Temporally coherent backmapping of molecular trajectories from coarse-grained to atomistic resolution
arXiv:2205.05213 · doi:10.1021/acs.jpca.2c07716
Abstract
Coarse-graining offers a means to extend the achievable time and length scales of molecular dynamics simulations beyond what is practically possible in the atomistic regime. Sampling molecular configurations of interest can be done efficiently using coarse-grained simulations, from which meaningful physicochemical information can be inferred if the corresponding all-atom configurations are reconstructed. However, this procedure of backmapping to reintroduce the lost atomistic detail into coarse-grain structures has proven a challenging task due to the many feasible atomistic configurations that can be associated with one coarse-grain structure. Existing backmapping methods are strictly frame-based, relying on either heuristics to replace coarse-grain particles with atomic fragments and subsequent relaxation, or parameterized models to propose atomic coordinates separately and independently for each coarse-grain structure. These approaches neglect information from previous trajectory frames that is critical to ensuring temporal coherence of the backmapped trajectory, while also offering information potentially helpful to produce higher-fidelity atomic reconstructions. In this work we present a deep learning-enabled data-driven approach for temporally coherent backmapping that explicitly incorporates information from preceding trajectory structures. Our method trains a conditional variational autoencoder to non-deterministically reconstruct atomistic detail conditioned on both the target coarse-grain configuration and the previously reconstructed atomistic configuration. We demonstrate our backmapping approach on two exemplar biomolecular systems: alanine dipeptide and the miniprotein chignolin. We show that our backmapped trajectories accurately recover the structural, thermodynamic, and kinetic properties of the atomistic trajectory data.
References in corpus (21)
- Well-Tempered Metadynamics: A Smoothly Converging and Tunable Free-Energy Method
- E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
- Identification of slow molecular order parameters for Markov model construction
- Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
- Adaptive Resolution Molecular Dynamics Simulation: Changing the Degrees of Freedom on the Fly
- Time-lagged autoencoders: Deep learning of slow collective variables for molecular kinetics
- A Variational Approach to Enhanced Sampling and Free Energy Calculations
- Molecular enhanced sampling with autoencoders: On-the-fly collective variable discovery and accelerated free energy landscape exploration
- Coarse Graining Molecular Dynamics with Graph Neural Networks
- A Data Ecosystem to Support Machine Learning in Materials Science
- Coarse-Graining Auto-Encoders for Molecular Dynamics
- Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing
- iMapD: intrinsic Map Dynamics exploration for uncharted effective free energy landscapes
- Discovery of Self-Assembling -Conjugated Peptides by Active Learning-Directed Coarse-Grained Molecular Simulation
- From Variational to Deterministic Autoencoders
- Machine Learning Implicit Solvation for Molecular Dynamics
- Markov State Models from short non-Equilibrium Simulations - Analysis and Correction of Estimation Bias
- Relevance of Rotationally Equivariant Convolutions for Predicting Molecular Properties
- Temporally coherent backmapping of molecular trajectories from coarse-grained to atomistic resolution
- Generative Coarse-Graining of Molecular Conformations
- Reconstruction of Protein Structures from Single-Molecule Time Series