Prediction of microdialysis relative recovery of flavone derivatives based on molecular descriptors

Abstract

Recuperação relativa (R e ) é uma das principais preocupações de microdiálise, uma técnica de amostragem acessível que pode coletar continuamente drogas livres no sangue e na maioria dos tecidos. Para uma determinada sonda de microdiálise, a recuperação de cada composto desta sonda está relacionada às características estruturais e propriedades físico-químicas se as condições experimentais estão estabelecidas. Neste trabalho, modelos de relação quantitativa estrutura-propriedade (QSPR) utilizando os métodos de regressão linear múltipla (MLR) e máquina de vetores de suporte (SVM) foram ajustados com o intuito de destrinchar relações de R e de microdiálise de compostos e seus descritores moleculares que capturam as características estruturais moleculares para uma série de derivados da flavona. Como resultado, parâmetros estatísticos significativos (modelo MLR: R 2 = 0,9268 (coeficiente de correlação), Q 2 LOO = 0,8572 (variância explicada prevista) e Q 2 ext = 0,8639 (variância explicada externa), e modelo SVM: R 2 = 0,9383 e Q 2 ext = 0,8536) foram obtidos, indicando boa estabilidade e habilidade preditiva dos modelos. Assim, tornando viável prever as recuperações relativas na microdiálise de alguns compostos a partir de seus descritores moleculares. Este estudo foi uma tentativa inovadora e pode fornecer novos métodos para pesquisar a recuperação de microdiálise dos compostos.Relative recovery (R e ) is one of the major concerns of microdialysis, a valuable sampling technique which can continuously collect unbound drugs in blood and most tissues. For a given microdialysis probe, the recovery of every compound from the probe is related to its structural characteristics and physicochemical property if the experiment condition is fixed. In this work, quantitative structure-property relationship (QSPR) models using multiple linear regression (MLR) and support vector machine (SVM) methods were setup to excavate the relationships of microdialysis R e of compounds and their molecular descriptors which capture the structural characteristics of molecules for a series of flavone derivatives. As result, significant statistical parameters (MLR model: R 2 = 0.9268 (correlation coefficient), Q 2 LOO = 0.8572 (explained variance in prediction) and Q 2 ext = 0.8639 (external explained variance), and SVM model: R 2 = 0.9383 and Q 2 ext = 0.8536) were obtained, indicating good stability and predictive ability of the models. Therefore, it seems feasible to predict the microdialysis relative recovery of some compounds from their molecular descriptors. This investigation was an innovative trial and can provide new methods for researching the microdialysis recovery of the compounds.

Support vector machines for modelling phosphocalcic hydroxyapatite by precipitation from a calcium carbonate solution and phosphoric acid solution

“…One of the main aims of SVM classification in general [50,51], and our study in particular, is the determination of the descriptors influencing the activity. The evaluation of the relevance of the four descriptors proved quite interesting and useful.…”

Predicting rejection of emerging contaminants through RO membrane filtration based on ANN-QSAR modeling approach: trends in molecular descriptors and structures towards rejections

“…On the other hand, molecular polarity is an important parameter in rejection by RO membranes because this factor influenced the interaction of the molecules with the membrane and, in turn, the diffusion of the molecules. 57,73,74…”

“…It should be mentioned in MLR analysis, EEig03d reported positive regression coefficients, which offered the descriptor had a positive effect on rejection, consequently, by increasing the value of EEig03d, rejection is increased. 74 …”

A QSAR Study on the 4-Substituted Coumarins as Potent Tubulin Polymerization Inhibitors

“…53 This descriptor is associated with molecular polarity and describes the electronic effects as well as the hydrophobic properties of molecule. 54 The second QSAR model (Eq. 7) describes the activities of coumarin analogs using one extra parameter added to the three previously explained features.…”