Journal of Chemometrics

Cover image for Journal of Chemometrics

September 2010

Volume 24, Issue 9

Pages 565–609

  1. Research Articles

    1. Top of page
    2. Research Articles
    1. Quantitative structure–activity relationship study on the inhibitors of fatty acid amide hydrolase (pages 565–573)

      Peng Lu, Ruisheng Zhang, Yongna Yuan and Zhiguo Gong

      Article first published online: 9 APR 2010 | DOI: 10.1002/cem.1314

      A quantitative structure activity relationship (QSAR) analysis was performed on the Ki values of a series of fatty acid amide hydrolase (FAAH) inhibitors. Six molecular descriptors selected by CODESSA software were used as inputs to perform heuristic method (HM) and support vector machine (SVM). The results obtained by SVM were compared with those obtained by the HM. The root mean square error (RMSE) for the training set given by HM and SVM were 0.555 and 0.404, respectively, which shows the performance of SVM model is better than that of the HM model. This paper provides a new and effective method for predicting the activity of FAAH inhibitors.

    2. Prediction of aqueous solubility of druglike organic compounds using partial least squares, back-propagation network and support vector machine (pages 584–595)

      Dong-Sheng Cao, Qing-Song Xu, Yi-Zeng Liang, Xian Chen and Hong-Dong Li

      Article first published online: 26 MAY 2010 | DOI: 10.1002/cem.1321

      In this study three commonly used methods, namely partial least squares (PLS), back-propagation network (BPN) and support vector regression (SVR), were employed to model quantitative structure-property relationship (QSPR) for the aqueous solubility of 180 druglike compounds. 28 molecular descriptors were used to relate the drug aqueous solubility. In order to obtain reliable and robust aqueous solubility prediction, a novel outlier detection method was employed to simultaneously detect all outliers in the established models. The results show that three models can obtain satisfactory prediction performance and predictive ability of SVR is superior to those of PLS and BPN.

    3. Window consensus PCA for multiblock statistical process control: adaption to small and time-dependent normal operating condition regions, illustrated by online high performance liquid chromatography of a three-stage continuous process (pages 596–609)

      Diana L. S. Ferreira, Sila Kittiwachana, Louise A. Fido, Duncan R. Thompson, Richard E. A. Escott and Richard G. Brereton

      Article first published online: 21 JUL 2010 | DOI: 10.1002/cem.1322

      Multiblock consensus principal component analysis is applied to online High Performance Liquid Chromatography of a three-stage continuous process. The problems of small Normal Operating Conditions regions and time dependency are tackled to provide improved block and super Q and D statistics for process monitoring.

SEARCH

SEARCH BY CITATION