Improvement of Multivariate Image Analysis Applied to Quantitative Structure-Activity Relationship (QSAR) Analysis by Using Wavelet-Principal Component Analysis Ranking Variable Selection and Least-Squares Support Vector Machine Regression: QSAR Study of Checkpoint Kinase WEE1 Inhibitors

2009 ◽  
Vol 73 (2) ◽  
pp. 244-252 ◽  
Author(s):  
Rodrigo A. Cormanich ◽  
Mohammad Goodarzi ◽  
Matheus P. Freitas
Keyword(s):  
Principal Component Analysis ◽  
Support Vector Machine ◽  
Principal Component ◽  
Quantitative Structure Activity Relationship ◽  
Support Vector ◽  
Quantitative Structure ◽  
Qsar Study ◽  
Qsar Analysis ◽  
Structure Activity ◽  
Multivariate Image

Prediction of Lipophilicity of some Quinolone Derivatives by using Quantitative Structure- Activity Relationship

2019 ◽  
Vol 16 ◽  
Author(s):  
Meysam Shirmohammadi ◽  
Zakiyeh Bayat ◽  
Esmat Mohammadinasab
Keyword(s):  
Partition Coefficient ◽  
Principal Component ◽  
Quantitative Structure Activity Relationship ◽  
Structure Activity Relationship ◽  
Activity Relationship ◽  
Quantitative Structure ◽  
Selection Methods ◽  
Qsar Study ◽  
Structure Activity ◽  
Descriptor Selection

: Quantitative structure activity relationship (QSAR) was used to study the partition coefficient of some quinolones and their derivatives. These molecules are broad-spectrum antibiotic pharmaceutics. First, data were divided into two categories of train and test (validation) sets using random selection method. Second, three approaches including stepwise selection (STS) (forward), genetic algorithm (GA), and simulated annealing (SA) were used to select the descriptors, with the aim of examining the effect feature selection methods. To find the relation between descriptors and partition coefficient, multiple linear regression (MLR), principal component regression (PCR) and partial least squares (PLS) were used. QSAR study showed that the both regression and descriptor selection methods have vital role in the results. Different statistical metrics showed that the MLR-SA approach with (r2=0.96, q2=0.91, pred_r2=0.95) gives the best outcome. The proposed expression by MLR-SA approach can be used in the better design of novel quinolones and their derivatives.

Quantum chemical and molecular dynamics studies of imidazoline derivatives as corrosion inhibitor and quantitative structure–activity relationship (QSAR) analysis using the support vector machine (SVM) method

2014 ◽  
Vol 13 (02) ◽  
pp. 1450012 ◽  
Author(s):  
Lei Du ◽  
Hongxia Zhao ◽  
Haixiang Hu ◽  
Xiuhui Zhang ◽  
Lin Ji ◽  
...  
Keyword(s):  
Molecular Dynamics ◽  
Support Vector Machine ◽  
Quantum Chemical ◽  
Qsar Model ◽  
Quantitative Structure Activity Relationship ◽  
Activity Relationship ◽  
Support Vector ◽  
Quantitative Structure ◽  
Hydrophilic Group ◽  
Structure Activity

The inhibition performance of 10 imidazoline molecules with number of carbon from 15 to 21 of hydrocarbon straight-chain was studied by weight-loss method and theoretical approaches. The main purpose was to build a quantitative structure–activity relationship (QSAR) between the structural properties and the inhibition efficiencies, and then to predict efficiencies of new corrosion inhibitors. The quantum chemical calculation suggested that the active region of imidazoline molecules was located on the imidazoline ring and hydrophilic group, and active sites were concentrated on the nitrogen atoms of the molecules and carbon atoms of hydrophilic group. A model in accordance with the real experimental solution was built in the molecular dynamics, and the equilibrium configuration indicated that the imidazoline molecules were adsorbed on Fe (110) surface in parallel manner. Descriptors for QSAR model building were selected by principal component analysis (PCA) and the model was built by the support vector machine (SVM) approach, which shows good performance since the value of correlation coefficient (R) was 0.99 and the root mean square error (RMSE) was 0.94. Additionally, six new imidazoline molecules were theoretically designed and the inhibition efficiencies of three molecules were predicted to be more than 86% by the established QSAR model.

Sign in / Sign up

Export Citation Format

Share Document