High-accuracy protein structures by combining machine-learning with physics-based refinement
High-accuracy protein structures by combining machine-learning with physics-based refinement
复制标题
DOI：
10.1002/prot.25847
复制
发表时间：
2019-11-15
影响因子：
2.9
通讯作者：
Feig, Michael
中科院分区：
文献类型：
--
作者：
Heo, Lim;Feig, Michael
蛋白质结构预测长期以来一直是实验结构测定的替代方法，特别是通过基于相关序列模板的同源性建模。最近，通过机器学习的协同进化分析的距离约束的基础上的模型，有显着扩大的能力，预测结构的序列没有模板。一种这样的方法，AlphaFold，在模板可用但不直接使用这些信息的序列上也表现良好。在这里，我们展示了将AlphaFold中基于机器学习的模型与最先进的基于物理学的改进相结合，通过分子动力学模拟进一步改进了预测，使其优于在最新一轮CASP中测试的任何其他预测方法。由此产生的模型具有高度准确的全球和本地的结构，包括高精度在功能上重要的接口残留物，它们是非常适合作为初始模型通过分子置换晶体结构测定。
Protein structure prediction has long been available as an alternative to experimental structure determination, especially via homology modeling based on templates from related sequences. Recently, models based on distance restraints from coevolutionary analysis via machine learning to have significantly expanded the ability to predict structures for sequences without templates. One such method, AlphaFold, also performs well on sequences where templates are available but without using such information directly. Here we show that combining machine-learning based models from AlphaFold with state-of-the-art physics-based refinement via molecular dynamics simulations further improves predictions to outperform any other prediction method tested during the latest round of CASP. The resulting models have highly accurate global and local structures, including high accuracy at functionally important interface residues, and they are highly suitable as initial models for crystal structure determination via molecular replacement.