Application of PC-ANN and PC-LS-SVM in QSAR of CCR1 antagonist compounds: A comparative study

Shahlaei, Mohsen; Fassihi, Afshin; Saghaie, Lotfollah

doi:10.1016/j.ejmech.2009.12.066

Cited by 47 publications

(23 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Artificial neural networks (ANNs), as a non-linear regression approach, has been widely used to investigate and solve various problems in various branches of science including QSAR [15,16]. ANNs can learn the complex relationships between given inputs and outputs, serving as a useful tool for constructing regression and classification, signal processing, and optimization models.…”

Section: Introductionmentioning

confidence: 99%

Application of partial least squares and radial basis function neural networks in multivariate imaging analysis-quantitative structure activity relationship: Study of cyclin dependent kinase 4 inhibitors

Saghaie

Shahlaei

Madadkar-Sobhani

et al. 2010

Journal of Molecular Graphics and Modelling

Self Cite

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Application of partial least squares and radial basis function neural networks in multivariate imaging analysis-quantitative structure activity relationship: Study of cyclin dependent kinase 4 inhibitors

Saghaie

Shahlaei

Madadkar-Sobhani

et al. 2010

Journal of Molecular Graphics and Modelling

Self Cite

View full text Add to dashboard Cite

“…If a linear model is assumed, some conventional statistical methods, such as the partial least squares method and multiple linear regression [16] can be used. If a nonlinear model is preferred on the other hand, machine learning methods like artificial neural networks [52] or support vector machines [53] can be applied.…”

Section: Qsarmentioning

confidence: 99%

Reviewing Ligand-Based Rational Drug Design: The Search for an ATP Synthase Inhibitor

Lee

Huang²,

Juan

2011

IJMS

View full text Add to dashboard Cite

Following major advances in the field of medicinal chemistry, novel drugs can now be designed systematically, instead of relying on old trial and error approaches. Current drug design strategies can be classified as being either ligand- or structure-based depending on the design process. In this paper, by describing the search for an ATP synthase inhibitor, we review two frequently used approaches in ligand-based drug design: The pharmacophore model and the quantitative structure-activity relationship (QSAR) method. Moreover, since ATP synthase ligands are potentially useful drugs in cancer therapy, pharmacophore models were constructed to pave the way for novel inhibitor designs.

show abstract

“…Compared with traditional neural networks, support vector machine algorithm can be converted to a quadratic optimization problem, in theory, will get a global optimum. LS-SVM with equality constraints instead of the traditional SVM inequality constraints, thus avoiding the solution is calculated fairly heavy squares programming problems; effectively improve the solution speed, so as the simple structure, fast calculation, but it is also to some extent the loss of SVM lose and robustness [5][6][7] . Based on the characteristics of scrap copper smelting process, select the appropriate input variables, using the weighted least squares support vector machine algorithm to each sample squared error given different weights for the customer impact of a training sample in order to establish a high predictive accuracy , anti-interference ability of scrap copper smelting process temperature dynamic models.…”

Section: Introductionmentioning

confidence: 99%

Dynamic model of liquid copper temperature based on weighted LS-SVM

Guan

et al. 2013

SPIE Proceedings

View full text Add to dashboard Cite

Aimed to the difficult temperature measurement of scrap copper smelting process, this paper proposed a method of dynamic prediction method of furnace temperature based on weighted least squares support vector machine (WLS-SVM).In this method, the main input and output variables of the process squared error is given different weights to overcome the impact of the training sample anomalies, and use PSO for WLS-SVM parameters optimization, enhanced ability to adapt of dynamic model for the nonlinear time-varying characteristics, improved the prediction accuracy of the model.Finally, simulated through actual operating data of scrap copper smelting process, and verified the effectiveness of the method.

show abstract

Application of PC-ANN and PC-LS-SVM in QSAR of CCR1 antagonist compounds: A comparative study

Cited by 47 publications

References 45 publications

Application of partial least squares and radial basis function neural networks in multivariate imaging analysis-quantitative structure activity relationship: Study of cyclin dependent kinase 4 inhibitors

Application of partial least squares and radial basis function neural networks in multivariate imaging analysis-quantitative structure activity relationship: Study of cyclin dependent kinase 4 inhibitors

Reviewing Ligand-Based Rational Drug Design: The Search for an ATP Synthase Inhibitor

Dynamic model of liquid copper temperature based on weighted LS-SVM

Contact Info

Product

Resources

About