Feature selection method based on fuzzy entropy for regression in QSAR studies

Elmi, Zahra; Faez, Karim; Goodarzi, Mohammad; Goudarzi, Nasser

doi:10.1080/00268970903078559

Cited by 30 publications

(8 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…QSAR models using different descriptors and modeling approaches for the target systems studied in the current work have been reported using the same datasets. Three studies for TS-1 (Elmi et al, 2009;Yi et al, 2008), one for TS-2 (Queiroz et al, 2011), two for TS-3 (Hu et al, 2009), and one each for TS-4 (Garg et al, 1999) and TS-5 (Debnath, 1999) were identified and studied for comparative performance with PMF-PLS QSAR. Note that for TS-6 no QSAR modeling study could be identified.…”

Section: Resultsmentioning

confidence: 99%

On the use of electronegativity and electron affinity based pseudo‐molecular field descriptors in developing correlations for quantitative structure‐activity relationship modeling of drug activities

et al. 2021

View full text Add to dashboard Cite

For quantitative structure-activity relationship (QSAR) modeling in ligand-based drug discovery programs, pseudo-molecular field (PMF) descriptors using intrinsic atomic properties, namely, electronegativity and electron affinity are studied. In combination with partial least squares analysis and Procrustes transformation, these PMF descriptors were employed successfully to develop correlations that predict the activities of target protein inhibitors involved in various diseases (cancer, neurodegenerative disorders, HIV, and malaria). The results show that the present QSAR approach is competitive to existing QSAR models. In order to demonstrate the use of this algorithm, we present results of screening naturally occurring molecules with unknown bioactivities. The pIC 50 predictions can screen molecules that have desirable activity before assessment by docking studies.

show abstract

Section: Resultsmentioning

confidence: 99%

On the use of electronegativity and electron affinity based pseudo‐molecular field descriptors in developing correlations for quantitative structure‐activity relationship modeling of drug activities

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In recent yeares, several QSAR and QSPR models have been used based on both linear and non-linear methods that aimed to predict different activities and properties [60][61][62][63][64][65][66][67][68][69][70][71] .…”

Section: Introductionmentioning

confidence: 99%

Quantitative Structure-Retention Index Relationship (QSRIR) Study of Monomethylalkanes on the Methylsilicone OV-1 Stationary Phase

Goudarzi¹,

Kalhor

2012

Analytical Chemistry Letters

Self Cite

View full text Add to dashboard Cite

A back-propagation artificial neural network (ANN) is used to create a model of gas chromatography retention indices for a data set of 196 monomethylalkanes on the methylsilicone OV-1 stationary phase. Multlinear regression (MLR) model of the same data is developed for comparison. The quantitative structure-property relationship (QSPR) models are validated by cross-validation as well as application of the models for prediction of retention indices of external set of compounds which do not have contribution to model development steps. The models are also validated by statistical parameters and Y-randomization. Both linear and non-linear methods provide accurate predictions. The mean-squared errors (MSE) for validation and test sets for MLR are 18.44 and 28.96, and those for ANN are 2.24 and 4.21, respectively.

show abstract

“…Machine learning and feature selection methods have been widely used in QSAR models . Levatić et al applied semisupervised learning in QSAR models.…”

Section: Introductionmentioning

confidence: 99%

Feature selection based on graph Laplacian by using compounds with known and unknown activities

Sheikhpour

Sarram

Gharaghani

et al. 2017

Journal of Chemometrics

View full text Add to dashboard Cite

A semisupervised feature selection method based on graph Laplacian (S 2 FSGL) was proposed for quantitative structure-activity relationship (QSAR) models, which uses an ℓ 2,1 -norm and compounds with both known and unknown activities. In the proposed S 2 FSGL method, 2 graphs G unsup and G sup are constructed. It uses the label information of compounds with known activities and the local structure of compounds with known and unknown activities to select the most important descriptors.The weight matrix of graph G unsup models the local structure of the compounds with known and unknown activities. The S 2 FSGL method uses the ℓ 2,1 -norm to consider the correlation between different descriptors when conducting descriptor selection.The performance of the proposed S 2 FSGL coupled with a kernel smoother model was evaluated using 2 QSAR data sets and compared with the performance of other feature selection methods. For the evaluation of the performance of QSAR models and selected descriptors, several different training and test sets were produced for each data set. The comparison between the statistical parameters of QSAR models built based on the semisupervised feature selection method and those obtained by other feature selection methods revealed the superiority of the proposed S 2 FSGL in selecting the most relevant descriptors. The results showed that the use of compounds with unknown activities beside compounds with known activities can be helpful in selecting the relevant descriptors of QSAR models.

show abstract

Feature selection method based on fuzzy entropy for regression in QSAR studies

Cited by 30 publications

References 33 publications

On the use of electronegativity and electron affinity based pseudo‐molecular field descriptors in developing correlations for quantitative structure‐activity relationship modeling of drug activities

On the use of electronegativity and electron affinity based pseudo‐molecular field descriptors in developing correlations for quantitative structure‐activity relationship modeling of drug activities

Quantitative Structure-Retention Index Relationship (QSRIR) Study of Monomethylalkanes on the Methylsilicone OV-1 Stationary Phase

Feature selection based on graph Laplacian by using compounds with known and unknown activities

Contact Info

Product

Resources

About