.png){kind=icon}
返回
Constraint Decoupled Latent Diffusion for Protein Backmapping
.png){kind=icon}
PRE
AI
DOI：10.1021/acs.jctc.5c01364.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Coarse-grained (CG) molecular dynamics simulations enable efficient exploration of protein conformational ensembles. However, reconstructing atomic details from CG structures (backmapping) remains a challenging problem. Current approaches face an inherent trade-off between maintaining atomistic accuracy and exploring diverse conformations, often necessitating complex constraint handling or extensive refinement steps. To address these challenges, we introduce a novel two-stage framework, named CODLAD (COnstraint Decoupled LAtent Diffusion). This framework first compresses atomic structures into discrete latent representations, explicitly embedding structural constraints, thereby decoupling constraint handling from generation. Subsequently, it performs efficient denoising diffusion in this latent space to produce structurally valid and diverse all-atom conformations. Comprehensive evaluations on diverse protein data sets demonstrate that CODLAD achieves state-of-the-art performance in atomistic accuracy, conformational diversity, and computational efficiency while exhibiting strong generalization across different protein systems.
期刊
IF:
5.5
论文数:
1.1W
被引数:
5.4W
机构
引用论文
Fast and accurate protein structure search with Foldseek使用Foldseek快速准确的蛋白质结构搜索.png)
NATURE BIOTECHNOLOGY
OAAI
NATURE BIOTECHNOLOGYIF41.7
OAAI分享收藏
分享收藏PED in 2021: a major update of the protein ensemble database for intrinsically disordered proteinsNUCLEIC ACIDS RESEARCHOAAI
NUCLEIC ACIDS RESEARCHIF13.1
OAAI分享收藏
查看更多内容