Flow-matching -- efficient coarse-graining of molecular dynamics without forces

Köhler, Jonas; Chen, Yaoyi; Krämer, Andreas; Clementi, Cecilia; Noé, Frank

doi:10.48550/arxiv.2203.11167

Cited by 8 publications

(10 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The simple graph-clustering CG model used in our method does not offer justification on what information is preserved, and may appear insufficient for more complex systems. CG modeling based on the essential dynamical information, and more sophisticated CG modeling techniques [17,[49][50][51][52][53][54][55] is another important future direction in designing more effective CG MD simulation schemes.…”

Section: Discussionmentioning

confidence: 99%

Simulate Time-integrated Coarse-grained Molecular Dynamics with Geometric Machine Learning

Fu¹,

Xie²,

Rebello³

et al. 2022

Preprint

View full text Add to dashboard Cite

Molecular dynamics (MD) simulation is the workhorse of various scientific domains but is limited by high computational cost. Learning-based force fields have made major progress in accelerating ab-initio MD simulation but are still not fast enough for many real-world applications that require long-time MD simulation. In this paper, we adopt a different machine learning approach where we coarse-grain a physical system using graph clustering, and model the system evolution with a very large time-integration step using graph neural networks. A novel score-based GNN refinement module resolves the long-standing challenge of long-time simulation instability. Despite only trained with short MD trajectory data, our learned simulator can generalize to unseen novel systems and simulate for much longer than the training trajectories. Properties requiring 10-100 ns level long-time dynamics can be accurately recovered at several-orders-of-magnitude higher speed than classical force fields. We demonstrate the effectiveness of our method on two realistic complex systems: (1) single-chain coarse-grained polymers in implicit solvent; (2) multi-component Li-ion polymer electrolyte systems.

show abstract

Section: Discussionmentioning

confidence: 99%

Simulate Time-integrated Coarse-grained Molecular Dynamics with Geometric Machine Learning

Fu¹,

Xie²,

Rebello³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Such gradient information could be included in FAB through force matching (Wang et al, 2019;Köhler et al, 2021;Köhler et al, 2022) or the addition of a KL divergence loss term. Wirnsberger et al (2022) train flows to accurately approximate the Boltzmann distribution of sameatom atomic solids with up to 512 atoms just using the target distribution's density.…”

Section: Discussion and Related Workmentioning

confidence: 99%

“…They cannot be easily converted into each other, and the L-form exists almost exclusively in nature. Hence, whenever alanine dipeptide is considered in the literature, it is almost always as the L-form (Wu et al, 2020;Campbell et al, 2021;Stimper et al, 2022;Dibak et al, 2021;Köhler et al, 2022). Therefore, we aim to train our model on only this form as well.…”

Section: Filtering Chiral Formsmentioning

confidence: 99%

Flow Annealed Importance Sampling Bootstrap

Midgley¹,

Stimper²,

Schölkopf³

et al. 2022

Preprint

View full text Add to dashboard Cite

Normalizing flows are tractable density models that can approximate complicated target distributions, e.g. Boltzmann distributions of physical systems. However, current methods for training flows either suffer from mode-seeking behavior, use samples from the target generated beforehand by expensive MCMC simulations, or use stochastic losses that have very high variance. To avoid these problems, we augment flows with annealed importance sampling (AIS) and minimize the mass covering α-divergence with α = 2, which minimizes importance weight variance. Our method, Flow AIS Bootstrap (FAB), uses AIS to generate samples in regions where the flow is a poor approximation of the target, facilitating the discovery of new modes. We target with AIS the minimum variance distribution for the estimation of the α-divergence via importance sampling. We also use a prioritized buffer to store and reuse AIS samples. These two features significantly improve FAB's performance. We apply FAB to complex multimodal targets and show that we can approximate them very accurately where previous methods fail. To the best of our knowledge, we are the first to learn the Boltzmann distribution of the alanine dipeptide molecule using only the unnormalized target density and without access to samples generated via Molecular Dynamics (MD) simulations: FAB produces better results than training via maximum likelihood on MD samples while using 100 times fewer target evaluations. After reweighting samples with importance weights, we obtain unbiased histograms of dihedral angles that are almost identical to the ground truth ones.

show abstract

“…59 Beyond force-matching, the effective f low by combining eq 2 and 4 can also be trained to recapitulate the CG probability density. 167 2-3.C. Based on Static Correlations.…”

Section: T H Imentioning

confidence: 99%

Bottom-up Coarse-Graining: Principles and Perspectives

Jin

Pak

Durumeric

et al. 2022

J. Chem. Theory Comput.

149

147

View full text Add to dashboard Cite

Large-scale computational molecular models provide scientists a means to investigate the effect of microscopic details on emergent mesoscopic behavior. Elucidating the relationship between variations on the molecular scale and macroscopic observable properties facilitates an understanding of the molecular interactions driving the properties of real world materials and complex systems (e.g., those found in biology, chemistry, and materials science). As a result, discovering an explicit, systematic connection between microscopic nature and emergent mesoscopic behavior is a fundamental goal for this type of investigation. The molecular forces critical to driving the behavior of complex heterogeneous systems are often unclear. More problematically, simulations of representative model systems are often prohibitively expensive from both spatial and temporal perspectives, impeding straightforward investigations over possible hypotheses characterizing molecular behavior. While the reduction in resolution of a study, such as moving from an atomistic simulation to that of the resolution of large coarse-grained (CG) groups of atoms, can partially ameliorate the cost of individual simulations, the relationship between the proposed microscopic details and this intermediate resolution is nontrivial and presents new obstacles to study. Small portions of these complex systems can be realistically simulated. Alone, these smaller simulations likely do not provide insight into collectively emergent behavior. However, by proposing that the driving forces in both smaller and larger systems (containing many related copies of the smaller system) have an explicit connection, systematic bottom-up CG techniques can be used to transfer CG hypotheses discovered using a smaller scale system to a larger system of primary interest. The proposed connection between different CG systems is prescribed by (i) the CG representation (mapping) and (ii) the functional form and parameters used to represent the CG energetics, which approximate potentials of mean force (PMFs). As a result, the design of CG methods that facilitate a variety of physically relevant representations, approximations, and force fields is critical to moving the frontier of systematic CG forward. Crucially, the proposed connection between the system used for parametrization and the system of interest is orthogonal to the optimization used to approximate the potential of mean force present in all systematic CG methods. The empirical efficacy of machine learning techniques on a variety of tasks provides strong motivation to consider these approaches for approximating the PMF and analyzing these approximations.

show abstract

Flow-matching -- efficient coarse-graining of molecular dynamics without forces

Cited by 8 publications

References 50 publications

Simulate Time-integrated Coarse-grained Molecular Dynamics with Geometric Machine Learning

Simulate Time-integrated Coarse-grained Molecular Dynamics with Geometric Machine Learning

Flow Annealed Importance Sampling Bootstrap

Bottom-up Coarse-Graining: Principles and Perspectives

Contact Info

Product

Resources

About