A new issue of this journal has just been published. To see abstracts of the papers it contains (with links through to the full papers) click here:
http://rss.sciencedirect.com/publication/science/5232
Selected papers from the latest issue:
Selected papers from the latest issue:
CORAL: QSAR modeling of toxicity of organic chemicals towardsDaphnia magna
15 October 2011, 22:05:36
Publication year: 2011
Source: Chemometrics and Intelligent Laboratory Systems, Available online 15 October 2011
A.P. Toropova, A.A. Toropov, S.E. Martyanov, E. Benfenati, G.Gini, ...
Convenient to apply and available on the Internet, CORAL software (http://www.insilico.eu/CORAL) has been used to build up quantitative structure – activity relationships (QSAR) for prediction of toxicity toDaphnia Magna. The QSARs developed in this study are one-variable models based on the optimal descriptors calculated with the Monte Carlo method. The toxicity has been modelled with the following representations of the molecular structure: (i) by hydrogen-suppressed graph (HSG); (ii) by simplified molecular input line entry system (SMILES); and (iii) by hybrid representation, i.e. the HSG together with SMILES. Four random splits into the sub-training, calibration, and test sets were examined. The hybrid version of the representation of the molecular structure provided the best accuracy of the prediction for the considered endpoint.
Source: Chemometrics and Intelligent Laboratory Systems, Available online 15 October 2011
A.P. Toropova, A.A. Toropov, S.E. Martyanov, E. Benfenati, G.Gini, ...
Convenient to apply and available on the Internet, CORAL software (http://www.insilico.eu/CORAL) has been used to build up quantitative structure – activity relationships (QSAR) for prediction of toxicity toDaphnia Magna. The QSARs developed in this study are one-variable models based on the optimal descriptors calculated with the Monte Carlo method. The toxicity has been modelled with the following representations of the molecular structure: (i) by hydrogen-suppressed graph (HSG); (ii) by simplified molecular input line entry system (SMILES); and (iii) by hybrid representation, i.e. the HSG together with SMILES. Four random splits into the sub-training, calibration, and test sets were examined. The hybrid version of the representation of the molecular structure provided the best accuracy of the prediction for the considered endpoint.
Highlights
► Correlations between toxicity toward Daphnia magna and optimal descriptors have been examined; ► Three types of the optimal descriptors have been studied: (i) descriptors which are calculated with solely graphs; (ii) descriptors which are calculated with solely SMILES; and (iii) hybrid descriptors which are calculated with both SMILES and graphs; ► The hybrid descriptors are best predictors of the above-mentioned endpoint for four random splits into the sub-training, calibration, and test sets.Improved sensitivity THrough Morris extension
15 October 2011, 22:05:36
Publication year: 2011
Source: Chemometrics and Intelligent Laboratory Systems, Available online 15 October 2011
J. Santiago, B. Corre, M. Claeys-Bruno, M. Sergent
This paper presents a new sensitivity analysis method called ISTHME based on the principles of Morris's method without the construction of randomized one-at-time (OAT) design. The presented method can be applied on any experimental design and more particularly on Space Filling Designs. This specificity is very interesting in terms of time and calculation economy. Indeed, we can use an universal design, which is adapted to sensitivity analysis as well as optimization without any supplementary simulation.
Source: Chemometrics and Intelligent Laboratory Systems, Available online 15 October 2011
J. Santiago, B. Corre, M. Claeys-Bruno, M. Sergent
This paper presents a new sensitivity analysis method called ISTHME based on the principles of Morris's method without the construction of randomized one-at-time (OAT) design. The presented method can be applied on any experimental design and more particularly on Space Filling Designs. This specificity is very interesting in terms of time and calculation economy. Indeed, we can use an universal design, which is adapted to sensitivity analysis as well as optimization without any supplementary simulation.
On the generalised case of sequential standard addition calibration
15 October 2011, 22:05:36
Publication year: 2011
Source: Chemometrics and Intelligent Laboratory Systems, Available online 14 October 2011
Richard J.C. Brown, Thomas P.S. Gillam
The generalised case of sequential standard addition calibration is described and explored mathematically. The procedure is generalised by removing the previously imposed requirement for the analysis step not to consume any of the sample. Expressions for the gradient, systematic bias and relative precision of extrapolation have been derived and solved. It has been shown that the characteristics of the calculated gradient and systematic bias of extrapolation for the generalised case with a single addition of standard solution are identical to those previously published for cases where no sample is consumed during analysis, depending only on the ratio of target analyte content in the standard to that in the sample. The relative precision of extrapolation has been calculated for a number of different scenarios encompassing all the variables involved in defining the generalised case. It has been demonstrated that the best precision is obtained when the mass of sample removed or consumed during analysis and the mass of standard added for calibration are large compared to the total sample mass.
Source: Chemometrics and Intelligent Laboratory Systems, Available online 14 October 2011
Richard J.C. Brown, Thomas P.S. Gillam
The generalised case of sequential standard addition calibration is described and explored mathematically. The procedure is generalised by removing the previously imposed requirement for the analysis step not to consume any of the sample. Expressions for the gradient, systematic bias and relative precision of extrapolation have been derived and solved. It has been shown that the characteristics of the calculated gradient and systematic bias of extrapolation for the generalised case with a single addition of standard solution are identical to those previously published for cases where no sample is consumed during analysis, depending only on the ratio of target analyte content in the standard to that in the sample. The relative precision of extrapolation has been calculated for a number of different scenarios encompassing all the variables involved in defining the generalised case. It has been demonstrated that the best precision is obtained when the mass of sample removed or consumed during analysis and the mass of standard added for calibration are large compared to the total sample mass.
Highlights
► The generalised case of sequential standard addition calibration has been described. ► An expression for the gradient, systematic bias and relative precision associated with the technique has been derived. ► It has been shown that for single point addition the generalised case is equivalent to previous, non-generalised, considerations. ► The linearity of multi-point addition shows a strong dependence on the solution mass and analyte concentration. ► The findings provide a new tool for analytical chemists to quantify analyte content in unknown solutions.Classification of central nervous system agents by least squares support vector machine based on their structural descriptors; a comparative study
15 October 2011, 22:05:36
Publication year: 2011
Source: Chemometrics and Intelligent Laboratory Systems, Available online 14 October 2011
Mehdi Ghorbanzad'e, Mohammad Hossein Fatemi
Linear and quadratic discriminant analysis and least squares support vector machine (LS-SVM) were used to classify a data set of 326 central nervous system (CNS) drugs as active or inactive CNS agents according to their permeation into the blood brain barrier. A pool of descriptors was calculated by DRAGON software and nine of them were selected based on Wilk's lambda and classification accuracy and used for classification of drugs in data set. The classification models were validated based on accuracy, sensitivity, specifity, Matthew's correlation coefficient and Cohen's kappa values. The developed LS-SVM model, as the superior model has the accuracy of 96.5% and 96.0%, Matthew's correlation coefficient of 0.930 and 0.920, Cohen's kappa value of 0.963 and 0.917, and area under recursive operating characteristic curve of 0.95 and 0.98 for training and test sets, respectively. The results of this study indicated the applicability of LS-SVM in classification of CNS drugs based on their structural descriptors.
Source: Chemometrics and Intelligent Laboratory Systems, Available online 14 October 2011
Mehdi Ghorbanzad'e, Mohammad Hossein Fatemi
Linear and quadratic discriminant analysis and least squares support vector machine (LS-SVM) were used to classify a data set of 326 central nervous system (CNS) drugs as active or inactive CNS agents according to their permeation into the blood brain barrier. A pool of descriptors was calculated by DRAGON software and nine of them were selected based on Wilk's lambda and classification accuracy and used for classification of drugs in data set. The classification models were validated based on accuracy, sensitivity, specifity, Matthew's correlation coefficient and Cohen's kappa values. The developed LS-SVM model, as the superior model has the accuracy of 96.5% and 96.0%, Matthew's correlation coefficient of 0.930 and 0.920, Cohen's kappa value of 0.963 and 0.917, and area under recursive operating characteristic curve of 0.95 and 0.98 for training and test sets, respectively. The results of this study indicated the applicability of LS-SVM in classification of CNS drugs based on their structural descriptors.
No comments:
Post a Comment