Quantum-accurate enhanced sampling and mini-protein folding through replica exchange for multiscale neural network potentials
- 1Department of Chemistry and Applied Biosciences, ETH Zürich Vladimir-Prelog-Weg 2 8093 Zürich Switzerland
Abstract
Neural network potentials (NNPs) have emerged as efficient alternatives to computationally demanding quantum-mechanical (QM) methods. AMPv3-EE-BMS25 (short AMP-BMS) is an equivariant NNP designed for multiscale ML/MM simulations that captures directional and long-range interactions. In classical molecular dynamics (MD) simulations, enhanced-sampling techniques are applied to cross large energy barriers and improve convergence. Among those, replica exchange with solute tempering (REST2) is an efficient method that selectively scales solute interactions while keeping the bath temperature fixed, thereby reducing the number of replicas required. Here, we present a REST2-like algorithm compatible with multiscale ML/MM simulations. This algorithm is combined with AMP-BMS by exploiting the separability of its Hamiltonian into solute–solute, solute–solvent, and solvent–solvent contributions. We validate the REST2–AMP approach on several peptidic systems in explicit solvent and demonstrate folding of the mini-proteins chignolin and CLN025 from extended conformations. Thus, our REST2 approach for ML/MM enables access to biologically relevant timescales while maintaining near-DFT accuracy.
Related
- Enhanced diffusion sampling: Efficient rare event sampling and free energy calculation with diffusion models
- Enhanced Sampling of Ligand Binding Coupled to RNA Base-flipping Dynamics
- Machine learning–enhanced label-free Raman spectroscopy for accurate serum-based detection of early-stage breast cancer via tumor-associated antigens
- SPectroscopy Informed Configurational Enhanced Sampling (SPICES)
- Shedding light on Gaussia Luciferase conformational space using multi-conformation enhanced sampling simulation
BibTeX
@article{solazzo2026quantumaccurate,
title = {{Quantum-accurate enhanced sampling and mini-protein folding through replica exchange for multiscale neural network potentials}},
author = {Riccardo Solazzo and Igor Gordiy and Sereina Riniker},
journal = {Chemical Science},
year = {2026},
month = nov,
doi = {10.1039/d6sc04555c},
url = {https://doi.org/10.1039/d6sc04555c},
note = {CC BY 3.0},
}
RIS
TY - JOUR
TI - Quantum-accurate enhanced sampling and mini-protein folding through replica exchange for multiscale neural network potentials
AU - Riccardo Solazzo
AU - Igor Gordiy
AU - Sereina Riniker
PY - 2026
DA - 2026/11/09
JO - Chemical Science
DO - 10.1039/d6sc04555c
UR - https://doi.org/10.1039/d6sc04555c
AB - Neural network potentials (NNPs) have emerged as efficient alternatives to computationally demanding quantum-mechanical (QM) methods. AMPv3-EE-BMS25 (short AMP-BMS) is an equivariant NNP designed for multiscale ML/MM simulations that captures directional and long-range interactions. In classical molecular dynamics (MD) simulations, enhanced-sampling techniques are applied to cross large energy barriers and improve convergence. Among those, replica exchange with solute tempering (REST2) is an efficient method that selectively scales solute interactions while keeping the bath temperature fixed, thereby reducing the number of replicas required. Here, we present a REST2-like algorithm compatible with multiscale ML/MM simulations. This algorithm is combined with AMP-BMS by exploiting the separability of its Hamiltonian into solute–solute, solute–solvent, and solvent–solvent contributions. We validate the REST2–AMP approach on several peptidic systems in explicit solvent and demonstrate folding of the mini-proteins chignolin and CLN025 from extended conformations. Thus, our REST2 approach for ML/MM enables access to biologically relevant timescales while maintaining near-DFT accuracy.
SN - 2041-6520
SN - 2041-6539
ER -