• Journal of the Korean Chemical Society
• /
• v.45 no.5
• /
• pp.422-428
• /
• 2001

Retention relative times(RRTs) of PAH molecules and their derivatives in gas chromatography are trained and predicted in testing sets using a multiple linear regression(MLR) and an artificial neural network(ANN). The main descriptors of PAHs and their derivatives in QSRR are the square root of molecular weight(sqmw), molecular connectivity($^1{\chi}_v$), molecular dipole moment(D) and length-to-breadth ratios(L/B). The results of MLR shows that a heavy molecule has a propensity for long retention time. L/B closely related with slot model is a good descriptor in MLR. On the other hand, ANN which is not effected by the linear dependencies among the descriptors were exclusively based on molecular weight and molecular dipole moment. The variances which shows the accuracy of prediction for retention times in testing sets are 1.860, 0.206 for MLR and ANN, respectively. It was shown that ANN can exceed the MLR in prediction accuracy.

• Archives of Pharmacal Research
• /
• v.27 no.10
• /
• pp.1009-1015
• /
• 2004

Quantitative Structure-Resolution Relationship (QSRR) using the Comparative Molecular Field Analysis (CoMFA) software was applied to predict the chromatographic behaviors of chiral drugs with an amine moiety on the chiral cellobiohydrolase (CBH) columns. As a result of the Quantitative CoMFA-Resolution Relationship study, using the partial least square method, prediction of the behavior of drugs with amine moiety upon chiral separation became possible from their three dimensional molecular structures. When a mixed mobile phase of 10 mM aqueous phosphate buffer (pH 7.0) - isopropanol (95 : 5) was employed, the best Quantitative CoMFA-Resolution Relationship, derived from the study, provided a cross-validated $q^2$ = 0.933, a normal $r^2$ = 0.995, while the best Quantitative CoMFA-Separation Factor Relationship, also derived from the study, yielded a cross-validated $q^2$ = 0.939, a normal $r^2$ = 0.991. When all of these results are considered, this QSRR-CoMFA analysis appears to be a very useful tool for the preliminary prediction on the chromatographic behaviors of drugs with an amine moiety inside chiral CBH columns.

• Journal of the Korean Chemical Society
• /
• v.44 no.2
• /
• pp.102-108
• /
• 2000

Relative retention times (RRTs) of RAH molecules in HPLC are trained and predicted intesting sets using a multiple linear regression (NLR) and an artificial neural network (ANN). The maindescriptors in QSRR are molecular connectivity ($^1X_v,\;^2X_v$), the length-to-breadth ratios (L/B), and molecular dipole moment(D). L/B which is related with slot model is a good descripter in ANN, but isn't in MLR. Varainces which show the accuracy of prediction times in testing sets are 0.0099, 0.0114 for ANN and MLR, respectively. It was shown that ANN can exceed the MLR in prediction accuracy.