Incorporating a neural network into the AMOEBA polarizable force field for ligand field effects of Cu2+ ions

Machine Learning-Driven Refinement of Reactive Force Fields via Hierarchical “Center-Environment” Features for Energetic Molecular Crystals

This work not only establishes a pioneering paradigm for interpretable ML-driven force field refinement but also provides the first feature engineering solution incorporating chemical, physical, and structural information specifically designed for the machine learning of energetic molecular crystals.

HessFit: Deriving Molecule-Specific Force Fields from Quantum Mechanical Hessians.

Aromatic Molecule Solvation in Liquid Water with Coupled Cluster Accuracy: The Balance of Pi-Interactions and Hydrophobicity

Aromatic organic solutes in water exhibit a delicate balance between hydrophobic solvation and directional O-H$\cdots \pi$ hydrogen bonds, yet widely used force fields and state-of-the-art density functional approaches struggle to provide a consistent picture of these pivotal interactions. We introduce a data-efficient upfitting strategy to train a machine learning interatomic potential (MLIP) based on the graph atomic cluster expansion for aqueous aromatic molecules with CCSD(T) accuracy for condensed phase simulations, using only finite molecular clusters. We apply our method to aqueous toluene (C$_6$H$_5$CH$_3$). The resulting CCSD(T)-quality MLIP reproduces coupled cluster energies and forces in bulk and reveals that commonly employed methods do not capture the crucial balance between hydrophilic and hydrophobic solvation, distorting the interactions of aromatic molecules with their environment. Representative biomolecular force fields substantially understructure the hydrophobic solvation shell and misorient interfacial water, while overestimating $\pi$-contacts, yielding an inconsistent solvation balance. Even hybrid DFT and MP2 overestimate barriers to breaking of water-$\pi$ hydrogen bonds. Our workflow provides a practical, general route to CCSD(T)-quality condensed-phase simulations of aqueous solutions, and thus constructed interaction potentials now open the door to consistent, highly accurate benchmark studies of $\pi$-contacts and hydrophobic effects in biomolecular contexts such as solvation of proteins and DNA in aqueous environments.

Transferable Collective Variable to accelerate Protein-Ligand (Un)Binding Transitions via Explainable Machine Learning and Intriguing Role of Ligand Solvation

This study presents a method to derive optimized CV from transition state region (TS) via an interpretable machine learning (ML) model, Elastic Net, which greatly accelerate ligand binding-unbinding transitions and achieves rapid free energy surface (FES) convergence across diverse systems.

Machine-learning molecular dynamics and DFT analysis of CoFe2O4 spinel stability and hydrogen recombination energetics for high-temperature thermochemical hydrogen production

ABSTRACT This study examines the structural stability of CoFe2O4 and the energetics of Langmuir–Hinshelwood recombinative desorption of two pre-adsorbed hydrogen atoms on the CoFe2O4 (111) surface, relevant to high-temperature thermochemical hydrogen production. A pretrained universal M3GNet graph neural-network potential is used for machine-learning molecular dynamics (MLMD), combined with surface DFT calculations at the PBE level. Two-phase MLMD simulations identify an equilibrium melting temperature of approximately 1350 K, while single-phase heating of a defect-free crystal yields an apparent transition at 1700K, interpreted as a superheating-limited upper bound. Within this solid-phase temperature window, DFT calculations show that atomic H is strongly chemisorbed on Co (Eads = −2.04 eV) and O (Eads = −4.29 eV) sites, with O-H bond lengths consistent with experiment, while molecular H₂ is only weakly physisorbed (Eads = 0.001 eV). The recombinative desorption of two co-adsorbed H atoms on adjacent Co/O sites proceeds with an activation barrier of 0.46 eV and an estimated rate of 1.6 × 1010 s−1 at 1300 K, confirming that H-H recombination is fast and is not the rate-limiting step under hydrogen-rich conditions. All DFT values are reported without an explicit Hubbard U correction and represent best feasible estimates within the present computational constraints.

Evaluating Electrostatic Embedding MLIP/MM for Relative Binding Free Energy Calculations

Electrostatic embedding improved every accuracy and correlation metric for TYK2 but performed comparably to the classical and mechanical-embedding baselines for CDK2, thrombin, p38 and JNK1, and standard single-molecule energy and charge benchmarks were not good predictors of this target-dependent outcome.