scholarly journals Kernel Methods for Predicting Yields of Chemical Reactions

2021 ◽  
Author(s):  
Alexe Haywood ◽  
Joseph Redshaw ◽  
Magnus Hanson-Heine ◽  
Adam Taylor ◽  
Alex Brown ◽  
...  
Keyword(s):  
Quantum Chemical ◽  
Density Functional ◽  
Aryl Halide ◽  
Reaction Yield ◽  
Support Vector ◽  
Quantum Chemical Descriptors ◽  
Functional Theory ◽  
Molecular Fingerprints ◽  
Chemical Descriptors ◽  
Synthetic Assessment

The use of machine learning methods for the prediction of reaction yield is an emerging area. We demonstrate the applicability of support vector regression (SVR) for predicting reaction yields, using combinatorial data. Molecular descriptors used in regression tasks related to chemical reac?tivity have often been based on time-consuming, computationally demanding quantum chemical calculations, usually density functional theory. Structure-based descriptors (molecular fingerprints and molecular graphs) are quicker and easier to calculate, and are applicable to any molecule. In this study, SVR models built on structure-based descriptors were compared to models built on quantum chemical descriptors. The models were evaluated along the dimension of each reaction component in a set of Buchwald-Hartwig amination reactions. The structure-based SVR models out-performed the quantum chemical SVR models, along the dimension of each reaction compo?nent. The applicability of the models was assessed with respect to similarity to training. Prospec?tive predictions of unseen Buchwald-Hartwig reactions are presented for synthetic assessment, to validate the generalisability of the models, with particular interest along the aryl halide dimension.

scholarly journals Kernel Methods for Predicting Yields of Chemical Reactions

2021 ◽  
Author(s):  
Alexe Haywood ◽  
Joseph Redshaw ◽  
Magnus Hanson-Heine ◽  
Adam Taylor ◽  
Alex Brown ◽  
...  
Keyword(s):  
Quantum Chemical ◽  
Density Functional ◽  
Aryl Halide ◽  
Reaction Yield ◽  
Support Vector ◽  
Quantum Chemical Descriptors ◽  
Functional Theory ◽  
Molecular Fingerprints ◽  
Chemical Descriptors ◽  
Synthetic Assessment

The use of machine learning methods for the prediction of reaction yield is an emerging area. We demonstrate the applicability of support vector regression (SVR) for predicting reaction yields, using combinatorial data. Molecular descriptors used in regression tasks related to chemical reac?tivity have often been based on time-consuming, computationally demanding quantum chemical calculations, usually density functional theory. Structure-based descriptors (molecular fingerprints and molecular graphs) are quicker and easier to calculate, and are applicable to any molecule. In this study, SVR models built on structure-based descriptors were compared to models built on quantum chemical descriptors. The models were evaluated along the dimension of each reaction component in a set of Buchwald-Hartwig amination reactions. The structure-based SVR models out-performed the quantum chemical SVR models, along the dimension of each reaction compo?nent. The applicability of the models was assessed with respect to similarity to training. Prospec?tive predictions of unseen Buchwald-Hartwig reactions are presented for synthetic assessment, to validate the generalisability of the models, with particular interest along the aryl halide dimension.

Prediction of the polarity parameter π for the radical derived from monomer

e-Polymers ◽  
2009 ◽  
Vol 9 (1) ◽  
Author(s):  
Xinliang Yu ◽  
Wenhao Yu ◽  
Bing Yi ◽  
Xueye Wang
Keyword(s):  
Neural Network ◽  
Quantum Chemical ◽  
Density Functional ◽  
Ann Model ◽  
Quantum Chemical Descriptors ◽  
Functional Theory ◽  
The Neural Network ◽  
Polarity Parameter ◽  
Chemical Descriptors ◽  
Artificial Neural Network Ann

AbstractAn artificial neural network (ANN) model was successfully developed for the modelling and prediction of the polarity parameter π used in the revised patterns scheme for the prediction of monomers reactivity ratios in radical polymerizations. Four quantum chemical descriptors based on density functional theory (DFT) calculations were used to develop the ANN model. The optimal condition of the neural network was obtained by adjusting various parameters by trial-and-error. Simulated with the final optimum BP neural network 4-4-1, the results show that the predicted parameter π values are in good agreement with the experimental ones, with the root mean square (rms) errors being 0.053 (R=0.960) for the training set and 0.070 (R=0.942) for the test set. The ANN model has better statistic quality than the MLR model, which indicates there are nonlinear relationships between these quantum chemical descriptors and the parameter π.

scholarly journals 2D-QSPR Study of Olfactive Thresholds for Pyrazine Derivatives Using DFT and Statistical Methods

2019 ◽  
Vol 3 (3) ◽  
pp. 179-186
Author(s):  
Assia Belhassan ◽  
Samir Chtita ◽  
Tahar Lakhlifi ◽  
Mohammed Bouachrine
Keyword(s):  
Quantum Chemical ◽  
Density Functional ◽  
Training Set ◽  
Quantum Chemical Descriptors ◽  
Qspr Model ◽  
Functional Theory ◽  
The Density Functional Theory ◽  
Chemical Descriptors ◽  
External Consistency ◽  
And Training

In this study, we have established two-dimensional quantitative structure propriety relationships (2D-QSPR) model, for a group of 78 molecules based on pyrazine, these molecules were subjected to a 2D-QSPR analyze for their odors thresholds propriety using stepwise Multiple Linear Regression (MLR). The 35 parameters are calculated for the 78 studied compounds using the Gaussian 09W, ChemOffice and ChemSketch softwares. Quantum chemical calculations are used to calculate electronic and quantum chemical descriptors, using the density functional theory (B3LYP/6-31G (d) DFT) methods.The model was used to predict the odors thresholds propriety of the test and training set compounds, and the statistical results exhibited high internal and external consistency as demonstrated by the validation methods.

scholarly journals Mechanistic Chromatographic Column Characterization for the Analysis of Flavonoids Using Quantitative Structure-Retention Relationships Based on Density Functional Theory

2020 ◽  
Vol 21 (6) ◽  
pp. 2053 ◽  
Author(s):  
Bogusław Buszewski ◽  
Petar Žuvela ◽  
Gulyaim Sagandykova ◽  
Justyna Walczak-Skierska ◽  
Paweł Pomastowski ◽  
...  
Keyword(s):  
Electrostatic Interactions ◽  
Density Functional ◽  
Stationary Phases ◽  
Retention Mechanism ◽  
Quantitative Structure ◽  
Quantum Chemical Descriptors ◽  
Functional Theory ◽  
Dispersion Effects ◽  
Chemical Descriptors ◽  
Structure Retention

This work aimed to unravel the retention mechanisms of 30 structurally different flavonoids separated on three chromatographic columns: conventional Kinetex C18 (K-C18), Kinetex F5 (K-F5), and IAM.PC.DD2. Interactions between analytes and chromatographic phases governing the retention were analyzed and mechanistically interpreted via quantum chemical descriptors as compared to the typical ‘black box’ approach. Statistically significant consensus genetic algorithm-partial least squares (GA-PLS) quantitative structure retention relationship (QSRR) models were built and comprehensively validated. Results showed that for the K-C18 column, hydrophobicity and solvent effects were dominating, whereas electrostatic interactions were less pronounced. Similarly, for the K-F5 column, hydrophobicity, dispersion effects, and electrostatic interactions were found to be governing the retention of flavonoids. Conversely, besides hydrophobic forces and dispersion effects, electrostatic interactions were found to be dominating the IAM.PC.DD2 retention mechanism. As such, the developed approach has a great potential for gaining insights into biological activity upon analysis of interactions between analytes and stationary phases imitating molecular targets, giving rise to an exceptional alternative to existing methods lacking exhaustive interpretations.

scholarly journals Estimation of n-octanol/water partition coefficients of polycyclic aromatic hydrocarbons by quantum chemical descriptors

2008 ◽  
Vol 6 (2) ◽  
pp. 310-318 ◽  
Author(s):  
Gui-Ning Lu ◽  
Xue-Qin Tao ◽  
Zhi Dang ◽  
Xiao-Yun Yi ◽  
Chen Yang
Keyword(s):  
Polycyclic Aromatic Hydrocarbons ◽  
Aromatic Hydrocarbons ◽  
Quantum Chemical ◽  
Partition Coefficients ◽  
Density Functional ◽  
Optimal Model ◽  
Quantum Chemical Descriptors ◽  
Polycyclic Aromatic ◽  
Pls Analysis ◽  
Chemical Descriptors

AbstractQuantitative structure-property relationship (QSPR) modeling is a powerful approach for predicting environmental behavior of organic pollutants with their structure descriptors. This study reports an optimal QSPR model for estimating logarithmic n-octanol/water partition coefficients (log K OW) of polycyclic aromatic hydrocarbons (PAHs). Quantum chemical descriptors computed with density functional theory at B3LYP/6-31G(d) level and partial least squares (PLS) analysis with optimizing procedure were used for generating QSPR models for log K OW of PAHs. The squared correlation coefficient (R 2) of the optimal model was 0.990, and the results of crossvalidation test (Q 2cum=0.976) showed this optimal model had high fitting precision and good predictability. The log K OW values predicted by the optimal model are very close to those observed. The PLS analysis indicated that PAHs with larger electronic spatial extent and lower total energy values tend to be more hydrophobic and lipophilic.

scholarly journals Electronic structural properties of amino/hydroxyl functionalized imidazolium-based bromide ionic liquids

2020 ◽  
Vol 18 (1) ◽  
pp. 576-583
Author(s):  
Xiaoling Hu ◽  
Xingang Jia ◽  
Kehe Su ◽  
Xuefan Gu
Keyword(s):  
Ionic Liquids ◽  
Structural Properties ◽  
Density Functional ◽  
Energy Levels ◽  
Ion Pairs ◽  
Binding Energies ◽  
Intramolecular Interactions ◽  
Quantum Chemical Descriptors ◽  
Functional Theory ◽  
Chemical Descriptors

AbstractElectronic structural properties of the three different imidazolium-based ionic liquids, namely, 1-butyl-3-methyl imidazolium bromide (C4mimBr), 1-(4-hydroxybutyl)-3-methylimidazolium bromide (C4OHmimBr), and 1-(4-aminobutyl)-3-methylimidazolium bromide (C4NH2mimBr), were investigated with density functional theory at the B3LYP/6-311++G(d,p) level. The conformations of the mentioned cations were fully studied first using CONFLEX 8.A program. The quantum theory of atoms in molecules was used to investigate the nature of intramolecular interactions. The counterpoise-corrected ion pairs binding energies were obtained at the same level of theory. Natural bond orbital analyses show that the largest intra-molecular interaction comes from the orbital overlap between n(N1) and π* (N4–C5) in the mentioned compounds. The energy levels of frontier molecular orbitals (FMOs) are displayed. The global quantum chemical descriptors are also calculated based on the energy values of FMOs.

scholarly journals Global chemical reactivity parameters for several chiral beta-blockers from Density Functional Theory Viewpoint

2016 ◽  
Vol 89 (4) ◽  
pp. 513-518 ◽  
Author(s):  
Mona Maria Talmaciu ◽  
Ede Bodoki ◽  
Radu Oprean
Keyword(s):  
Quantum Chemical ◽  
Density Functional ◽  
Chemical Potential ◽  
Chemical Reactivity ◽  
Beta Blockers ◽  
Chemical Hardness ◽  
Quantum Chemical Descriptors ◽  
Chemical Structures ◽  
Coronary Syndrome ◽  
Chemical Descriptors

Background and aim.  Beta-adrenergic antagonists have been established as first line treatment in the medical management of hypertension, acute coronary syndrome and other cardiovascular diseases, as well as for the prevention of initial episodes of gastrointestinal bleeding in patients with cirrhosis and esophageal varices, glaucoma, and have recently become the main form of treatment of infantile hemangiomas.The aim of the present study is to calculate for 14 beta-blockers several quantum chemical descriptors in order to interpret various molecular properties such as electronic structure, conformation, reactivity, in the interest of determining how such descriptors could have an impact on our understanding of the experimental observations and describing various aspects of chemical binding of beta-blockers in terms of these descriptors.Methods. The 2D chemical structures of the beta-blockers (14 molecules with one stereogenic center) were cleaned in 3D, their geometry was preoptimized using the software MOPAC2012, by PM6 method, and then further refined using standard settings in MOE; HOMO and LUMO descriptors were calculated using semi-empirical molecular orbital methods AM1, MNDO and PM3, for the lowest energy conformers and the quantum chemical descriptors (HLG, electronegativity, chemical potential, hardness and softness, electrophilicity) were then calculated.Results. According to HOMO-LUMO gap and the chemical hardness the most stable compounds are alprenolol, bisoprolol and esmolol. The softness values calculated for the study molecules revolve around 0.100. Propranolol, sotalol and timolol have among the highest electrophilicity index of the studied beta-blocker molecules. Results obtained from calculations showed that acebutolol, atenolol, timolol and sotalol have the highest values for the electronegativity index. Conclusions. The future aim is to determine whether it is possible to find a valid correlation between these descriptors and the physicochemical behavior of the molecules from this class. The HLG could be correlated to the experimentally recorded electrochemical properties of the molecules. HOMO could be correlated to the observed oxidation potential, since the required voltage is related to the energy of the HOMO, because only the electron from this orbital is involved in the oxidation process.

Spectroscopic and Quantum Chemical Investigations of Hypothetical m-Diacetylaminoazopyrimidine and Its Photovoltaic Properties

2021 ◽  
Vol 14 (2) ◽  
pp. 139-154
Keyword(s):  
Excited State ◽  
Quantum Chemical ◽  
Density Functional ◽  
Chemical Potential ◽  
Energy Gap ◽  
Dye Sensitized Solar Cells ◽  
Chemical Hardness ◽  
Quantum Chemical Descriptors ◽  
Photovoltaic Properties ◽  
Chemical Descriptors

Abstract: Here, an attempt is made to theoretically study and predict the electronic and spectroscopic (UV-Vis and IR) and structural properties, quantum chemical descriptors and subsequent application of diacetylaminoazopyrimidine in dye-sensitized solar cells (DSSCs). Ground- and excited-state time-dependent density functional theory (TD-DFT) calculations were carried out using material studio and ORCA software, respectively. The computed ground-state energy gap, chemical hardness, chemical softness, chemical potential, electronegativity and electrophilicity index are: 3.60 eV, 1.80 eV, 0.56 eV, 4.49 eV, -4.49 eV and 5.68, respectively. Conversely, the DFT-predicted excited-state quantum chemical descriptors are: 1.67 eV, 0.83 eV, 1.20 eV, 4.71 eV and -4.71 eV, corresponding to the energy gap, chemical hardness, chemical softness, chemical potential and electronegativity, respectively. Furthermore, vibrational frequency calculations confirm the presence of some key functional groups (N=N, C=O, C-H) present in the dye molecules. The computed optoelectronic parameters, such as light-harvesting efficiency, electron injection and open-circuit voltage are 0.06 eV, -8.59 eV and -5.75 eV, respectively. Overall, the dye possesses a relatively good current conversion efficiency as compared to other dyes studied in the literature; hence, it could be used as a novel material for photovoltaic technological applications. Keywords: Diacetylaminoazopyrimidine, DFT, Excited state, Spectroscopy, DSSCs.

Sign in / Sign up

Export Citation Format

Share Document