2009
DOI: 10.1016/j.chroma.2009.04.064
|View full text |Cite
|
Sign up to set email alerts
|

Evaluating the performances of quantitative structure-retention relationship models with different sets of molecular descriptors and databases for high-performance liquid chromatography predictions

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
7
0

Year Published

2011
2011
2021
2021

Publication Types

Select...
7
1

Relationship

0
8

Authors

Journals

citations
Cited by 24 publications
(7 citation statements)
references
References 52 publications
0
7
0
Order By: Relevance
“…PLS is a regression technique that works with two matrices, X (independent variables) and Y (dependent variables), and has two objectives to well approximate X and Y and to model the relationship between them . This methodology has advantages over MLR because it works with intercorrelated variables . The relation between the chemical descriptors and the dependent data is described as a linear model in the space described by the latent variables .…”
Section: Methodsmentioning
confidence: 99%
“…PLS is a regression technique that works with two matrices, X (independent variables) and Y (dependent variables), and has two objectives to well approximate X and Y and to model the relationship between them . This methodology has advantages over MLR because it works with intercorrelated variables . The relation between the chemical descriptors and the dependent data is described as a linear model in the space described by the latent variables .…”
Section: Methodsmentioning
confidence: 99%
“…[14,15] However, owing to the frequently poor predictive ability of QSRRs, use is often made of the insertion of strategies to improve accuracy, such as molecular descriptor optimisers, feature selection tools, and training subset selectors. [16][17][18][19] Previous studies from our group have shown the very significant advantages gained by careful selection of the set of compounds used to train the QSRR. [7,8,[20][21][22][23] In particular, we have shown that filtering a database of compounds with known molecular descriptors and known retention times to identify a subset of the most relevant training compounds can greatly improve prediction accuracy.…”
Section: Introductionmentioning
confidence: 99%
“…The linear solvation energy relationship (LSER) theory is most suitable for investigating these models because it allows one to compare various sorbents [2][3][4]. Many-parameter correlation models are currently widely used; they allow the prediction of the retention characteristics of the compounds synthesized for the first time under the conditions of HPLC [5][6][7][8][9][10][11][12][13][14][15][16]. The use of manyparameter correlation equations also allows the prediction of the physicochemical parameters (descriptors) of molecules and the potential biological activity of compounds [17].…”
Section: Introductionmentioning
confidence: 99%