Google DeepMind 发布 AlphaGenome 图谱

Google DeepMind 发布 AlphaGenome 图谱
AlphaGenome Atlas: a high-resolution map of human DNA

原始链接: https://blog.google/innovation-and-ai/models-and-research/google-deepmind/alphagenome-atlas/

Google DeepMind 推出了 **AlphaGenome Atlas**，这是一个开创性的数据库，旨在破译人类基因组中此前被称为“非编码”或“神秘”DNA 的那 98% 部分。通过使用 AlphaGenome AI 模型，研究人员预先计算了所有 90 亿种可能的单字母遗传变异的调控影响，生成了一个 1PB 大小的数据集。为了简化这种复杂性，该图谱引入了 **AlphaGenome 变异影响 (AVI) 分数**。该指标整合了编码和非编码区域的数据，使科学家能够快速优先筛选出最重要的遗传变异进行研究。该图谱在临床和研究领域已展现出变革性的意义。它已成功帮助确定了罕见疾病的遗传病因，并揭示了非编码变异与复杂性状（如 BMI）之间隐藏的关联。通过提供直观的无代码网络门户，AlphaGenome Atlas 让这些信息的使用更加普及，使全球研究人员能够加速生物学发现并破解长久以来的基因组谜团。

Google DeepMind 近日发布了“AlphaGenome Atlas”，这是一个包含 1PB 数据量的庞大数据集，预先计算了人类基因组中所有可能的单核苷酸变异对调控功能的影响。这一消息在 Hacker News 上引发了激烈讨论。支持者认为这是重大的科学贡献，也是医学研究的有用资源；然而，基因组学领域的批评者和专家提出了几点担忧： * **科学效用：** 许多人认为，该模型相比 Borzoi 等现有的顶尖模型并没有显著提升。一些专家警告称，序列到功能的预测在处理复杂的人类生物学时，本质上仍然存在局限且不可靠。 * **方法论质疑：** 怀疑论者指出，近期针对简单生物的研究显示，AI 模型未能准确预测突变的影响，这表明目前针对人类尺度的预测充其量只是推测。 * **企业与伦理顾虑：** 此次发布引发了关于 Google 在科学研究中角色的争论。用户讨论了私营公司控制基础生物学数据的风险、基准测试指标的透明度，以及该项目究竟是真正的科学进步还是仅仅为了企业公关。尽管有人希望该图谱最终能助力临床诊断，但许多人对其当前的临床价值仍持怀疑态度。

原文

The human genome is made of about 3 billion base pairs of DNA — but much of it remains a mystery. Scientists understand the 2% of the human genome that codes for proteins relatively well, but have only limited knowledge of the remaining 98%. Our AlphaGenome model has already shown how single changes in these non-coding DNA regions can disrupt molecular processes like protein production, but the bigger picture remained unclear.

Today, we're introducing AlphaGenome Atlas, a database that predicts the effects of every possible single nucleotide variant in the human genome. We used the AlphaGenome AI model to pre-calculate the regulatory impact of all 9 billion single-letter genetic changes, resulting in a massive, 1-petabyte dataset. Our new Atlas helps scientists rapidly query this vast information.

To help researchers rapidly navigate this, the Atlas introduces the AlphaGenome Variant Impact (AVI) score. This single, easy-to-use score combines predictions for both coding and non-coding regions, allowing researchers to quickly prioritize the most promising avenues for research without sifting through thousands of data points.

Empowering researchers to solve biological mysteries

AlphaGenome Atlas is already acting as a powerful augmentation partner for the scientific community, accelerating research in areas like:

Rare genomic variations: At the Broad Institute, Laura Covill and her team used the AVI score to prioritize variants for unsolved rare disease research. The tool highlighted a critical variant in the DNM1 gene, predicting that it created an incorrect splice site. This provided crucial supporting evidence to successfully solve the case.
Complex traits: Identifying rare, non-coding variants linked to complex traits is difficult due to statistical noise. Dr. Gareth Hawkes applied AlphaGenome Atlas to data from 54,000+ UK Biobank participants. By grouping variants based on predicted molecular effects, he uncovered 22% more non-coding genetic associations. Focusing on the top 1% of impactful variants, he identified 19 genetic regions linked to body mass index (BMI), directing the next stage of targeted research.

Opening access to researchers and biologists worldwide

AlphaGenome Atlas is available today through an intuitive website portal that requires zero coding skills, democratizing access for clinical researchers and biologists worldwide. This is part of our ongoing commitment to accelerate genomic discovery and science, for everyone.

AlphaGenome Atlas provides grounded genomic insights that will accelerate the pace of biological discovery.