This work lays the foundation for NNPs where solvation is an integral part of the model, enabling the development of multiscale NNPs for simulating large biomolecular systems.
Abstract
Neural network potentials (NNPs) can provide insight into biological processes at atomic resolution. Training these NNPs requires large and diverse datasets of molecules, conformations, and configurations. However, so far little attention has been paid to the description of solvation, despite its importance for biomolecular systems. This work lays the foundation for NNPs where solvation is an integral part of the model. Following a quantum-mechanics/molecular-mechanics (QM/MM) formalism with an electrostatic embedding scheme, systems are decomposed into a QM zone with the solute(s), which is electrostatically coupled to the point charges from surrounding solvent molecules (MM zone). Using an accelerated sampling approach, we generate the biomolecular multiscale simulation (BMS25) dataset with over 50,000 topologies and more than 1.5 million unique conformations of peptides and miniproteins as well as small molecules and transition states from chemical reactions. The dataset includes energies, gradients, and multipoles of solute molecules as well as gradients on solvent molecules at the
ω
B97M-D4/ma-def2-TZVPP level of theory, enabling the development of multiscale NNPs for simulating large biomolecular systems.
A physics-based framework for the relationship between the electrostatic energy and the electrostatic field generated by the MM environment, MIREANN exhibits powerful transferability in reproducing the free energy barriers predicted by QM/MM-MD with errors less than 0.5 kcal mol–1 for various enzyme variants without the need to retrain the MLP.
Xinhu Sha, Xuehui Guo, Zi-Yu Chen et al.· Journal of Chemical Theory a...· 0 citations
This work releases OpenGEM26 (Open Generated Ensemble of Molecules, 2026), a large-scale dataset comprising 200,000 unique molecules and 4.4 million conformations composed of H, C, N, O, S and Cl with up to ten heavy atoms, providing a high-quality resource and robust ML potential for efficient simulations of sulfur- and chlorine-containing organic molecules.
It is demonstrated that BioEmu can generate plausible conformational ensembles for relatively large, six-and seven-pass membrane proteins, sampling rare states at a fraction of the computational cost of conventional MD simulations, suggesting that AI-based ensemble generation could provide an accessible approach for exploring membrane protein dynamics and complement conventional molecular modelling approaches.
B. Clifton, Adam G Grieve, Robin A. Corey· bioRxiv· 0 citations
It is argued that, since physics-based simulations and machine learning provide complementary approximations to the underlying probability distribution associated with biomolecular recognition events, and they excel respectively in consistency with free-energy landscapes and state populations and in predictive accuracy, the central challenge for the coming decade will be integrating them into hybrid frameworks that are scalable and transferable.
R. Khalil, Elena Frasnetti, Han Kurt et al.· Journal of Physical Chemistr...· 0 citations
Molecular dynamics (MD) simulations have become an increasingly important component of modern medicinal chemistry and structure-based drug discovery, providing atomistic insight into protein-ligand interactions that extends beyond static experimental structures and docking models. By explicitly accounting for conformational flexibility, solvent effects, and time-dependent behaviour, MD simulations enable the refinement of binding poses, the identification of transient and allosteric sites, and the quantitative estimation of binding thermodynamics and kinetics, the latter increasingly accessible through Markov state models (MSMs) and milestoning approaches that reconstruct long-timescale behaviour from ensembles of short trajectories. In this mini-review, we provide a practical overview of classical atomistic MD methodologies commonly used in medicinal chemistry, including force-field-based simulations, enhanced sampling techniques, and free-energy calculation methods such as alchemical and end-point approaches. Emphasis is placed on the strengths and limitations of each technique, with particular attention to their appropriate use across different stages of the drug discovery pipeline. We further discuss best practices for system preparation, simulation protocol design, convergence assessment, and reproducibility, highlighting common pitfalls that can lead to overinterpretation of simulation results. Selected examples illustrate how MD simulations have informed medicinal chemistry decisions in lead identification and optimisation. Finally, we briefly outline emerging directions, including the integration of machine learning, ensemble-based approaches, and next-generation force fields, which are expected to further expand the role of MD simulations in medicinal chemistry.
S. S. Çınaroğlu· Mini-Reviews in Medical Chem...· 0 citations
This Perspective surveys the central methodological challenges in developing ML/MM frameworks, including the generation of high-quality reference data and the treatment of multiscale coupling.
Xinhu Sha, Chenyu Wu, Daiqian Xie et al.· Journal of Physical Chemistr...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
