When Do Quantum Mechanical Descriptors Help Graph Neural Networks to Predict Chemical Properties?

Deep graph neural networks are extensively utilized to predict chemical reactivity and molecular properties. However, because of the complexity of chemical space, such models often have difficulty extrapolating beyond the chemistry contained in the training set. Augmenting the model with quantum mechanical (QM) descriptors is anticipated to improve its generalizability. However, obtaining QM descriptors often requires CPU-intensive computational chemistry calculations. To identify when QM descriptors help graph neural networks predict chemical properties, we conduct a systematic investigation of the impact of atom, bond, and molecular QM descriptors on the performance of directed message passing neural networks (D-MPNNs) for predicting 16 molecular properties. The analysis surveys computational and experimental targets, as well as classification and regression tasks, and varied data set sizes from several hundred to hundreds of thousands of data points. Our results indicate that QM descriptors are mostly beneficial for D-MPNN performance on small data sets, provided that the descriptors correlate well with the targets and can be readily computed with high accuracy. Otherwise, using QM descriptors can add cost without benefit or even introduce unwanted noise that can degrade model performance. Strategic integration of QM descriptors with D-MPNN unlocks potential for physics-informed, data-efficient modeling with some interpretability that can streamline de novo drug and material designs. To facilitate the use of QM descriptors in machine learning workflows for chemistry, we provide a set of guidelines regarding when and how to best leverage QM descriptors, a high-throughput workflow to compute them, and an enhancement to Chemprop, a widely adopted open-source D-MPNN implementation for chemical property prediction.

Tailoring parameters for QM/MM simulations: accurate modeling of adsorption and catalysis in zirconium-based metal-organic frameworks.

Quantum mechanics/molecular mechanics (QM/MM) simulations offer an efficient way to model reactions occurring in complex environments. This study introduces a specialized set of charge and Lennard-Jones parameters tailored for electrostatically embedded QM/MM calculations, aiming to accurately model both adsorption processes and catalytic reactions in zirconium-based metal-organic frameworks (Zr-MOFs). To validate our approach, we compare adsorption energies derived from QM/MM simulations against experimental results and Monte Carlo simulation outcomes. The developed parameters showcase the ability of QM/MM simulations to represent long-range electrostatic and van der Waals interactions faithfully. This capability is evidenced by the prediction of adsorption energies with a low root mean square error of 1.1 kcal mol-1 across a wide range of adsorbates. The practical applicability of our QM/MM model is further illustrated through the study of glucose isomerization and epimerization reactions catalyzed by two structurally distinct Zr-MOF catalysts, UiO-66 and MOF-808. Our QM/MM calculations closely align with experimental activation energies. Importantly, the parameter set introduced here is compatible with the widely used universal force field (UFF). Moreover, we thoroughly explore how the size of the cluster model and the choice of density functional theory (DFT) methodologies influence the simulation outcomes. This work provides an accurate and computationally efficient framework for modeling complex catalytic reactions within Zr-MOFs, contributing valuable insights into their mechanistic behaviors and facilitating further advancements in this dynamic area of research.

Fast Water Transport in UTSA-280 via a Knock-Off Mechanism.

Water and other small molecules frequently coordinate within metal-organic frameworks (MOFs). These coordinated molecules may actively engage in mass transfer, moving together with the transport molecules, but this phenomenon has yet to be examined. In this study, we explore a unique water transfer mechanism in UTSA-280, where an incoming water molecule can displace a coordinated molecule for mass transfer. We refer to this process as the "knock-off" mechanism. Despite UTSA-280 possessing one-dimensional channels, the knock-off transport enables water movement along the other two axes, effectively simulating a pseudo-three-dimensional mass transfer. Even with a relatively narrow pore width, the knock-off mechanism enables a high water flux in the UTSA-280 membrane. The knock-off mechanism also renders UTSA-280 superior water/ethanol diffusion selectivity for pervaporation. To validate this unique mechanism, we conducted 1 H and 2 H solid-state NMR on UTSA-280 after the adsorption of deuterated water. We also derived potential energy diagrams from the density functional theory to gain atomic-level insight into the knock-off and the direct-hopping mechanisms. The simulation findings reveal that the energy barrier of the knock-off mechanism is marginally lower than the direct-hopping pathway, implying its potential role in enhancing water diffusion in UTSA-280.

Deep Learning-Based Increment Theory for Formation Enthalpy Predictions.

Machine learning predictions of molecular thermochemistry, such as formation enthalpy, have been limited for large and complicated species because of the lack of available training data. Such predictions would be important in the prediction of reaction thermodynamics and the construction of kinetic models. Herein, we introduce a graph-based deep learning approach that can separately learn the enthalpy contribution of each atom in its local environment with the effect of the overall molecular structure taken into account. Because this approach follows the additivity scheme of increment theory, it can be generalized to larger and more complicated species not present in the training data. By training the model on molecules with up to 11 heavy atoms, it can predict the formation enthalpy of testing molecules with up to 42 heavy atoms with a mean absolute error of 2 kcal/mol, which is less than half of the error of the conventional increment theory. We expect that this approach will also enable rapid prediction of other extensive properties of large molecules that are difficult to derive from experiments or ab initio calculation.

Permeable reactive barrier of waste sludge from wine processing utilized to block a metallic mixture plume in a simulated aquifer.

Heavy metal contamination in underground water commonly occurs in industrial areas in Taiwan. Wine-processing waste sludge (WPWS) can adsorb and remove several toxic metals from aqueous solutions. In this study, WPWS particles were used to construct a permeable reactive barrier (PRB) for the remediation of a contaminant plume comprising HCrO4-, Cu2+, Zn2+, Ni2+, Cd2+, and AsO33- in a simulated aquifer. This PRB effectively prevented the dispersals of Cu2+, Zn2+, and HCrO4-, and their concentrations in the pore water behind the barrier declined below the control standard levels. However, the PRB failed to prevent the diffusion of Ni2+, Cd2+, and AsO33-, and their concentrations were occasionally higher than the control standard levels. However, 18% to 45% of As, 84% to 93% of Cd, and 16% to 77% of Ni were removed by the barrier. Ni ions showed less adsorption on the fine sand layer because of the layer's ineffectiveness in multiple competitive adsorptions. Therefore, the ions infiltrated the barrier at a high concentration, which increased the loading for the barrier blocking. The blocking efficiency was related to the degree of adsorption of heavy metals in the sand layer and the results of their competitive adsorption.

Diels-Alder Conversion of Acrylic Acid and 2,5-Dimethylfuran to para-Xylene Over Heterogeneous Bi-BTC Metal-Organic Framework Catalysts Under Mild Conditions.

The heterogeneous metal-organic framework Bi-BTC successfully catalyzed the synthesis of para-xylene from bio-based 2,5-dimethylfuran and acrylic acid in a promising yield (92 %), under relatively mild conditions (160 °C, 10 bar), and with a low reaction-energy barrier (47.3 kJ mol-1 ). The proposed reaction strategy also demonstrates a remarkable versatility for furan derivatives such as furan and 2-methylfuran.

Evaluating Scalable Uncertainty Estimation Methods for Deep Learning-Based Molecular Property Prediction.

Advances in deep neural network (DNN)-based molecular property prediction have recently led to the development of models of remarkable accuracy and generalization ability, with graph convolutional neural networks (GCNNs) reporting state-of-the-art performance for this task. However, some challenges remain, and one of the most important that needs to be fully addressed concerns uncertainty quantification. DNN performance is affected by the volume and the quality of the training samples. Therefore, establishing when and to what extent a prediction can be considered reliable is just as important as outputting accurate predictions, especially when out-of-domain molecules are targeted. Recently, several methods to account for uncertainty in DNNs have been proposed, most of which are based on approximate Bayesian inference. Among these, only a few scale to the large data sets required in applications. Evaluating and comparing these methods has recently attracted great interest, but results are generally fragmented and absent for molecular property prediction. In this paper, we quantitatively compare scalable techniques for uncertainty estimation in GCNNs. We introduce a set of quantitative criteria to capture different uncertainty aspects and then use these criteria to compare MC-dropout, Deep Ensembles, and bootstrapping, both theoretically in a unified framework that separates aleatoric/epistemic uncertainty and experimentally on public data sets. Our experiments quantify the performance of the different uncertainty estimation methods and their impact on uncertainty-related error reduction. Our findings indicate that Deep Ensembles and bootstrapping consistently outperform MC-dropout, with different context-specific pros and cons. Our analysis leads to a better understanding of the role of aleatoric/epistemic uncertainty, also in relation to the target data set features, and highlights the challenge posed by out-of-domain uncertainty.

Accurate Thermochemistry with Small Data Sets: A Bond Additivity Correction and Transfer Learning Approach.

Machine learning provides promising new methods for accurate yet rapid prediction of molecular properties, including thermochemistry, which is an integral component of many computer simulations, particularly automated reaction mechanism generation. Often, very large data sets with tens of thousands of molecules are required for training the models, but most data sets of experimental or high-accuracy quantum mechanical quality are much smaller. To overcome these limitations, we calculate new high-level data sets and derive bond additivity corrections to significantly improve enthalpies of formation. We adopt a transfer learning technique to train neural network models that achieve good performance even with a relatively small set of high-accuracy data. The training data for the entropy model are carefully selected so that important conformational effects are captured. The resulting models are generally applicable thermochemistry predictors for organic compounds with oxygen and nitrogen heteroatoms that approach experimental and coupled cluster accuracy while only requiring molecular graph inputs. Due to their versatility and the ease of adding new training data, they are poised to replace conventional estimation methods for thermochemical parameters in reaction mechanism generation. Since high-accuracy data are often sparse, similar transfer learning approaches are expected to be useful for estimating many other molecular properties.

Self-Evolving Machine: A Continuously Improving Model for Molecular Thermochemistry.

Because collecting precise and accurate chemistry data is often challenging, chemistry data sets usually only span a small region of chemical space, which limits the performance and the scope of applicability of data-driven models. To address this issue, we integrated an active learning machine with automatic ab initio calculations to form a self-evolving model that can continuously adapt to new species appointed by the users. In the present work, we demonstrate the self-evolving concept by modeling the formation enthalpies of stable closed-shell polycyclic species calculated at the B3LYP/6-31G(2df,p) level of theory. By combining a molecular graph convolutional neural network with a dropout training strategy, the model we developed can predict density functional theory (DFT) enthalpies for a broad range of polycyclic species and assess the quality of each predicted value. For the species which the current model is uncertain about, the automatic ab initio calculations provide additional training data to improve the performance of the model. For a test set composed of 2858 cyclic and polycyclic hydrocarbons and oxygenates, the enthalpies predicted by the model agree with the reference DFT values with a root-mean-square error of 2.62 kcal/mol. We found that a model originally trained on hydrocarbons and oxygenates can broaden its prediction coverage to nitrogen-containing species via an active learning process, suggesting that the continuous learning strategy is not only able to improve the model accuracy but is also capable of expanding the predictive capacity of a model to unseen species domains.

Unimolecular Reaction Pathways of a γ-Ketohydroperoxide from Combined Application of Automated Reaction Discovery Methods.

Ketohydroperoxides are important in liquid-phase autoxidation and in gas-phase partial oxidation and pre-ignition chemistry, but because of their low concentration, instability, and various analytical chemistry limitations, it has been challenging to experimentally determine their reactivity, and only a few pathways are known. In the present work, 75 elementary-step unimolecular reactions of the simplest γ-ketohydroperoxide, 3-hydroperoxypropanal, were discovered by a combination of density functional theory with several automated transition-state search algorithms: the Berny algorithm coupled with the freezing string method, single- and double-ended growing string methods, the heuristic KinBot algorithm, and the single-component artificial force induced reaction method (SC-AFIR). The present joint approach significantly outperforms previous manual and automated transition-state searches - 68 of the reactions of γ-ketohydroperoxide discovered here were previously unknown and completely unexpected. All of the methods found the lowest-energy transition state, which corresponds to the first step of the Korcek mechanism, but each algorithm except for SC-AFIR detected several reactions not found by any of the other methods. We show that the low-barrier chemical reactions involve promising new chemistry that may be relevant in atmospheric and combustion systems. Our study highlights the complexity of chemical space exploration and the advantage of combined application of several approaches. Overall, the present work demonstrates both the power and the weaknesses of existing fully automated approaches for reaction discovery which suggest possible directions for further method development and assessment in order to enable reliable discovery of all important reactions of any specified reactant(s).