从简单到复杂：使用 cg2all 从粗粒模型重建全原子结构。
From simple to complex: Reconstructing all-atom structures from coarse-grained models using cg2all.
机构信息
School of Physics, Georgia Institute of Technology, Atlanta, GA 30332, USA.
School of Chemistry and Biochemistry, Georgia Institute of Technology, Atlanta, GA 30332, USA.
出版信息
Structure. 2024 Jan 4;32(1):5-7. doi: 10.1016/j.str.2023.12.004.
Abstract
In this issue of Structure, Heo and Feig present cg2all, a novel deep-learning model capable of efficiently predicting all-atom protein structures from coarse-grained (CG) representations. The model maintains high accuracy, even when the CG model is simplified to a single bead per residue, and has a number of promising applications.
摘要
在本期的《结构》杂志中，Heo 和 Feig 提出了 cg2all，这是一种新型的深度学习模型，能够从粗粒化（CG）表示中有效地预测全原子蛋白质结构。该模型即使将 CG 模型简化为每个残基一个珠子，也能保持很高的准确性，并且具有许多有前途的应用。
相似文献
1
From simple to complex: Reconstructing all-atom structures from coarse-grained models using cg2all.从简单到复杂：使用 cg2all 从粗粒模型重建全原子结构。
Structure. 2024 Jan 4;32(1):5-7. doi: 10.1016/j.str.2023.12.004.
2
One bead per residue can describe all-atom protein structures.一个珠位代表一个残基，可以描述全原子蛋白质结构。
Structure. 2024 Jan 4;32(1):97-111.e6. doi: 10.1016/j.str.2023.10.013. Epub 2023 Nov 23.
3
ABC2A: A Straightforward and Fast Method for the Accurate Backmapping of RNA Coarse-Grained Models to All-Atom Structures.ABC2A：一种将 RNA 粗粒模型准确映射回全原子结构的简单快速方法。
Molecules. 2024 Mar 11;29(6):1244. doi: 10.3390/molecules29061244.
4
Bridging between NMA and Elastic Network Models: Preserving All-Atom Accuracy in Coarse-Grained Models.NMA与弹性网络模型之间的桥梁：在粗粒度模型中保持全原子精度。
PLoS Comput Biol. 2015 Oct 16;11(10):e1004542. doi: 10.1371/journal.pcbi.1004542. eCollection 2015 Oct.
5
Benchmarking coarse-grained models of organic semiconductors via deep backmapping.通过深度反向映射对有机半导体的粗粒度模型进行基准测试。
Front Chem. 2022 Sep 9;10:982757. doi: 10.3389/fchem.2022.982757. eCollection 2022.
6
Two-bead polarizable water models combined with a two-bead multipole force field (TMFF) for coarse-grained simulation of proteins.用于蛋白质粗粒度模拟的双珠极化水模型与双珠多极力场（TMFF）相结合。
Phys Chem Chem Phys. 2017 Mar 8;19(10):7410-7419. doi: 10.1039/c6cp07958j.
7
Systematic methods for defining coarse-grained maps in large biomolecules.用于定义大型生物分子中粗粒度图谱的系统方法。
Adv Exp Med Biol. 2015;827:33-48. doi: 10.1007/978-94-017-9245-5_4.
8
Accurate Estimation of Solvent Accessible Surface Area for Coarse-Grained Biomolecular Structures with Deep Learning.深度学习在粗粒生物分子结构溶剂可及表面积的精确估计中的应用。
J Phys Chem B. 2021 Aug 26;125(33):9490-9498. doi: 10.1021/acs.jpcb.1c05203. Epub 2021 Aug 12.
9
Dynamic force matching: A method for constructing dynamical coarse-grained models with realistic time dependence.动态力匹配：一种构建具有真实时间依赖性的动态粗粒化模型的方法。
J Chem Phys. 2015 Apr 21;142(15):154104. doi: 10.1063/1.4917454.
10
Identifying Coarse-Grained Representations for Electronic Predictions.识别用于电子预测的粗粒度表示。
J Chem Theory Comput. 2023 Aug 8;19(15):4982-4990. doi: 10.1021/acs.jctc.3c00466. Epub 2023 Jul 5.
引用本文的文献
1
Deep Learning of Proteins with Local and Global Regions of Disorder.具有局部和全局无序区域的蛋白质的深度学习
ArXiv. 2025 Mar 29:arXiv:2502.11326v2.
2
SeqDance: A Protein Language Model for Representing Protein Dynamic Properties.SeqDance：一种用于表示蛋白质动态特性的蛋白质语言模型。
bioRxiv. 2024 Oct 15:2024.10.11.617911. doi: 10.1101/2024.10.11.617911.
本文引用的文献
1
One bead per residue can describe all-atom protein structures.一个珠位代表一个残基，可以描述全原子蛋白质结构。
Structure. 2024 Jan 4;32(1):97-111.e6. doi: 10.1016/j.str.2023.10.013. Epub 2023 Nov 23.
2
Highly accurate protein structure prediction with AlphaFold.利用 AlphaFold 进行高精度蛋白质结构预测。
Nature. 2021 Aug;596(7873):583-589. doi: 10.1038/s41586-021-03819-2. Epub 2021 Jul 15.
3
Martini 3: a general purpose force field for coarse-grained molecular dynamics.马蒂尼 3 模型：一种通用的粗粒化分子动力学力场。
Nat Methods. 2021 Apr;18(4):382-388. doi: 10.1038/s41592-021-01098-3. Epub 2021 Mar 29.
4
The Rosetta All-Atom Energy Function for Macromolecular Modeling and Design.用于大分子建模与设计的罗塞塔全原子能量函数。
J Chem Theory Comput. 2017 Jun 13;13(6):3031-3048. doi: 10.1021/acs.jctc.7b00125. Epub 2017 May 12.
5
Applications of the molecular dynamics flexible fitting method.分子动力学柔性拟合方法的应用。
J Struct Biol. 2011 Mar;173(3):420-7. doi: 10.1016/j.jsb.2010.09.024. Epub 2010 Oct 12.
6
PRIMO/PRIMONA: a coarse-grained model for proteins and nucleic acids that preserves near-atomistic accuracy.PRIMO/PRIMONA：一种用于蛋白质和核酸的粗粒度模型，可保持近乎原子级精度。
Proteins. 2010 Apr;78(5):1266-81. doi: 10.1002/prot.22645.
7
Improved prediction of protein side-chain conformations with SCWRL4.使用 SCWRL4 提高蛋白质侧链构象预测。
Proteins. 2009 Dec;77(4):778-95. doi: 10.1002/prot.22488.
Zotero 插件