目前已有外部机构利用该工具在罕见病致病变异定位及人群遗传学关联分析中成功缩小候选范围,提升检测效率。专家评价认为该数据库降低了算力门槛并简化了分析流程,但也指出其预测结果不直接等同于致病性结论,且受限于模型对远距离调控及复杂间接过程的覆盖能力。

第一财经·新闻 zh 2026-09-09 08:00

一口气算完90亿种DNA变化,谷歌用AI破解罕见病

当地时间 9 月 8 日,谷歌 DeepMind 发布人类基因组预测平台 AlphaGenome Atlas,可预测人类基因组中约 90 亿种单字母 DNA 变化。该平台基于 AlphaGenome 模型预先计算变异分子影响,形成规模达 1PB 的数据集,数据体量是 AlphaFold 数据库的 30 多倍。目前平台通过网页、API 及 Antigravity 技能向学术研究开放,非商业用户免费使用;谷歌计划推出商业版本。平台配套发布 AVI 评分,结合 AlphaGenome 与 AlphaMissense 结果,覆盖蛋白质编码区与非编码区。在罕见病研究中,Broad 研究所科学家 Laura Covill利用该工具从数百万变异中锁定关键剪接错误,埃克塞特大学研究员 Gareth Hawkes将其用于筛选英…