Machine learning from quantum chemistry to predict experimental solvent effects on reaction rates† † Electronic supplementary information (ESI) available. See DOI: https://doi.org/10.1039/d3sc05353a
Ontology highlight
ABSTRACT:
SUBMITTER: Chung Y
PROVIDER: S-EPMC10866337 | biostudies-literature | 2024 Jan
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Many molecular design tasks benefit from fast and accurate calculations of quantum-mechanical (QM) properties. However, the computational cost of QM methods applied to drug-like molecules currently renders large-scale applications of quantum chemistry challenging. Aiming to mitigate this problem, we developed DelFTa, an open-source toolbox for the prediction of electronic properties of drug-like molecules at the density functional (DFT) level of theory, using Δ-machine-learning. Δ-Learning corrects the prediction error (Δ) of a fast but inaccurate property calculation. DelFTa employs state-of-the-art three-dimensional message-passing neural networks trained on a large dataset of QM properties. It provides access to a wide array of quantum observables on the molecular, atomic and bond levels by predicting approximations to DFT values from a low-cost semiempirical baseline. Δ-Learning outperformed its direct-learning counterpart for most of the considered QM endpoints. The results suggest that predictions for non-covalent intra- and intermolecular interactions can be extrapolated to larger biomolecular systems. The software is fully open-sourced and features documented command-line and Python APIs.
| S-EPMC9093086 | biostudies-literature
Project description:Large discrepancies between well-mixed reaction rates and effective reactions rates estimated under fluid flow conditions have been a major issue for predicting reactive transport in porous media systems. In this study, we introduce a framework that accurately predicts effective reaction rates directly from pore structural features by combining 3D pore-scale numerical simulations with machine learning (ML). We first perform pore-scale reactive transport simulations with fluid-solid reactions in hundreds of porous media and calculate effective reaction rates from pore-scale concentration fields. We then train a Random Forests model with 11 pore structural features and effective reaction rates to quantify the importance of structural features in determining effective reaction rates. Based on the importance information, we train artificial neural networks with varying number of features and demonstrate that effective reaction rates can be accurately predicted with only three pore structural features, which are specific surface, pore sphericity, and coordination number. Finally, global sensitivity analyses using the ML model elucidates how the three structural features affect effective reaction rates. The proposed framework enables accurate predictions of effective reaction rates directly from a few measurable pore structural features, and the framework is readily applicable to a wide range of applications involving porous media flows.
| S-EPMC8971379 | biostudies-literature
Project description:Advancements in the implementation of quantum hardware have enabled the acquisition of data that are intractable for emulation with classical computers. The integration of classical machine learning (ML) algorithms with these data holds potential for unveiling obscure patterns. Although this hybrid approach extends the class of efficiently solvable problems compared to using only classical computers, this approach has been only realized for solving restricted problems because of the prevalence of noise in current quantum computers. Here, we extend the applicability of the hybrid approach to problems of interest in many-body physics, such as predicting the properties of the ground state of a given Hamiltonian and classifying quantum phases. By performing experiments with various error-reducing procedures on superconducting quantum hardware with 127 qubits, we managed to acquire refined data from the quantum computer. This enabled us to demonstrate the successful implementation of theoretically suggested classical ML algorithms for systems with up to 44 qubits. Our results verify the scalability and effectiveness of the classical ML algorithms for processing quantum experimental data.
| S-EPMC11364692 | biostudies-literature
Project description:The quantum mechanically calculable Q descriptor is shown to be a potent quantifier of chemical reactivity in complex molecules - it shows a strong correlation to experimentally derived field effects in non-aromatic substrates and Hammett σm and σp parameters. Models for predicting substituent effects from Q are presented and applied, including on the elusive pentazolyl substituent. The presented approach enables fast computational estimation of substituent effects, and, in extension, medium-throughput screening of molecules and compound design. An experimental dataset is suggested as a candidate benchmark for aiding the general development and comparison of electronic structure analyses. It is here used to evaluate the experimental quantum chemistry (EQC) framework for chemical bonding analysis in larger molecules.
| S-EPMC8049055 | biostudies-literature
Project description:Reaction databases provide a great deal of useful information to assist planning of experiments but do not provide any interpretation or chemical concepts to accompany this information. In this work, reactions are labeled with experimental conditions, and network analysis shows that consistencies within clusters of data points can be leveraged to organize this information. In particular, this analysis shows how particular experimental conditions (specifically solvent) are effective in enabling specific organic reactions (Friedel-Crafts, Aldol addition, Claisen condensation, Diels-Alder, and Wittig), including variations within each reaction class. Network analysis shows data points for reactions tend to break into clusters that depend on the catalyst and chemical structure. This type of clustering, which mimics how a chemist reasons, is derived directly from the network. Therefore, the findings of this work could augment synthesis planning by providing predictions in a fashion that mimics human chemists. To numerically evaluate solvent prediction ability, three methods are compared: network analysis (through the k-nearest neighbor algorithm), a support vector machine, and a deep neural network. The most accurate method in 4 of the 5 test cases is the network analysis, with deep neural networks also showing good prediction scores. The network analysis tool was evaluated by an expert panel of chemists, who generally agreed that the algorithm produced accurate solvent choices while simultaneously being transparent in the underlying reasons for its predictions.
| S-EPMC7167595 | biostudies-literature
Project description:Y6 and its derivatives have greatly improved the power conversion efficiency (PCE) of organic photovoltaics (OPVs). Further developing high-performance Y6 derivative acceptor materials through the relationship between the chemical structures and properties of these materials will help accelerate the development of OPV. Here, machine learning and quantum chemistry are used to understand the structure-property relationships and develop new OPV acceptor materials. By encoding the molecules with an improved one-hot code, the trained machine learning model shows good predictive performance, and 22 new acceptors with predicted PCE values greater than 17% within the virtual chemical space are screened out. Trends associated with the discovered high-performing molecules suggest that Y6 derivatives with medium-length side chains have higher performance. Further quantum chemistry calculations reveal that the end acceptor units mainly affect the frontier molecular orbital energy levels and the electrostatic potential on molecular surface, which in turn influence the performance of OPV devices. A series of promising Y6 derivative candidates is screened out and a rational design guide for developing high-performance OPV acceptors is provided. The approach in this work can be extended to other material systems for rapid materials discovery and can provide a framework for designing novel and promising OPV materials.
| S-EPMC8867193 | biostudies-literature
Project description:Knowledge of the mechanism of formation, levels and toxicological profiles of the chemical products in the aerosols (i.e., vapor plus particulate phases) of e-cigarettes is needed in order to better inform basic research as well as the general public, regulators, and industry. To date, studies of e-cigarette emissions have mainly focused on chromatographic techniques for quantifying and comparing the levels of selected e-cigarette aerosol components to those found in traditional cigarettes. E-cigarettes heat and aerosolize the solvents propylene glycol (PG) and glycerol (GLY), thereby affording unique product profiles as compared to traditional cigarettes. The chemical literature strongly suggests that there should be more compounds produced by PG and GLY than have been reported in e-cigarette aerosols to date. Herein we report an extensive investigation of the products derived from vaporizing PG and GLY under mild, single puff conditions. This has led to the discovery of several new compounds produced under vaping conditions. Prior reports on e-cigarette toxin production have emphasized temperature as the primary variable in solvent degradation. In the current study, the molecular pathways leading to enhanced PG/GLY reactivity are described, along with the most impactful chemical conditions promoting byproduct production.
| S-EPMC5307352 | biostudies-literature
Project description:Fast and accurate simulation of complex chemical systems in environments such as solutions is a long standing challenge in theoretical chemistry. In recent years, machine learning has extended the boundaries of quantum chemistry by providing highly accurate and efficient surrogate models of electronic structure theory, which previously have been out of reach for conventional approaches. Those models have long been restricted to closed molecular systems without accounting for environmental influences, such as external electric and magnetic fields or solvent effects. Here, we introduce the deep neural network FieldSchNet for modeling the interaction of molecules with arbitrary external fields. FieldSchNet offers access to a wealth of molecular response properties, enabling it to simulate a wide range of molecular spectra, such as infrared, Raman and nuclear magnetic resonance. Beyond that, it is able to describe implicit and explicit molecular environments, operating as a polarizable continuum model for solvation or in a quantum mechanics/molecular mechanics setup. We employ FieldSchNet to study the influence of solvent effects on molecular spectra and a Claisen rearrangement reaction. Based on these results, we use FieldSchNet to design an external environment capable of lowering the activation barrier of the rearrangement reaction significantly, demonstrating promising venues for inverse chemical design.
| S-EPMC8409491 | biostudies-literature
Project description:Machine learning advances chemistry and materials science by enabling large-scale exploration of chemical space based on quantum chemical calculations. While these models supply fast and accurate predictions of atomistic chemical properties, they do not explicitly capture the electronic degrees of freedom of a molecule, which limits their applicability for reactive chemistry and chemical analysis. Here we present a deep learning framework for the prediction of the quantum mechanical wavefunction in a local basis of atomic orbitals from which all other ground-state properties can be derived. This approach retains full access to the electronic structure via the wavefunction at force-field-like efficiency and captures quantum mechanics in an analytically differentiable representation. On several examples, we demonstrate that this opens promising avenues to perform inverse design of molecular structures for targeting electronic property optimisation and a clear path towards increased synergy of machine learning and quantum chemistry.
| S-EPMC6858523 | biostudies-literature
Project description:Synthetic design allowing predictive control of charge transfer and other optoelectronic properties of Lewis acid adducts remains elusive. This challenge must be addressed through complementary methods combining experimental with computational insights from first principles. Ab initio calculations for optoelectronic properties can be computationally expensive and less straightforward than those sufficient for simple ground-state properties, especially for adducts of large conjugated molecules and Lewis acids. In this contribution, we show that machine learning (ML) can accurately predict density functional theory (DFT)-calculated charge transfer and even properties associated with excited states of adducts from readily obtained molecular descriptors. Seven ML models, built from a dataset of over 1000 adducts, show exceptional performance in predicting charge transfer and other optoelectronic properties with a Pearson correlation coefficient of up to 0.99. More importantly, the influence of each molecular descriptor on predicted properties can be quantitatively evaluated from ML models. This contributes to the optimization of a priori design of Lewis adducts for future applications, especially in organic electronics.
| S-EPMC10233689 | biostudies-literature