scholarly journals Exploring differential evolution for inverse QSAR analysis

F1000Research ◽  
2017 ◽  
Vol 6 ◽  
pp. 1285 ◽  
Author(s):  
Tomoyuki Miyao ◽  
Kimito Funatsu ◽  
Jürgen Bajorath
Keyword(s):  
Differential Evolution ◽  
High Activity ◽  
Feature Space ◽  
Qsar Model ◽  
Quantitative Structure Activity Relationship ◽  
Support Vector ◽  
Qsar Modeling ◽  
Activity Data ◽  
Structure Generation ◽  
Qsar Analysis

Inverse quantitative structure-activity relationship (QSAR) modeling encompasses the generation of compound structures from values of descriptors corresponding to high activity predicted with a given QSAR model. Structure generation proceeds from descriptor coordinates optimized for activity prediction. Herein, we concentrate on the first phase of the inverse QSAR process and introduce a new methodology for coordinate optimization, termed differential evolution (DE), that originated from computer science and engineering. Using simulation and compound activity data, we demonstrate that DE in combination with support vector regression (SVR) yields effective and robust predictions of optimized coordinates satisfying model constraints and requirements. For different compound activity classes, optimized coordinates are obtained that exclusively map to regions of high activity in feature space, represent novel positions for structure generation, and are chemically meaningful.

scholarly journals Exploring differential evolution for inverse QSAR analysis

F1000Research ◽  
2017 ◽  
Vol 6 ◽  
pp. 1285 ◽  
Author(s):  
Tomoyuki Miyao ◽  
Kimito Funatsu ◽  
Jürgen Bajorath
Keyword(s):  
Differential Evolution ◽  
High Activity ◽  
Feature Space ◽  
Qsar Model ◽  
Quantitative Structure Activity Relationship ◽  
Support Vector ◽  
Qsar Modeling ◽  
Activity Data ◽  
Structure Generation ◽  
Qsar Analysis

Inverse quantitative structure-activity relationship (QSAR) modeling encompasses the generation of compound structures from values of descriptors corresponding to high activity predicted with a given QSAR model. Structure generation proceeds from descriptor coordinates optimized for activity prediction. Herein, we concentrate on the first phase of the inverse QSAR process and introduce a new methodology for coordinate optimization, termed differential evolution (DE), that originated from computer science and engineering. Using simulation and compound activity data, we demonstrate that DE in combination with support vector regression (SVR) yields effective and robust predictions of optimized coordinates satisfying model constraints and requirements. For different compound activity classes, optimized coordinates are obtained that exclusively map to regions of high activity in feature space, represent novel positions for structure generation, and are chemically meaningful.

scholarly journals A QSAR Modeling on Aurone Derivatives as Antimalarial Agents

2020 ◽  
Vol 32 (11) ◽  
pp. 2839-2845
Author(s):  
R. Hadanau
Keyword(s):  
Qsar Model ◽  
Quantitative Structure Activity Relationship ◽  
Multilinear Regression ◽  
Qsar Modeling ◽  
Qsar Analysis ◽  
Antimalarial Agents ◽  
Inhibition Concentration ◽  
Qsar Models ◽  
Semi Empirical ◽  
Statistical Criteria

A quantitative structure activity relationship (QSAR) analysis was performed on several compound and aurone derivatives (1-16) and 17-21 compounds were used as internal and external tests, respectively. Studies have investigated aurone derivatives; however, for aurone compounds, QSAR analysis has not been conducted. The semi-empirical PM3 method of HyperChem for Windows 8.0 was used to optimise the aurone derivative structures to acquire descriptors. For 15 influential descriptors, the multilinear regression MLR analysis was conducted by employing the backward method, and four new QSAR models were obtained. According to statistical criteria, model 2 was the optimum QSAR model for predicting the inhibition concentration (IC50) theoretical value against novel aurone derivatives. The modelling of 40 (22-61) aurone compounds was achieved. Six novel compounds (54, 55, 58, 59, 60, and 61) were synthesized in a laboratory because the IC50 of these compounds was lower than that of chloroquine (IC50 = 0.14 μM).

scholarly journals QUANTITATIVE STRUCTURE-ACTIVITY RELATIONSHIP ANALYSIS (QSAR) OF VINCADIFFORMINE ANALOGUES AS THE ANTIPLASMODIAL COMPOUNDS OF THE CHLOROQUINOSENSIBLE STRAIN

2010 ◽  
Vol 5 (3) ◽  
pp. 255-260
Author(s):  
Iqmal Tahir ◽  
Mudasir Mudasir ◽  
Irza Yulistia ◽  
Mustofa Mustofa
Keyword(s):  
Molecular Orbital ◽  
Qsar Model ◽  
Quantitative Structure Activity Relationship ◽  
Structure Activity Relationship ◽  
Activity Relationship ◽  
Quantitative Structure ◽  
Activity Data ◽  
Qsar Analysis ◽  
Relationship Analysis ◽  
Structure Activity

Quantitative Structure-Activity Relationship (QSAR) analysis of vincadifformine analogs as an antimalarial drug has been conducted using atomic net charges (q), moment dipole (), LUMO (Lowest Unoccupied Molecular Orbital) and HOMO (Highest Occupied Molecular Orbital) energies, molecular mass (m) as well as surface area (A) as the predictors to their activity. Data of predictors are obtained from computational chemistry method using semi-empirical molecular orbital AM1 calculation. Antimalarial activities were taken as the activity of the drugs against chloroquine-sensitive Plasmodium falciparum (Nigerian Cell) strain and were presented as the value of ln(1/IC50) where IC50 is an effective concentration inhibiting 50% of the parasite growth. The best QSAR model has been determined by multiple linier regression analysis giving QSAR equation: Log (1/IC50) = 9.602.qC1 -17.012.qC2 +6.084.qC3 -19.758.qC5 -6.517.qC6 +2.746.qC7 -6.795.qN +6.59.qC8 -0.190. -0.974.ELUMO +0.515.EHOMO -0.274. +0.029.A -1.673 (n = 16; r = 0.995; SD = 0.099; F = 2.682)   Keywords: QSAR analysis, antimalaria, vincadifformine.  

scholarly journals Identification of Anti-SARS-CoV-2 Compounds from Food Using QSAR-Based Virtual Screening, Molecular Docking, and Molecular Dynamics Simulation Analysis

2021 ◽  
Vol 14 (4) ◽  
pp. 357
Author(s):  
Magdi E. A. Zaki ◽  
Sami A. Al-Hussain ◽  
Vijay H. Masand ◽  
Siddhartha Akasapu ◽  
Sumit O. Bajaj ◽  
...  
Keyword(s):  
Molecular Dynamics ◽  
Molecular Docking ◽  
Virtual Screening ◽  
Simulation Analysis ◽  
Qsar Model ◽  
Quantitative Structure Activity Relationship ◽  
Dynamics Simulation ◽  
Multilinear Regression ◽  
Qsar Analysis ◽  
Main Protease

Due to the genetic similarity between SARS-CoV-2 and SARS-CoV, the present work endeavored to derive a balanced Quantitative Structure−Activity Relationship (QSAR) model, molecular docking, and molecular dynamics (MD) simulation studies to identify novel molecules having inhibitory potential against the main protease (Mpro) of SARS-CoV-2. The QSAR analysis developed on multivariate GA–MLR (Genetic Algorithm–Multilinear Regression) model with acceptable statistical performance (R2 = 0.898, Q2loo = 0.859, etc.). QSAR analysis attributed the good correlation with different types of atoms like non-ring Carbons and Nitrogens, amide Nitrogen, sp2-hybridized Carbons, etc. Thus, the QSAR model has a good balance of qualitative and quantitative requirements (balanced QSAR model) and satisfies the Organisation for Economic Co-operation and Development (OECD) guidelines. After that, a QSAR-based virtual screening of 26,467 food compounds and 360 heterocyclic variants of molecule 1 (benzotriazole–indole hybrid molecule) helped to identify promising hits. Furthermore, the molecular docking and molecular dynamics (MD) simulations of Mpro with molecule 1 recognized the structural motifs with significant stability. Molecular docking and QSAR provided consensus and complementary results. The validated analyses are capable of optimizing a drug/lead candidate for better inhibitory activity against the main protease of SARS-CoV-2.

scholarly journals Development of a Hierarchical Support Vector Regression-Based In Silico Model for Caco-2 Permeability

Pharmaceutics ◽  
2021 ◽  
Vol 13 (2) ◽  
pp. 174 ◽  
Author(s):  
Giang Huong Ta ◽  
Cin-Syong Jhang ◽  
Ching-Feng Weng ◽  
Max K. Leong
Keyword(s):  
Drug Discovery ◽  
Support Vector Regression ◽  
Human Colon ◽  
Qsar Model ◽  
Quantitative Structure Activity Relationship ◽  
Support Vector ◽  
Human Colon Carcinoma Cell ◽  
Drug Discovery And Development ◽  
Training Samples ◽  
Experimental Values

Drug absorption is one of the critical factors that should be taken into account in the process of drug discovery and development. The human colon carcinoma cell layer (Caco-2) model has been frequently used as a surrogate to preliminarily investigate the intestinal absorption. In this study, a quantitative structure–activity relationship (QSAR) model was generated using the innovative machine learning-based hierarchical support vector regression (HSVR) scheme to depict the exceedingly confounding passive diffusion and transporter-mediated active transport. The HSVR model displayed good agreement with the experimental values of the training samples, test samples, and outlier samples. The predictivity of HSVR was further validated by a mock test and verified by various stringent statistical criteria. Consequently, this HSVR model can be employed to forecast the Caco-2 permeability to assist drug discovery and development.

Study on Anti-Tumor Activity of Novel 3-Substituted 4 Anilino-Coumarin Derivatives Using Quantitative Structure-Activity Relationship (QSAR)

2019 ◽  
Vol 948 ◽  
pp. 101-108 ◽  
Author(s):  
Daratu E.K. Putri ◽  
Harno Dwi Pranowo ◽  
Winarto Haryadi
Keyword(s):  
Quantitative Structure Activity Relationship ◽  
Structure Activity Relationship ◽  
Activity Relationship ◽  
Linear Regression Method ◽  
Coumarin Derivatives ◽  
Quantitative Structure ◽  
Activity Data ◽  
Qsar Analysis ◽  
Structure Activity ◽  
Anti Tumor Activity

Study on anti breast cancer activity of 3-substituted 4-anilino coumarin derivatives by using quantitative structure-activity relationship (QSAR) has been performed. The structures and the activity data were literatured from Guoshun et al. experiment. The molecular and electronic molecule properties were obtained from DFT/BPV86 6-31G method calculation after was through methods validation. The QSAR analysis were shown by Multi Linear Regression method (MLR). The best model of obtained for 3-substituted 4-anilino coumarin derivatives is: Log IC50 = 5.905 + (0.936 x qC1) + (-8.225 x qC8) + (-0.582 x qC13) + (11.273 x qC15) + (0.869 x ∆E) ; n = 26; r2= 0.704; Fcal/Ftab = 2.462; SEE = 0.184.

scholarly journals 2D-QSAR Study of Indolylpyrimidines Derivative as Antibacterial against Pseudomonas aeruginosa and Staphylococcus aureus: A Comparative Approach

2014 ◽  
Vol 2014 ◽  
pp. 1-9 ◽  
Author(s):  
Prasanna A. Datar
Keyword(s):  
Staphylococcus Aureus ◽  
Pseudomonas Aeruginosa ◽  
Qsar Model ◽  
Antibacterial Activities ◽  
Quantitative Structure Activity Relationship ◽  
Comparative Approach ◽  
Qsar Study ◽  
Qsar Analysis ◽  
Leave One Out ◽  
And Staphylococcus Aureus

A set of 15 indolylpyrimidine derivatives with their antibacterial activities in terms of minimum inhibitory concentration against the gram-negative bacteria Pseudomonas aeruginosa and gram-positive Staphylococcus aureus were selected for 2D quantitative structure activity relationship (QSAR) analysis. QSAR was performed using a combination of various descriptors such as steric, electronic and topological. Stepwise regression method was used to derive the most significant QSAR equation for predicting the inhibitory activity of this class of molecules. The best QSAR model was further validated by a leave one out technique as well as by the random trials. A high correlation between experimental and predicted inhibitory values was observed. A comparative picture of behavior of indolylpyrimidines against both of the microorganisms is discussed.

scholarly journals Mechanistic and Predictive QSAR Analysis of Diverse Molecules to Capture Salient and Hidden Pharmacophores for Anti-Thrombotic Activity

2021 ◽  
Vol 22 (15) ◽  
pp. 8352
Author(s):  
Magdi E. A. Zaki ◽  
Sami A. Al-Hussain ◽  
Vijay H. Masand ◽  
Manoj K. Sabnani ◽  
Abdul Samad
Keyword(s):  
External Validation ◽  
Factor Xa ◽  
Predictive Ability ◽  
Qsar Model ◽  
Quantitative Structure Activity Relationship ◽  
Data Set ◽  
Qsar Analysis ◽  
Lead Compounds ◽  
Charged Ring ◽  
Life Threatening

Thrombosis is a life-threatening disease with a high mortality rate in many countries. Even though anti-thrombotic drugs are available, their serious side effects compel the search for safer drugs. In search of a safer anti-thrombotic drug, Quantitative Structure-Activity Relationship (QSAR) could be useful to identify crucial pharmacophoric features. The present work is based on a larger data set comprising 1121 diverse compounds to develop a QSAR model having a balance of acceptable predictive ability (Predictive QSAR) and mechanistic interpretation (Mechanistic QSAR). The developed six parametric model fulfils the recommended values for internal and external validation along with Y-randomization parameters such as R2tr = 0.831, Q2LMO = 0.828, R2ex = 0.783. The present analysis reveals that anti-thrombotic activity is found to be correlated with concealed structural traits such as positively charged ring carbon atoms, specific combination of aromatic Nitrogen and sp2-hybridized carbon atoms, etc. Thus, the model captured reported as well as novel pharmacophoric features. The results of QSAR analysis are further vindicated by reported crystal structures of compounds with factor Xa. The analysis led to the identification of useful novel pharmacophoric features, which could be used for future optimization of lead compounds.

scholarly journals QSAR Analysis of 5-Substituted-2-Benzoyl-aminobenzoic acids as PPAR Modulator

2004 ◽  
Vol 1 (5) ◽  
pp. 243-250 ◽  
Author(s):  
R. Hemalatha ◽  
L. K. Soni ◽  
A. K. Gupta ◽  
S. G. Kaskhedikar
Keyword(s):  
Linear Regression Analysis ◽  
Qsar Model ◽  
Multiple Linear Regression Analysis ◽  
Quantitative Structure Activity Relationship ◽  
Statistical Regression ◽  
Qsar Study ◽  
Qsar Analysis ◽  
Aminobenzoic Acids ◽  
Leave One Out ◽  
Α Activity

A quantitative structure activity relationship (QSAR) study on a series of analogs of 5-aryl thiazolidine-2, 4-diones with activity on PPAR-α and PPAR-γwas made using combination of various thermodynamic, electronic and spatial descriptors. Several statistical regression expressions were obtained using multiple linear regression analysis. The best QSAR model was further validated by leave one out cross validation method. The studied revealed that for dual PPAR-α/γactivity dipole-dipole energy and PMI-Z play significant role and contributed positively for PPAR-γand PPAR-α activity respectively. Thus, QSAR brings important structural insight to aid the design of dual PPAR-α /γreceptor agonist.

scholarly journals QSAR modeling of antibacterial activity of some benzimidazole derivatives

2011 ◽  
Vol 17 (1) ◽  
pp. 33-38 ◽  
Author(s):  
Sanja Podunavac-Kuzmanovic ◽  
Dragoljub Cvetkovic
Keyword(s):  
Antibacterial Activity ◽  
Qsar Model ◽  
Quantitative Structure Activity Relationship ◽  
Structural Features ◽  
Benzimidazole Derivatives ◽  
Qsar Modeling ◽  
Qsar Study ◽  
Validation Procedure ◽  
Leave One Out

A quantitative structure-activity relationship (QSAR) study has been carried out for training set of 12 benzimidazole derivatives to correlate and predict the antibacterial activity of studied compounds against Gram-negative bacteria Pseudomonas aeruginosa. Multiple linear regression was used to select the descriptors and to generate the best prediction model that relates the structural features to inhibitory activity. The predictivity of the model was estimated by cross-validation with the leave-one-out method. Our results suggest a QSAR model based on the following descriptors: parameter of lipophilicity (logP) and hydration energy (HE). Good agreement between experimental and predicted inhibitory values, obtained in the validation procedure, indicated the good quality of the generated QSAR model.

Sign in / Sign up

Export Citation Format

Share Document