Predicting the reaction rates between flavonoids and methylglyoxal by combining molecular properties and machine learning
Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Standard
Predicting the reaction rates between flavonoids and methylglyoxal by combining molecular properties and machine learning. / Zhu, Hongkai; Liu, Jingyuan; Andersen, Mogens L.; Peters, Günther H.J.; Lund, Marianne N.
I: Food Bioscience, Bind 54, 102890, 2023.Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Predicting the reaction rates between flavonoids and methylglyoxal by combining molecular properties and machine learning
AU - Zhu, Hongkai
AU - Liu, Jingyuan
AU - Andersen, Mogens L.
AU - Peters, Günther H.J.
AU - Lund, Marianne N.
N1 - Publisher Copyright: © 2023 The Authors
PY - 2023
Y1 - 2023
N2 - The kinetics of the reaction between methylglyoxal (MGO) and epigallocatechin gallate have been investigated at pH 7.4 and 37 °C, and the kinetic data were combined with previously obtained data of six other flavonoids to develop a model that allows to predict the trapping capacity of MGO based on the molecular properties of the seven flavonoids. The observed data were augmented by using synthetic minority oversampling technique forming a new data set that was used to create the predicting models for the trapping rate constant of MGO by flavonoids via principal component regression (PCR) and back-propagation neural network algorithm, respectively. The PCR model based on the first six principle components was robust and accurate comparing other created models, with an associated root-mean-square error value of 8.02 × 10−7 on the testing set. This work provides quantitative structure-activity models for rapid and accurate prediction of the trapping rate constant of MGO by flavonoids.
AB - The kinetics of the reaction between methylglyoxal (MGO) and epigallocatechin gallate have been investigated at pH 7.4 and 37 °C, and the kinetic data were combined with previously obtained data of six other flavonoids to develop a model that allows to predict the trapping capacity of MGO based on the molecular properties of the seven flavonoids. The observed data were augmented by using synthetic minority oversampling technique forming a new data set that was used to create the predicting models for the trapping rate constant of MGO by flavonoids via principal component regression (PCR) and back-propagation neural network algorithm, respectively. The PCR model based on the first six principle components was robust and accurate comparing other created models, with an associated root-mean-square error value of 8.02 × 10−7 on the testing set. This work provides quantitative structure-activity models for rapid and accurate prediction of the trapping rate constant of MGO by flavonoids.
KW - Computational chemistry
KW - Data augmentation
KW - Dicarbonyl
KW - Kinetics
KW - Neural network
KW - Principal component regression
U2 - 10.1016/j.fbio.2023.102890
DO - 10.1016/j.fbio.2023.102890
M3 - Journal article
AN - SCOPUS:85164004588
VL - 54
JO - Food Bioscience
JF - Food Bioscience
SN - 2212-4292
M1 - 102890
ER -
ID: 360068263