作为先验的AlphaFold:在预训练的神经网络上条件化的实验性结构确定.
bioRxiv : the preprint server for biology
|March 3, 2025
概括
我们开发了ROCKET,这是一种通过将实验数据与AlphaFold2.2.2集成来增强蛋白质结构预测的方法. 机器人改进模型,捕捉了标准方法错过的关键生物变异.
科学领域:
- 结构生物学 结构生物学
- 计算生物学 计算生物学
- 生物物理学的生物物理.
背景情况:
- 机器学习,特别是AlphaFold2,已经彻底改变了从序列的蛋白质结构预测.
- 由于有限的高质量数据,在建模侧链包装,构造动力学和生物分子相互作用方面仍然存在挑战.
- 新兴的技术,如冷电子断层扫描 (cryo-ET) 和高通量晶体学产生庞大的结构数据,但模型解释是一个瓶.
研究的目的:
- 通过将实验测量与AlphaFold2.2结合起来,提高结构分析的效率.
- 开发一种名为ROCKET的AlphaFold2的增强,能够使用冷EM,冷ET和X射线结晶学数据来改进预测.
- 为了证明ROCKET能够捕捉超出AlphaFold2范围的生物显著结构变异的能力.
主要方法:
- 用ROCKET增强AlphaFold2,它通过使用冷EM,冷ET和X射线结晶学数据来改进预测.
- 在同进化嵌入空间中执行结构优化,而不是卡特西亚坐标,以自动化复杂的建模任务.
- 使用可微分的晶体学和冷电磁目标函数,可适应其他结构预测方法.
主要成果:
- ROCKET成功地改进了AlphaFold2的预测,捕获了AlphaFold2单独无法识别的生物学重要结构变异.
- 该方法自动化了具有挑战性的建模任务,包括功能循环翻转和域重排,超越了当前的最先进和手动建模.
- ROCKET不需要AlphaFold2重新训练,并且可以适应多元仪,联体联折和其他数据类型.
结论:
- ROCKET提供了一个新的框架,用于将实验数据与机器学习相结合,以进行增强的生物分子结构预测.
- 能够高效地采样跨越障碍的重排,为可扩展和自动化模型构建打开了新的道路.
- ROCKET的可扩展框架和可适应的目标函数有助于更广泛地将实验可观测值与结构生物学中的机器学习整合起来.
相关概念视频
Determination
17.8K
During embryogenesis, cells become progressively committed to different fates through a two-step process: specification followed by determination. Specification is demonstrated by removing a segment of an early embryo, “neutrally” culturing the tissue in vitro—for example, in a petri dish with simple medium—and then observing the derivatives. If the cultured region gives rise to cell types that it would normally generate in the embryo, this means that it is specified. In...
17.8K
Survival Tree
50
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a...
Building a Survival Tree
Constructing a...
50
Experimental Designs
11.0K
An experimental design is a systematic process that allows researchers to evaluate the relationship between dependent and independent variables. There are three widely used types of experimental design - pre-experimental design, true experimental design, and quasi-experimental design. In pre-experimental design, the researcher compares the data before and after some interventions or treatments. The true-experimental design has more than one purposefully created group, a commonly measured...
11.0K


