Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: molecular descriptor

Sortuj według:

Ogranicz wyniki do:

Quantitative structure-retention relationship prediction of Kováts retention index of some organic acids

Fatemi M. H., Elyasi M.

Acta Chromatographica

2013

Vol. 25, no. 3

411--422

In this work, quantitative structure-retention relationship (QSRR) approaches were applied for modeling and prediction of the gas chromatographic retention indices of some amino acids (AAs) and carboxylic acids (CAs). The genetic algorithm (GA) method was used to select the most relevant descriptors, which are responsible for the retention of these compounds. Then, multiple linear regression (MLR), artificial neural network (ANN) and support vector machine (SVM) were utilized to construct the nonlinear and linear quantitative structure-retention relationship models. The obtained results revealed that the GA-ANN developed model was better than other models. This model has the average absolute relative errors of 0.043, 0.052 and 0.045 for training, internal and external test set. Applying the 10-fold cross-validation procedure on GAAAN model obtained the statistics of Q2 = 0.941 which revealed the reliability of this model.

Application of Molecular Descriptors to the Prediction of Retention in Organic Solvent Nanofiltration

Koter S., Gilewicz-Łukasik B., Nowaczyk A., Nowaczyk J.

Polish Journal of Chemistry

2009

Vol. 83, nr 12

2137-2152

An attempt to apply the molecular descriptors for the characterization of retention of solutes in organic solvent nanofiltration has been performed. The descriptors were calculated using the program Dragon. The geometry of each solute molecule has been optimized using GaussianŽ. Two linear equations relating the retention coefficient, R, with one or two descriptors have been tested using two sets of solutes. The first one (“soft” set) consisted of saturated and aromatic hydrocarbons (data of White, J. Membr.Sci., 205, 191 (2002)), the second one (“hard” set) contained the substituted aromatic hydro carbons with heteroatoms (data of Geens et al., J. Membr. Sci., 281, 139 (2006)). It has been found that the “soft” set of compounds is described reasonably well by both equations. The best descriptors belong to GET AWAY descriptors and Burdeneigen values. Regarding the “hard” set of compounds only the 2-descriptors equation yields a satisfactory fitting of R. Here the 3D-MoRSE descriptors are the best for 7 of 14 membrane-solvent systems.