A Differentiable Neural-Network Force Field for Ionic Liquids

Machine learning-driven investigation of the structure and dynamics of the BMIM-BF4 room temperature ionic liquid

Room-temperature ionic liquids are an exciting group of materials with the potential to revolutionize energy storage. Due to their chemical structure and means of interaction, they are challenging to study computationally. Classical descriptions of their inter- and intra-molecular interactions require time intensive parametrization of force-fields which is prone to assumptions. While ab initio molecular dynamics approaches can capture all necessary interactions, they are too slow to achieve the time and length scales required. In this work, we take a step towards addressing these challenges by applying state-of-the-art machine-learned potentials to the simulation of 1-butyl-3-methylimidazolium tetrafluoroborate. We demonstrate a learning-on-the-fly procedure to train machine-learned potentials from single-point density functional theory calculations before performing production molecular dynamics simulations. Obtained structural and dynamical properties are in good agreement with computational and experimental references. Furthermore, our results show that hybrid machine-learned potentials can contribute to an improved prediction accuracy by mitigating the inherent shortsightedness of the models. Given that room-temperature ionic liquids necessitate long simulations to address their slow dynamics, achieving an optimal balance between accuracy and computational cost becomes imperative. To facilitate further investigation of these materials, we have made our IPSuite-based training and simulation workflow publicly accessible, enabling easy replication or adaptation to similar systems.

Transferability and Accuracy of Ionic Liquid Simulations with Equivariant Machine Learning Interatomic Potentials

Ionic liquids (ILs) are an exciting class of electrolytes finding applications in many areas from energy storage to solvents, where they have been touted as "designer solvents" as they can be mixed to precisely tailor the physiochemical properties. As using machine learning interatomic potentials (MLIPs) to simulate ILs is still relatively unexplored, several questions need to be answered to see if MLIPs can be transformative for ILs. Since ILs are often not pure, but are either mixed together or contain additives, we first demonstrate that a MLIP can be trained to be compositionally transferable; i.e., the MLIP can be applied to mixtures of ions not directly trained on, while only being trained on a few mixtures of the same ions. We also investigated the accuracy of MLIPs for a novel IL, which we experimentally synthesize and characterize. Our MLIP trained on ∼200 DFT frames is in reasonable agreement with our experiments and DFT.

Phonon Transport in Defect-Laden Bilayer Janus PtSTe Studied Using Neural-Network Force Fields

We explore the phonon transport properties of defect-laden bilayer PtSTe using equilibrium molecular dynamics simulations based on a neural-network force field. Defects prove very efficient at depressing the thermal conductivity of the structure, and flower defects have a particularly powerful effect, comparable to that of double vacancies. Furthermore, the conductivity of the structure with flower defects exhibits an unusual temperature dependence due to structural instability at high temperatures. We look into the distortion to normal modes around the defect by means of the projected phonon density of states and find diverse phenomena including localized modes and blue shifts.

Smart carbon-based sensors for the detection of non-coding RNAs associated with exposure to micro(nano)plastics: an artificial intelligence perspective

Micro(nano)plastics (MNPs) are pervasive environmental pollutants that individuals eventually consume. Despite this, little is known about MNP's impact on public health. In this article, we assess the evidence for potentially harmful consequences of MNPs in the human body, concentrating on molecular toxicity and exposure routes. Since MNPs are present in various consumer products, foodstuffs, and the air we breathe, exposure can occur through ingestion, inhalation, and skin contact. MNPs exposure can cause mitochondrial oxidative stress, inflammatory lesions, and epigenetic modifications, releasing specific non-coding RNAs in circulation, which can be detected to diagnose non-communicable diseases. This article examines the most fascinating smart carbon-based nanobiosensors for detecting circulating non-coding RNAs (lncRNAs and microRNAs). Carbon-based smart nanomaterials offer many advantages over traditional methods, such as ease of use, sensitivity, specificity, and efficiency, for capturing non-coding RNAs. In particular, the synthetic methods, conjugation chemistries, doping, and in silico approach for the characterization of synthesized carbon nanodots and their adaptability to identify and measure non-coding RNAs associated with MNPs exposure is discussed. Furthermore, the article provides insights into the use of artificial intelligence tools for designing smart carbon nanomaterials.

Efficient Molecular Dynamics Simulations of Deep Eutectic Solvents with First-Principles Accuracy Using Machine Learning Interatomic Potentials

In recent years, deep eutectic solvents emerged as highly tunable and ecofriendly alternatives to common organic solvents and liquid electrolytes. In the present work, the ability of machine learning (ML) interatomic potentials for molecular dynamics (MD) simulations of these liquids is explored, showcasing a trained neural network potential for a 1:2 ratio mixture of choline chloride and urea (reline). Using the ML potentials trained on density functional theory data, MD simulations for large systems of thousands of atoms and nanosecond-long time scales are feasible at a fraction of the computational cost of the target first-principles simulations. The obtained structural and dynamical properties of reline from MD simulations using our machine learning models are in good agreement with the first-principles MD simulations and experimental results. Running a single MD simulation is highlighted as a general shortcoming of typical first-principles studies if the dynamic properties are investigated. Furthermore, velocity cross-correlation functions are employed to study the collective dynamics of the molecular components in reline.

Electron Density Learning of Z-Bonds in Ionic Liquids and Its Application

Ionic liquids (ILs) exhibit fascinating properties due to special Z-bonds and have been widely used in electrochemical systems. The local Z-bond networks potentially cause a discrepancy in electrochemical properties. Understanding the correlations between the Z-bond energy (EZ-bond) and the electrochemical properties is helpful to identify appropriate ILs. It is difficult to estimate the correlations from single density functional theory calculations or molecular dynamic simulations. In this work, a machine learning model targeting the electronic density (ρBCP) of Z-bonds has been trained successfully, as expected for use in systems above the nanoscale size. The connection between the EZ-bond and the electrochemical potential window in ILs@TiO2, as well as that between the EZ-bond and the charge carrier mobility in ILs-PEDOT:Tos@SiO2, was separately investigated. This study highlights an efficient model for predicting ρBCP in nanoscale systems and anticipates exploring the connection between Z-bonds and the electrochemical properties of IL-based systems.

SPICE, A Dataset of Drug-like Molecules and Peptides for Training Machine Learning Potentials

Machine learning potentials are an important tool for molecular simulation, but their development is held back by a shortage of high quality datasets to train them on. We describe the SPICE dataset, a new quantum chemistry dataset for training potentials relevant to simulating drug-like small molecules interacting with proteins. It contains over 1.1 million conformations for a diverse set of small molecules, dimers, dipeptides, and solvated amino acids. It includes 15 elements, charged and uncharged molecules, and a wide range of covalent and non-covalent interactions. It provides both forces and energies calculated at the ωB97M-D3(BJ)/def2-TZVPPD level of theory, along with other useful quantities such as multipole moments and bond orders. We train a set of machine learning potentials on it and demonstrate that they can achieve chemical accuracy across a broad region of chemical space. It can serve as a valuable resource for the creation of transferable, ready to use potential functions for use in molecular simulations.

A Hybrid Machine Learning Approach for Structure Stability Prediction in Molecular Co-crystal Screenings

Co-crystals are a highly interesting material class as varying their components and stoichiometry in principle allows tuning supramolecular assemblies toward desired physical properties. The in silico prediction of co-crystal structures represents a daunting task, however, as they span a vast search space and usually feature large unit cells. This requires theoretical models that are accurate and fast to evaluate, a combination that can in principle be accomplished by modern machine-learned (ML) potentials trained on first-principles data. Crucially, these ML potentials need to account for the description of long-range interactions, which are essential for the stability and structure of molecular crystals. In this contribution, we present a strategy for developing Δ-ML potentials for co-crystals, which use a physical baseline model to describe long-range interactions. The applicability of this approach is demonstrated for co-crystals of variable composition consisting of an active pharmaceutical ingredient and various co-formers. We find that the Δ-ML approach offers a strong and consistent improvement over the density functional tight binding baseline. Importantly, this even holds true when extrapolating beyond the scope of the training set, for instance in molecular dynamics simulations under ambient conditions.

Neural-network-backed evolutionary search for SrTiO3(110) surface reconstructions

The determination of atomic structures in surface reconstructions has typically relied on structural models derived from intuition and domain knowledge. Evolutionary algorithms have emerged as powerful tools for such structure searches. However, when density functional theory is used to evaluate the energy the computational cost of a thorough exploration of the potential energy landscape is prohibitive. Here, we drive the exploration of the rich phase diagram of TiO_x overlayer structures on SrTiO₃(110) by combining the covariance matrix adaptation evolution strategy (CMA-ES) and a neural-network force field (NNFF) as a surrogate energy model. By training solely on SrTiO₃(110) 4×1 overlayer structures and performing CMA-ES runs on 3×1, 4×1 and 5×1 overlayers, we verify the transferability of the NNFF. The speedup due to the surrogate model allows taking advantage of the stochastic nature of the CMA-ES to perform exhaustive sets of explorations and identify both known and new low-energy reconstructions.

The covariance matrix adaptation evolution strategy (CMA-ES) and a fully automatically differentiable, transferable neural-network force field are combined to explore TiO_x overlayer structures on SrTiO₃(110) 3×1, 4×1 and 5×1 surfaces.