Prediction of 13C NMR chemical shifts by artificial neural network. I. Partial charge model as atomic descriptor

Kiryanov, Ilya I.; Mukminov, Farit H.; Tulyabaev, Arthur R.

doi:10.1016/j.chemolab.2016.01.010

Cited by 6 publications

(1 citation statement)

References 29 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…В исследованиях структур с внутримолекулярными водородными связями существуют подходы, основанные на поиске электронных дескрипторов, которые могут быть количественно взаимосвязаны с экспериментально наблюдаемыми физико-химическими характеристиками [7], в том числе химическими сдвигами, наблюдаемыми в 1 Н ЯМР-спектрах. Известно использование дескрипторов, основанных на учете типа химической связи, окружении атома, его электроотрицательности, атомных зарядах [8]. Находят применение зависимости между химическим сдвигом и энергией водородной связи [9], которые изучаются как экспериментально, так и теоретически в сложных или неравновесных системах (стекла, биологические объекты).…”

Section: Introductionunclassified

Atomic Dipole Polarization in Predictions of Chemical Shifts of Amide and Pyrrolidine Protons

Borodina,

Bartashevich

2021

Chem

View full text Add to dashboard Cite

A quantitative relationship has been established between the localization indices of electrons in atomic basins and chemical shifts of protons in amide and pyrrolidine fragments when they are present together in organic molecules. The fragments under consideration are important as key functional groups in the molecules of chiral inducers involved in stereoselective syntheses, in order to obtain drugs based on pyrimidinone heterocyclic systems. Integral properties of electron density, such as the magnitude of intra-atomic dipole polarization and charges of hydrogen atoms, calculated by integration of the electron density over the volumes of atomic basins, correlate with chemical shifts significantly better than the point atomic charges. Our proposed parametric model for the rapid prediction of chemical shifts is based on an equation that includes the electron localization index in the hydrogen atom basin as a factor. The developed approach offers a theoretical model for a rapid quantitative assessment of chemical shifts and makes it possible to formulate the main structural factors that provide correlation between the calculated and experimental chemical shifts of hydrogen atoms involved in intramolecular hydrogen bonds. It has been revealed that intramolecular hydrogen bonds are the main structural features that ensure the correlation of atomic integral characteristics with chemical shifts in the considered molecules. The results obtained in the course of theoretical modeling have been verified by comparison with the experimental 1H NMR data for 4-hydroxyproline-2-carboxanilide podands with different oxyethylene chain lengths, which are chiral inductors of stereoselective syntheses of drugs based on pyrimidinone heterocyclic systems.

show abstract

Section: Introductionunclassified

Atomic Dipole Polarization in Predictions of Chemical Shifts of Amide and Pyrrolidine Protons

Borodina,

Bartashevich

2021

Chem

View full text Add to dashboard Cite

show abstract

Neural network for prediction of ¹³C NMR chemical shifts of fullerene C₆₀ mono‐adducts

Kiryanov

Tulyabaev

Mukminov

et al. 2018

Journal of Chemometrics

View full text Add to dashboard Cite

Real‐valued models based on deep artificial neural networks were proposed to predict 13C NMR chemical shifts of fullerene C60 core carbon atoms for computer‐aided structure elucidation of complex fullerene C60 mono‐adducts. We showed that parametric rectified linear units could be successfully used as activation functions in hidden layers of artificial neural networks for decision of complex physical‐chemical tasks. A total of 400 artificial neural networks were trained and tested in order to reveal the best‐fitted models. The best prediction accuracy of real‐valued models was achieved with MAEP = 1.83 ppm/RMSEP = 2.60 ppm using artificial neural network model which has 110 and 120 hidden units, respectively, with parametric rectified linear unit as activation function.

show abstract

Correlation between 13C NMR chemical shifts and complete sets of descriptors of natural coumarin derivatives

Lisha

Zhu

et al. 2019

Chemometrics and Intelligent Laboratory Systems

View full text Add to dashboard Cite

Prediction of 13C NMR chemical shifts by artificial neural network. I. Partial charge model as atomic descriptor

Cited by 6 publications

References 29 publications

Atomic Dipole Polarization in Predictions of Chemical Shifts of Amide and Pyrrolidine Protons

Atomic Dipole Polarization in Predictions of Chemical Shifts of Amide and Pyrrolidine Protons

Neural network for prediction of ¹³C NMR chemical shifts of fullerene C₆₀ mono‐adducts

Correlation between 13C NMR chemical shifts and complete sets of descriptors of natural coumarin derivatives

Contact Info

Product

Resources

About

Prediction of 13C NMR chemical shifts by artificial neural network. I. Partial charge model as atomic descriptor

Cited by 6 publications

References 29 publications

Atomic Dipole Polarization in Predictions of Chemical Shifts of Amide and Pyrrolidine Protons

Atomic Dipole Polarization in Predictions of Chemical Shifts of Amide and Pyrrolidine Protons

Neural network for prediction of 13C NMR chemical shifts of fullerene C60 mono‐adducts

Correlation between 13C NMR chemical shifts and complete sets of descriptors of natural coumarin derivatives

Contact Info

Product

Resources

About

Neural network for prediction of ¹³C NMR chemical shifts of fullerene C₆₀ mono‐adducts