Home About us Contact
|
Home About us Contact | ||
|
|
||
Prediction Set (prediction + set)
Selected AbstractsVisual Quantitative Estimation: Semiquantitative Wall Motion Scoring and Determination of Ejection FractionECHOCARDIOGRAPHY, Issue 5 2003M.D., Steven J. Lavine Ejection fraction (EF) is the most commonly used parameter of left ventricular (LV) systolic function and can be assessed by echocardiography. Quantitative echocardiography is time consuming and is as accurate as visual estimation, which has significant variability. We hypothesized that each echocardiographer has developed a mental set of guidelines that relate to how much individual segment shortening constitutes normal function or hypokinesis of varying extents. We determined the accuracy of applying these guidelines to an accepted technique of EF determination using a retrospective analysis of consecutive two-dimensional echocardiographic studies performed on patients who had radioventriculography (RVG) within 48 hours. Using a 12 segment model, we scored each segment at the base and mid-ventricular level based on segmental excursion and thickening. The apex was scored similarly but with 1/3 of the value based on a cylinder-cone model. EF was determined from the sum of segment scores and was estimated visually. We termed this approach visual quantitative estimation (VQE). We correlated the EF derived from VQE and visual estimation with RVG EF. In the training set, VQE demonstrated a strong correlation with RVG(r = 0.969), which was significantly greater than visual estimation(r = 0.896, P < 0.01). The limits of agreement for VQE (+12% to ,7%) were similar to the limits of RVG agreement with contrast ventriculography (+10% to ,11%) with similar intraobserver and interobserver variabilities. Similar correlation was noted in the prediction set between VQE and RVG EF(r = 0.967, P < 0.001). We conclude that VQE provides highly correlated estimates of EF with RVG. (ECHOCARDIOGRAPHY, Volume 20, July 2003) [source] Solvent effects on kinetics of an aromatic nucleophilic substitution reaction in mixtures of an ionic liquid with molecular solvents and prediction using artificial neural networksINTERNATIONAL JOURNAL OF CHEMICAL KINETICS, Issue 3 2009Aziz Habibi-Yangjeh Kinetics of the reaction between 1-chloro-2,4-dinitrobenzene and aniline was studied in mixtures of 1-ethyl-3-methylimidazolium ethylsulfate ([EMIM][EtSO4]) with methanol, chloroform, and dimethylsulfoxide at 25°C. Single-parameter correlations of log kA versus normalized polarity parameter (ENT), hydrogen-bond acceptor basicity (,), hydrogen-bond donor acidity (,), and dipolarity/polarizability (,*) of media do not give acceptable results. Multiparameter linear regression (MLR) of log kA versus the solvatochromic parameters demonstrates that the reaction rate constant increases with ENT, ,*, and , and decreases with , parameter. To predict accurately solvent effects on the rate constant, optimized artificial neural network with three inputs (including ,, ,*, and , parameters) was applied for prediction of the log kA values in the prediction set. It was found that properly selected and trained neural network could fairly represent the dependence of the reaction rate constant on solvatochromic parameters. Mean percent deviation of 5.023 for the prediction set by the MLR model should be compared with the value of 0.343 by the artificial neural network model. These improvements are due to the fact that the reaction rate constant shows nonlinear correlations with the solvatochromic parameters. © 2008 Wiley Periodicals, Inc. Int J Chem Kinet 41: 153,159, 2009 [source] Stacked partial least squares regression analysis for spectral calibration and predictionJOURNAL OF CHEMOMETRICS, Issue 10 2009Wangdong Ni Abstract Two novel algorithms which employ the idea of stacked generalization or stacked regression, stacked partial least squares (SPLS) and stacked moving-window partial least squares (SMWPLS) are reported in the present paper. The new algorithms establish parallel, conventional PLS models based on all intervals of a set of spectra to take advantage of the information from the whole spectrum by incorporating parallel models in a way to emphasize intervals highly related to the target property. It is theoretically and experimentally illustrated that the predictive ability of these two stacked methods combining all subsets or intervals of the whole spectrum is never poorer than that of a PLS model based only on the best interval. These two stacking algorithms generate more parsimonious regression models with better predictive power than conventional PLS, and perform best when the spectral information is neither isolated to a single, small region, nor spread uniformly over the response. A simulation data set is employed in this work not only to demonstrate this improvement, but also to demonstrate that stacked regressions have the potential capability of predicting property information from an outlier spectrum in the prediction set. Moisture, oil, protein and starch in Cargill corn samples have been successfully predicted by these new algorithms, as well as hydroxyl number for different instruments of terpolymer samples including and excluding an outlier spectrum. Copyright © 2009 John Wiley & Sons, Ltd. [source] Artemisinin Derivatives with Antimalarial Activity against Plasmodium falciparum Designed with the Aid of Quantum Chemical and Partial Least Squares MethodsMOLECULAR INFORMATICS, Issue 8 2003Abstract Artemisinin derivatives with antimalarial activity against Plasmodium falciparum resistant to mefloquine are designed with the aid of Quantum Chemical and Partial Least Squares Methods. The PLS model with three principal components explaining 89.55% of total variance, Q2=0.83 and R2=0.92 was obtained for 14/5 molecules in the training/external validation set. The most important descriptors for the design of the model were one level above the lowest unoccupied molecular orbital energy (LUMO+1), atomic charges in atoms C9 and C11 (Q9) and (Q11) respectively, the maximum number of hydrogen atoms that might make contact with heme (NH) and RDF030,m (a radial distribution function centered at 3.0,Å interatomic distance and weighted by atomic masses). From a set of ten proposed artemisinin derivatives, a new compound (26), was predicted with antimalarial activity higher than the compounds reported in literature. Molecular graphics and modeling supported the PLS results and revealed heme-ligand and protein-ligand stereoelectronic relationships as important for antimalarial activity. The most active 26 and 29 in the prediction set possess substituents at C9 able to extend to hemoglobin exterior, what determines the high activity of these compounds. [source] Quantitative Structure,Activity Relationship Models for Predicting Biological Properties, Developed by Combining Structure- and Ligand-Based Approaches: An Application to the Human Ether-a-go-go-Related Gene Potassium Channel InhibitionCHEMICAL BIOLOGY & DRUG DESIGN, Issue 4 2009Alessio Coi A strategy for developing accurate quantitative structure,activity relationship models enabling predictions of biological properties, when suitable knowledge concerning both ligands and biological target is available, was tested on a data set where molecules are characterized by high structural diversity. Such a strategy was applied to human ether-a-go-go-related gene K+ channel inhibition and consists of a combination of ligand- and structure-based approaches, which can be carried out whenever the three-dimensional structure of the target macromolecule is known or may be modeled with good accuracy. Molecular conformations of ligands were obtained by means of molecular docking, performed in a previously built theoretical model of the channel pore, so that descriptors depending upon the three-dimensional molecular structure were properly computed. A modification of the directed sphere-exclusion algorithm was developed and exploited to properly splitting the whole dataset into Training/Test set pairs. Molecular descriptors, computed by means of the codessa program, were used for the search of reliable quantitative structure,activity relationship models that were subsequently identified through a rigorous validation analysis. Finally, pIC50 values of a prediction set, external to the initial dataset, were predicted and the results confirmed the high predictive power of the model within a quite wide chemical space. [source] Application of PC-ANN to Acidity Constant Prediction of Various Phenols and Benzoic Acids in WaterCHINESE JOURNAL OF CHEMISTRY, Issue 5 2008Aziz HABIBI-YANGJEH Abstract Principal component regression (PCR) and principal component-artificial neural network (PC-ANN) models were applied to prediction of the acidity constant for various benzoic acids and phenols (242 compounds) in water at 25 °C. A large number of theoretical descriptors were calculated for each molecule. The first fifty principal components (PC) were found to explain more than 95% of variances in the original data matrix. From the pool of these PC's, the eigenvalue ranking method was employed to select the best set of PC for PCR and PC-ANN models. The PC-ANN model with architecture 47-20-1 was generated using 47 principal components as inputs and its output is pKa. For evaluation of the predictive power of the PCR and PC-ANN models, pKa values of 37 compounds in the prediction set were calculated. Mean percentage deviation (MPD) for PCR and PC-ANN models are 18.45 and 0.6448, respectively. These improvements are due to the fact that the pKa of the compounds demonstrate non-linear correlations with the principal components. Comparison of the results obtained by the models reveals superiority of the PC-ANN model relative to the PCR model. [source] | ||||||||||