引导式测验 · 中等 等级
抗体和蛋白质设计测验中的人工智能
了解结构预测、基于扩散的主链生成和序列设计如何为蛋白质工程贡献不同的步骤。
问题 1 的 8
DeepMind 的 AlphaFold 取得了哪些著名的成就?
预览每个问题8 问题
当您参加测验时,就会出现答案和解释。
- DeepMind 的 AlphaFold 取得了哪些著名的成就?
- 根据序列准确预测蛋白质结构
- 更快的互联网路由
- 更好的天气预报
- 更便宜的太阳能电池板
- 射频扩散有什么作用?
- 下棋
- 通过扩散生成新的蛋白质骨架
- 翻译语言
- 压缩图像
- ProteinMPNN 在蛋白质设计中的作用是什么?
- 它打印物理蛋白质
- 它测量温度
- It proposes amino-acid sequences compatible with a target backbone
- 它可以编辑活体患者的 DNA
- 在抗体中,AI通常设计什么部分来结合靶标?
- 细胞膜
- 线粒体
- 核糖体
- CDR结合环
- 为什么预测设计的蛋白质链如何折叠如此重要?
- Structure influences protein function, which still requires experimental testing
- 颜色取决于它
- 它设置细胞的温度
- 它仅决定血型
- When an AI-designed protein is developed as a therapeutic biologic for human use in the United States, what additional step applies before marketing?
- The applicable development and regulatory review, including a biologics license application when required
- No review, because computational design establishes safety
- Only a structure-prediction benchmark
- Approval for every research protein before any laboratory study
- What kind of structure does AlphaFold-Multimer aim to predict?
- Only the DNA sequence of a single gene
- The exact number of cells in a tissue
- The arrangement of multiple interacting protein chains in a complex
- The amino-acid sequence without any structure
- What types of molecules can AlphaFold 3 model in addition to proteins?
- Only additional protein chains
- Only whole cells and tissues
- Every chemical reaction rate in a living organism
- DNA, RNA, and small-molecule ligands in biomolecular complexes