The onset of whole-cell modeling using the martini force field

Stevens, Jan A.; Grünewald, Fabian; Tilburg, Marco van; Thornburg, Zane R.; Gilbert, Benjamin R.; Brier, Troy A.; Luthey‐Schulten, Zaida; Marrink, Siewert J.

doi:10.1016/j.bpj.2022.11.2281

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Molecular mechanics methods are instrumental in studying atomistic systems comprising thousands to millions of atoms due to their rapid energy and force approximations. 5 Employing classical mechanics and featuring nearly linear complexity, these methods are particularly applicable to the study of complex biological macromolecules. 6 However, these methods have limitations, often relying on fixed atom types and predefined interaction rules.…”

Section: ■ Introductionmentioning

confidence: 99%

TrIP─Transformer Interatomic Potential Predicts Realistic Energy Surface Using Physical Bias

Hedelius,

Tingey,

Della Corte

2023

J. Chem. Theory Comput.

View full text Add to dashboard Cite

Accurate interatomic energies and forces enable high-quality molecular dynamics simulations, torsion scans, potential energy surface mappings, and geometry optimizations. Machine learning algorithms have enabled rapid estimates of the energies and forces with high accuracy. Further development of machine learning algorithms holds promise for producing universal potentials that support many different atomic species. We present the Transformer Interatomic Potential (TrIP): a chemically sound potential based on the SE(3)-Transformer. TrIP's species-agnostic architecture, which uses continuous atomic representation and homogeneous graph convolutions, encourages parameter sharing between atomic species for more general representations of chemical environments, maintains a reasonable number of parameters, serves as a form of regularization, and is a step toward accurate universal interatomic potentials. TrIP achieves state-of-the-art accuracies on the COMP6 benchmark with an energy prediction of just 1.02 kcal/mol MAE. We introduce physical bias in the form of Ziegler−Biersack−Littmark-screened nuclear repulsion and constrained atomization energies. An energy scan of a water molecule demonstrates that these changes improve longand near-range interactions compared to other neural network potentials. TrIP also demonstrates stability in molecular dynamics simulations, demonstrating reasonable exploration of Ramachandran space.

show abstract

Section: ■ Introductionmentioning

confidence: 99%