Coarse-Graining with Equivariant Neural Networks: A Path Toward Accurate and Data-Efficient Models

Loose, Timothy D.; Sahrmann, Patrick G.; Qu, Thomas S.; Voth, Gregory A.

doi:10.1021/acs.jpcb.3c05928

Cited by 5 publications

(3 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Remarkably, it is precisely the same technique that provides one possible solution: equivariant neural network potentials, as has recently been demonstrated. ,− It is not surprising in retrospect that these tools are suitable for this task. The goal of coarse-graining is to find the potential of mean force (PMF) for a reduced set of degrees of freedom.…”

Section: Recursive Coarse-grainingmentioning

confidence: 89%

See 1 more Smart Citation

The Potential of Neural Network Potentials

Duignan

2024

ACS Phys. Chem Au

View full text Add to dashboard Cite

In the next half-century, physical chemistry will likely undergo a profound transformation, driven predominantly by the combination of recent advances in quantum chemistry and machine learning (ML). Specifically, equivariant neural network potentials (NNPs) are a breakthrough new tool that are already enabling us to simulate systems at the molecular scale with unprecedented accuracy and speed, relying on nothing but fundamental physical laws. The continued development of this approach will realize Paul Dirac's 80-year-old vision of using quantum mechanics to unify physics with chemistry and providing invaluable tools for understanding materials science, biology, earth sciences, and beyond. The era of highly accurate and efficient firstprinciples molecular simulations will provide a wealth of training data that can be used to build automated computational methodologies, using tools such as diffusion models, for the design and optimization of systems at the molecular scale. Large language models (LLMs) will also evolve into increasingly indispensable tools for literature review, coding, idea generation, and scientific writing.

show abstract

Section: Recursive Coarse-grainingmentioning

confidence: 89%

“…Currently, coarse-graining with an NNP is applied to relatively small-scale classical systems, such as simplifying water to a single site or for proteins. ,,, However, they could potentially be iteratively applied to increasingly larger scales, perhaps one day encompassing complexes of multiple proteins, cell membranes, etc.…”

Section: Recursive Coarse-grainingmentioning

confidence: 99%

The Potential of Neural Network Potentials

Duignan

2024

ACS Phys. Chem Au

View full text Add to dashboard Cite

show abstract

“…These approaches look promising but, to the best of our knowledge, have not yet been tested extensively. Also, these approaches have general caveats, such as the demand for extensive training data, as described by Loose et al 61 …”

Section: Discussionmentioning

confidence: 99%

Structure-Based Protein Assembly Simulations Including Various Binding Sites and Conformations

Walter,

Quoika,

Zacharias

2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Many biological functions are mediated by large complexes formed by multiple proteins and other cellular macromolecules. Recent progress in experimental structure determination, as well as in integrative modeling and protein structure prediction using deep learning approaches, has resulted in a rapid increase in the number of solved multiprotein assemblies. However, the assembly process of large complexes from their components is much less well-studied. We introduce a rapid computational structure-based (SB) model, GoCa, that allows to follow the assembly process of large multiprotein complexes based on a known native structure. Beyond existing SB Go ̅ -type models, it distinguishes between intra-and intersubunit interactions, allowing us to include coupled folding and binding. It accounts automatically for the permutation of identical subunits in a complex and allows the definition of multiple minima (native) structures in the case of proteins that undergo global transitions during assembly. The model is successfully tested on several multiprotein complexes. The source code of the GoCa program including a tutorial is publicly available on Github: https://github.com/ZachariasLab/GoCa. We also provide a web source that allows users to quickly generate the necessary input files for a GoCa simulation: https://goca.t38webservices.nat.tum.de.

show abstract

Transferable Implicit Solvation via Contrastive Learning of Graph Neural Networks

Airas,

Ding,

Zhang

2023

ACS Cent. Sci.

View full text Add to dashboard Cite

Implicit solvent models are essential for molecular dynamics simulations of biomolecules, striking a balance between computational efficiency and biological realism. Efforts are underway to develop accurate and transferable implicit solvent models and coarse-grained (CG) force fields in general, guided by a bottom-up approach that matches the CG energy function with the potential of mean force (PMF) defined by the finer system. However, practical challenges arise due to the lack of analytical expressions for the PMF and algorithmic limitations in parameterizing CG force fields. To address these challenges, a machine learning-based approach is proposed, utilizing graph neural networks (GNNs) to represent the solvation free energy and potential contrasting for parameter optimization. We demonstrate the effectiveness of the approach by deriving a transferable GNN implicit solvent model using 600,000 atomistic configurations of six proteins obtained from explicit solvent simulations. The GNN model provides solvation free energy estimations much more accurately than state-of-the-art implicit solvent models, reproducing configurational distributions of explicit solvent simulations. We also demonstrate the reasonable transferability of the GNN model outside of the training data. Our study offers valuable insights for deriving systematically improvable implicit solvent models and CG force fields from a bottom-up perspective.

show abstract

Coarse-Graining with Equivariant Neural Networks: A Path Toward Accurate and Data-Efficient Models

Cited by 5 publications

References 54 publications

The Potential of Neural Network Potentials

The Potential of Neural Network Potentials

Structure-Based Protein Assembly Simulations Including Various Binding Sites and Conformations

Transferable Implicit Solvation via Contrastive Learning of Graph Neural Networks

Contact Info

Product

Resources

About