返回
Fitting Atomic Structures into Cryo-EM Maps by Coupling Deep Learning-Enhanced Map Processing with Global-Local Optimization
DOI:10.1021/acs.jcim.5c00004.png)
摘要
En 中文
随着蛋白质结构预测技术的突破,通过结构拟合从冷冻电子显微镜(cryo-EM)密度图中构建原子结构变得越来越关键。然而,所构建模型的准确性严重依赖于结构-图拟合的精度。在本研究中,我们介绍了DEMO-EMfit,一种渐进式方法,它整合了基于深度学习的骨架图提取与全局-局部结构姿态搜索,以将原子结构拟合到密度图中。DEMO-EMfit已在包含蛋白质和核酸复合物的冷冻电子断层扫描(cryo-ET)和cryo-EM图的基准数据集上进行了广泛评估。结果表明,DEMO-EMfit优于当前最先进的方法,为将原子结构拟合到密度图中提供了一种高效且准确的工具。
Keyword:
PROTEIN STRUCTURES
DENSITY MAPS
REFINEMENT
期刊
IF:
5.3
论文数:
9.1K
被引数:
4.0W
机构
暂无机构信息
引用论文
I-TASSER-MTD: a deep-learning-based platform for multi-domain protein structure and function predictionI-tasser-mtd: 基于深度学习的多域蛋白质结构和功能预测平台
NATURE PROTOCOLS
IF16
De novo atomic protein structure modeling for cryoEM density maps using 3D transformer and HMM
NATURE COMMUNICATIONS
IF15.7
Non-uniform refinement: adaptive regularization improves single-particle cryo-EM reconstruction非均匀细化: 自适应正则化改进单粒子cryo-em重建
NATURE METHODS
IF32.1
De novo protein structure determination from near-atomic-resolution cryo-EM maps
NATURE METHODS
IF32.1
MultiFit: a web server for fitting multiple protein structures into their electron microscopy density map
NUCLEIC ACIDS RESEARCH
IF13.1

