Predicting the biological activities of triazole derivatives as SGLT2 inhibitors using multilayer perceptron neural network, support vector machine, and projection pursuit regression models

Abstract Quantitative structure–activity relationship (QSAR) studies were performed in this work to predict the pIC50 of non-glycoside sodium-dependent glucose cotransporter-2 (SGLT2) inhibitors (46 triazole derivatives). Four descriptors were selected from the pool of DRAGON descriptors using the enhanced replacement method. Three nonlinear regression methods—multilayer perceptron neural network (MLP NN), support vector machine (SVM), and projection pursuit regression (PPR)—were then used to build the QSAR models. The performance of the obtained models was assessed through the cross-validation and external validation of the test set. PPR produced a better model than MLP NN and SVM with coefficients of determination of 0.962 and 0.871 and root mean square errors of 0.162 and 0.471 for the training and test sets, respectively. This study developed simple and efficient approaches to predict the pIC50 of triazole derivatives and provided some insights into their structural features for the development of more potential SGLT2 inhibitors.

[1]  Mario Roberto Senger,et al.  1-Phenyl-1H- and 2-phenyl-2H-1,2,3-triazol derivatives: design, synthesis and inhibitory effect on alpha-glycosidases. , 2014, European journal of medicinal chemistry.

[2]  Ralph A. DeFronzo,et al.  Why Do SGLT2 Inhibitors Inhibit Only 30–50% of Renal Glucose Reabsorption in Humans? , 2012, Diabetes.

[3]  K. P. Singh,et al.  Support vector machines in water quality management. , 2011, Analytica chimica acta.

[4]  Richard Donnelly,et al.  Sodium–glucose co‐transporter‐2 inhibitors: an emerging new class of oral antidiabetic drug , 2009, Diabetes, obesity & metabolism.

[5]  Patrick Höhener,et al.  Predicting equilibrium vapour pressure isotope effects by using artificial neural networks or multi-linear regression - A quantitative structure property relationship approach. , 2015, Chemosphere.

[6]  Venkatesan Suryanarayanan,et al.  Atom-based 3D QSAR studies on novel N-β-d-xylosylindole derivatives as SGLT2 inhibitors , 2012, Medicinal Chemistry Research.

[7]  A K Madan,et al.  Models for H₃ receptor antagonist activity of sulfonylurea derivatives. , 2014, Journal of molecular graphics & modelling.

[8]  Paulo Cortez,et al.  Using sensitivity analysis and visualization techniques to open black box data mining models , 2013, Inf. Sci..

[9]  J. Torrecilla,et al.  Estimation of toxicity of ionic liquids in Leukemia Rat Cell Line and Acetylcholinesterase enzyme by principal component analysis, neural networks and multiple lineal regressions. , 2009, Journal of hazardous materials.

[10]  Zhide Hu,et al.  Prediction of fungicidal activities of rice blast disease based on least-squares support vector machines and project pursuit regression. , 2008, Journal of agricultural and food chemistry.

[11]  Pablo R. Duchowicz,et al.  pKa modeling and prediction of a series of pH indicators through genetic algorithm-least square support vector regression , 2010 .

[12]  Eduardo A. Castro,et al.  QSAR on aryl-piperazine derivatives with activity on malaria , 2012 .

[13]  Jian Zhang,et al.  Discovery of non-glucoside SGLT2 inhibitors. , 2011, Bioorganic & medicinal chemistry letters.

[14]  Taghi Khayamian,et al.  Interactions of G-quadruplex DNA binding site with berberine derivatives and construct a structure-based QSAR using docking descriptors , 2013, Medicinal Chemistry Research.

[15]  Roberto Todeschini,et al.  Molecular descriptors for chemoinformatics , 2009 .

[16]  S. Nair,et al.  Sodium glucose cotransporter 2 inhibitors as a new treatment for diabetes mellitus. , 2010, The Journal of clinical endocrinology and metabolism.

[17]  Lalitha Guruprasad,et al.  Structural Insights into the Active Site of Human Sodium Dependent Glucose Co-Transporter 2: Homology Modelling, Molecular Docking, and 3D-QSAR Studies , 2012 .

[18]  Guochao Liao,et al.  QSAR studies on triazole derivatives as sglt inhibitors via CoMFA and CoMSIA , 2015 .

[19]  Dong Yun,et al.  Data Mining for Seeking an Accurate Quantitative Relationship between Molecular Structure and GC Retention Indices of Alkenes by Projection Pursuit , 2002, J. Chem. Inf. Comput. Sci..

[20]  Mehdi Mehrpooya,et al.  Prediction of some important physical properties of sulfur compounds using quantitative structure–properties relationships , 2008, Molecular Diversity.

[21]  Ruisheng Zhang,et al.  Prediction of CCR5 receptor binding affinity of substituted 1-(3,3-diphenylpropyl)-piperidinyl amides and ureas based on the heuristic method, support vector machine and projection pursuit regression. , 2009, European journal of medicinal chemistry.

[22]  Marjana Novic,et al.  Quantitative structure-activity relationships (QSARs) using the novel marine algal toxicity data of phenols. , 2012, Journal of molecular graphics & modelling.

[23]  Rebekah K. Prasoona,et al.  Optimization of Gaussian Kernel Function in Support Vector Machine aided QSAR studies of C-aryl glucoside SGLT2 inhibitors , 2013, Interdisciplinary Sciences: Computational Life Sciences.

[24]  Eduardo A. Castro,et al.  Replacement Method and Enhanced Replacement Method Versus the Genetic Algorithm Approach for the Selection of Molecular Descriptors in QSPR/QSAR Theories , 2010, J. Chem. Inf. Model..

[25]  Paola Gramatica,et al.  Real External Predictivity of QSAR Models. Part 2. New Intercomparable Thresholds for Different Validation Criteria and the Need for Scatter Plot Inspection , 2012, J. Chem. Inf. Model..

[26]  Yun Ling,et al.  Optimization of triazoles as novel and potent nonphlorizin SGLT2 inhibitors. , 2011, Bioorganic & medicinal chemistry letters.

[27]  Rajarshi Guha,et al.  Utilizing high throughput screening data for predictive toxicology models: protocols and application to MLSCN assays , 2008, J. Comput. Aided Mol. Des..

[28]  Richard D. Gill,et al.  Octane number prediction based on gas chromatographic analysis with non-linear regression techniques , 1994 .

[29]  Xiaoyun Zhang,et al.  Prediction of inhibition of matrix metalloproteinase inhibitors based on the combination of Projection Pursuit Regression and Grid Search method , 2008 .

[30]  Apilak Worachartcheewan,et al.  QSAR modeling of aromatase inhibitory activity of 1-substituted 1,2,3-triazole analogs of letrozole. , 2013, European journal of medicinal chemistry.

[31]  Mancang Liu,et al.  Prediction of gas-phase reduced ion mobility constants (K(0)) based on the multiple linear regression and projection pursuit regression. , 2007, Talanta.

[32]  Eduardo A. Castro,et al.  Predictive QSAR study of chalcone derivatives cytotoxicity activity against HT-29 human colon adenocarcinoma cell lines , 2014 .

[33]  J. Friedman,et al.  Projection Pursuit Regression , 1981 .

[34]  Anandamayee Majumdar,et al.  Reconsidering the welfare cost of inflation in the US: a nonparametric estimation of the nonlinear long-run money-demand equation using projection pursuit regressions , 2014 .

[35]  E. Castro,et al.  Modified and enhanced replacement method for the selection of molecular descriptors in QSAR and QSPR theories , 2008 .

[36]  M. Karelson,et al.  Quantum-Chemical Descriptors in QSAR/QSPR Studies. , 1996, Chemical reviews.

[37]  Yagamare Fall,et al.  Theoretical study of GSK−3α: neural networks QSAR studies for the design of new inhibitors using 2D descriptors , 2011, Molecular Diversity.

[38]  Sven P. Jacobsson,et al.  Algorithmic approaches for studies of variable influence, contribution and selection in neural networks , 2000 .

[39]  Joaquín Izquierdo,et al.  Predictive models for forecasting hourly urban water demand , 2010 .

[40]  V. Vyas,et al.  CoMFA and CoMSIA studies on C-aryl glucoside SGLT2 inhibitors as potential anti-diabetic agents , 2013, SAR and QSAR in environmental research.

[41]  N. Lewis,et al.  Phlorizin: a review , 2005, Diabetes/metabolism research and reviews.

[42]  M. Fatemi,et al.  Cytotoxicity estimation of ionic liquids based on their effective structural features. , 2011, Chemosphere.