paper-with-me

홈 › Papers

Learning protein conformational space by enforcing physics with convolutions and latent interpolations

2019-10-10 · Venkata K. Ramaswamy, Chris G. Willcocks, Matteo T. Degiacomi

Determining the different conformational states of a protein and the transition paths between them is key to fully understanding the relationship between biomolecular structure and function. This can be accomplished by sampling protein conformational space with molecular simulation methodologies. Despite advances in computing hardware and sampling techniques, simulations always yield a discretized representation of this space, with transition states undersampled proportionally to their associated energy barrier. We present a convolutional neural network that learns a continuous conformational space representation from example structures, and loss functions that ensure intermediates between examples are physically plausible. We show that this network, trained with simulations of distinct protein states, can correctly predict a biologically relevant non-linear transition path, without any example on the path provided. We also show we can transfer features learnt from one protein to others, which results in superior performances, and requires a surprisingly small number of training examples.

📄 PDF Abstract BibTeX arXiv:1910.04543

Code (0)

등록된 구현이 없습니다.

Tasks

Transfer Learning

Similar Papers 제목 키워드 기반

PETIMOT: A Novel Framework for Inferring Protein Motions from Sparse Data Using SE(3)-Equivariant Graph Neural Networks

2025-03-19 · Valentin Lombard, Sergei Grudinin, Elodie Laine

Proteins move and deform to ensure their biological functions. Despite significant progress in protein structure prediction, approximating conformational ensembles at physiological conditions remains a fundamental open p…

Graph Neural NetworkProtein Structure PredictionTransfer Learning

MoDyGAN: Combining Molecular Dynamics With GANs to Investigate Protein Conformational Space

2025-07-18 · Jingbo Liang, Bruna Jacobson arxiv

Extensively exploring protein conformational landscapes remains a major challenge in computational biology due to the high computational cost involved in dynamic physics-based simulations. In this work, we propose a nove…

Ensemble Learning

CryoACE: An Atom-centric Framework for Accurate and Automated Model Building in Cryo-EM

2026-06-30 · Minzhang Li, Mingrui Li, Weichen Qin, Qihe Chen 외 arxiv

Protein automodeling from cryo-EM density maps faces unique challenges in enforcing physicochemical validity and managing conformational heterogeneity. Current solvers are often limited to static predictions or require c…

LAST: Latent Space Assisted Adaptive Sampling for Protein Trajectories

2022-04-27 · Hao Tian, Xi Jiang, Sian Xiao, Hunter La Force 외

Molecular dynamics (MD) simulation is widely used to study protein conformations and dynamics. However, conventional simulation suffers from being trapped in some local energy minima that are hard to escape. Thus, most c…

Looking for central tendencies in the conformational freedom of proteins using NMR measurements

2016-02-18

We study the conformational freedom of a protein made by two rigid domains connected by a flexible linker. The conformational freedom is represented as an unknown probability distribution on the space of allowed states. …