Dataset Information

Hammett neural networks: prediction of frontier orbital energies of tungsten-benzylidyne photoredox complexes.

ABSTRACT: The successful application of Hammett parameters as input features for regressive machine learning models is demonstrated and applied to predict energies of frontier orbitals of highly reducing tungsten-benzylidyne complexes of the form W([triple bond, length as m-dash]CArR)L4X. Using a reference molecular framework and the meta- and para-substituent Hammett parameters of the ligands, the models predict energies of frontier orbitals that correlate with redox potentials. The regressive models capture the multivariate character of electron-donating trends as influenced by multiple substituents even for non-aryl ligands, harnessing the breadth of Hammett parameters in a generalized model. We find a tungsten catalyst with tetramethylethylenediamine (tmeda) equatorial ligands and axial methoxyl substituents that should attract significant experimental interest since it is predicted to be highly reducing when photoactivated with visible light. The utilization of Hammett parameters in this study presents a generalizable and compact representation for exploring the effects of ligand substitutions.

SUBMITTER: Chang AM

PROVIDER: S-EPMC6657405 | biostudies-literature | 2019 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Hammett neural networks: prediction of frontier orbital energies of tungsten-benzylidyne photoredox complexes.

Chang Alexander M AM Freeze Jessica G JG Batista Victor S VS

Chemical science 20190612 28

The successful application of Hammett parameters as input features for regressive machine learning models is demonstrated and applied to predict energies of frontier orbitals of highly reducing tungsten-benzylidyne complexes of the form W([triple bond, length as m-dash]CArR)L4X. Using a reference molecular framework and the meta- and para-substituent Hammett parameters of the ligands, the models predict energies of frontier orbitals that correlate with redox potentials. ...[more]

PMID: 31391907

Similar Datasets

Project description:Applicability of Hammett parameters (σ m and σ p ) was tested in extended π-systems in gas phase. Three different model graphene systems, viz. 5,5-graphene (GR), 3-B-5,5-graphene (3BGR), and 3-N-5,5-graphene (3NGR), were designed as extended π-systems, and interactions of various nitrobenzene derivatives (mainly m- and p-substituted together with some multiple substitutions) on such platforms were monitored using density functional theory (M06/cc-pVDZ, M06/cc-pVTZ, M06/sp-aug-cc-pVTZ) and Møller-Plesset second-order perturbation (MP2/cc-pV-DZ) theory. Offset face to face (OSFF) stackings were found to be the favored orientations, and reasonable correlations were found between binding energies (ΔE B) and the ∑|σ m | values of the substituted nitrobenzenes. It was proposed previously that |σ m | contains information about the substituents' polarizability and controls electrostatic and dispersion interactions. The combination of ∑|σ m | and molar refractivity (as ∑M r) or change in polarizability (Δα: with respect to benzene) of nitrobenzene derivatives generated statistically significant correlation with respect to ΔE B, thereby supporting the hypothesis related to the validity of |σ m | correlations. The |σ p | parameters also maintain similar correlations for the various p-substituted nitrobenzene derivatives together with several multiply-substituted nitrobenzene derivatives. The correlation properties in such cases are similar to the |σ m | cases, and the energy partition analysis for both the situations reveled importance of electrostatic and dispersion contributions in such interactions. The applicability of Hammett parameters was observed previously on the restricted parallel face to face orientation of benzene···substituted benzene systems, and the present results show that such an idea could be used to predict ΔE B values in OSFF orientations, if the scaffolds are designed in such a way that substituted benzene systems cannot escape their π-clouds.

Project description:The prediction of breeding values and phenotypes is of central importance for both livestock and crop breeding. In this study, we analyze the use of artificial neural networks (ANN) and, in particular, local convolutional neural networks (LCNN) for genomic prediction, as a region-specific filter corresponds much better with our prior genetic knowledge on the genetic architecture of traits than traditional convolutional neural networks. Model performances are evaluated on a simulated maize data panel (n = 10,000; p = 34,595) and real Arabidopsis data (n = 2,039; p = 180,000) for a variety of traits based on their predictive ability. The baseline LCNN, containing one local convolutional layer (kernel size: 10) and two fully connected layers with 64 nodes each, is outperforming commonly proposed ANNs (multi layer perceptrons and convolutional neural networks) for basically all considered traits. For traits with high heritability and large training population as present in the simulated data, LCNN are even outperforming state-of-the-art methods like genomic best linear unbiased prediction (GBLUP), Bayesian models and extended GBLUP, indicated by an increase in predictive ability of up to 24%. However, for small training populations, these state-of-the-art methods outperform all considered ANNs. Nevertheless, the LCNN still outperforms all other considered ANNs by around 10%. Minor improvements to the tested baseline network architecture of the LCNN were obtained by increasing the kernel size and of reducing the stride, whereas the number of subsequent fully connected layers and their node sizes had neglectable impact. Although gains in predictive ability were obtained for large scale data sets by using LCNNs, the practical use of ANNs comes with additional problems, such as the need of genotyping all considered individuals, the lack of estimation of heritability and reliability. Furthermore, breeding values are additive by design, whereas ANN-based estimates are not. However, ANNs also comes with new opportunities, as networks can easily be extended to account for additional inputs (omics, weather etc.) and outputs (multi-trait models), and computing time increases linearly with the number of individuals. With advances in high-throughput phenotyping and cheaper genotyping, ANNs can become a valid alternative for genomic prediction.

Project description:A broad collection of technologies, including e.g. drug metabolism, biofuel combustion, photochemical decontamination of water, and interfacial passivation in energy production/storage systems rely on chemical processes that involve bond-breaking molecular reactions. In this context, a fundamental thermodynamic property of interest is the bond dissociation energy (BDE) which measures the strength of a chemical bond. Fast and accurate prediction of BDEs for arbitrary molecules would lay the groundwork for data-driven projections of complex reaction cascades and hence a deeper understanding of these critical chemical processes and, ultimately, how to reverse design them. In this paper, we propose a chemically inspired graph neural network machine learning model, BonDNet, for the rapid and accurate prediction of BDEs. BonDNet maps the difference between the molecular representations of the reactants and products to the reaction BDE. Because of the use of this difference representation and the introduction of global features, including molecular charge, it is the first machine learning model capable of predicting both homolytic and heterolytic BDEs for molecules of any charge. To test the model, we have constructed a dataset of both homolytic and heterolytic BDEs for neutral and charged (-1 and +1) molecules. BonDNet achieves a mean absolute error (MAE) of 0.022 eV for unseen test data, significantly below chemical accuracy (0.043 eV). Besides the ability to handle complex bond dissociation reactions that no previous model could consider, BonDNet distinguishes itself even in only predicting homolytic BDEs for neutral molecules; it achieves an MAE of 0.020 eV on the PubChem BDE dataset, a 20% improvement over the previous best performing model. We gain additional insight into the model's predictions by analyzing the patterns in the features representing the molecules and the bond dissociation reactions, which are qualitatively consistent with chemical rules and intuition. BonDNet is just one application of our general approach to representing and learning chemical reactivity, and it could be easily extended to the prediction of other reaction properties in the future.

Dataset Information

Hammett neural networks: prediction of frontier orbital energies of tungsten-benzylidyne photoredox complexes.

Publications

Hammett neural networks: prediction of frontier orbital energies of tungsten-benzylidyne photoredox complexes.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure