2010
DOI: 10.1016/j.ejmech.2010.02.055
|View full text |Cite
|
Sign up to set email alerts
|

QSAR analysis of diaryl COX-2 inhibitors: Comparison of feature selection and train-test data selection methods

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

1
29
0

Year Published

2012
2012
2017
2017

Publication Types

Select...
8

Relationship

1
7

Authors

Journals

citations
Cited by 33 publications
(30 citation statements)
references
References 12 publications
1
29
0
Order By: Relevance
“…Combining of PLS with GA provides the possibility of descriptor selection from a pool of collinear descriptors without over fitting problem which could be happen using PLS method . The GAPLS toolbox that was developed by Leardi for QSAR studies was applied using the MATLAB software for descriptor selection based on the Soltani et al (2010) procedure.…”
Section: Gapls Methodsmentioning
confidence: 99%
See 1 more Smart Citation
“…Combining of PLS with GA provides the possibility of descriptor selection from a pool of collinear descriptors without over fitting problem which could be happen using PLS method . The GAPLS toolbox that was developed by Leardi for QSAR studies was applied using the MATLAB software for descriptor selection based on the Soltani et al (2010) procedure.…”
Section: Gapls Methodsmentioning
confidence: 99%
“…We must have methods for detecting and assessing outliers in QSAR studies. There are different methods for outlier detection in which the scoring method is one of the most frequently applied methods (Soltani et al, 2010). The Y-outlier is employed in this study for detecting the different target variables.…”
Section: Recognition Of Outliermentioning
confidence: 99%
“…38,[55][56][57] Their success, to a great degree, is dependent on proper characterizations of the molecular structure and selection of the structural descriptors. A total of 1785 molecular descriptors, including functional group counts, 2D autocorrelations, information indices, GETAWAY descriptors, 3D-MoRSE descriptors, RDF descriptors, topological indices, WHIM descriptors, etc.…”
Section: Methodsmentioning
confidence: 99%
“…The principal components (PCs) as a new set of variables (mutually orthogonal) were obtained by this method. The first PC contains the largest variance and the second PC contains the second largest variance [26]. The variable selection in PCA was performed using the Fisher's weights approach and the results are summarized as the following Eqs.…”
Section: Ache-qsarmentioning
confidence: 99%