Ligand-Based Virtual Screening Using Tailored Ensembles: A Prioritization Tool for Dual A2AAdenosine Receptor Antagonists / Monoamine Oxidase B Inhibitors.

BACKGROUND Virtual Screening methodologies have emerged as efficient alternatives for the discovery of new drug candidates. At the same time, ensemble methods are nowadays frequently used to overcome the limitations of employing a single model in ligand-based drug design. However, many applications of ensemble methods to this area do not consider important aspects related to both virtual screening and the modeling process. During the application of ensemble methods to virtual screening the proper validation of the models in virtual screening conditions is often neglected. No analysis of the diversity of the ensemble members is performed frequently or no considerations regarding the applicability domain of the base models are being made. METHODS In this research, we review basic concepts and definitions related to virtual screening. We comment recent applications of ensemble methods to ligand-based virtual screening and highlight their advantages and limitations. RESULTS Next, we propose a method based on genetic algorithms optimization for the generation of virtual screening tailored ensembles which address the previously identified problems in the current applications of ensemble methods to virtual screening. CONCLUSION Finally, the proposed methodology is successfully applied to the generation of ensemble models for the ligand-based virtual screening of dual target A2A adenosine receptor antagonists and MAO-B inhibitors as potential Parkinson's disease therapeutics.

[1]  Magdalena Bacilieri,et al.  The application of a 3D-QSAR (autoMEP/PLS) approach as an efficient pharmacodynamic-driven filtering method for small-sized virtual library: application to a lead optimization of a human A3 adenosine receptor antagonist. , 2006, Bioorganic & medicinal chemistry.

[2]  Subhash C. Bagui,et al.  Combining Pattern Classifiers: Methods and Algorithms , 2005, Technometrics.

[3]  M. Cordeiro,et al.  Discovery of MAO-B inhibitors - present status and future directions part I: oxygen heterocycles and analogs. , 2012, Mini reviews in medicinal chemistry.

[4]  Stephani Joy Y Macalino,et al.  Role of computer-aided drug design in modern drug discovery , 2015, Archives of Pharmacal Research.

[5]  Calvin Yu-Chian Chen,et al.  Two Birds with One Stone? Possible Dual-Targeting H1N1 Inhibitors from Traditional Chinese Medicine , 2011, PLoS Comput. Biol..

[6]  Alexander Golbraikh,et al.  Predictive QSAR modeling based on diversity sampling of experimental datasets for the training and test set selection , 2002, J. Comput. Aided Mol. Des..

[7]  J. Dearden,et al.  QSAR modeling: where have you been? Where are you going to? , 2014, Journal of medicinal chemistry.

[8]  S. Moro,et al.  Pyrido[2,3-e]-1,2,4-triazolo[4,3-a]pyrazin-1-one as a new scaffold to develop potent and selective human A3 adenosine receptor antagonists. Synthesis, pharmacological evaluation, and ligand-receptor modeling studies. , 2009, Journal of medicinal chemistry.

[9]  Fernanda Borges,et al.  Combining QSAR classification models for predictive modeling of human monoamine oxidase inhibitors. , 2013, European journal of medicinal chemistry.

[10]  M. Youdim,et al.  Bifunctional drug derivatives of MAO-B inhibitor rasagiline and iron chelator VK-28 as a more effective approach to treatment of brain ageing and ageing neurodegenerative diseases , 2005, Mechanisms of Ageing and Development.

[11]  A. Sarai,et al.  Genetic algorithm optimization in drug design QSAR: Bayesian-regularized genetic neural networks (BRGNN) and genetic algorithm-optimized support vectors machines (GA-SVM) , 2011, Molecular Diversity.

[12]  E. Novellino,et al.  Derivatives of 4-amino-6-hydroxy-2-mercaptopyrimidine as novel, potent, and selective A3 adenosine receptor antagonists. , 2008, Journal of medicinal chemistry.

[13]  K. Klotz,et al.  9-Ethyladenine derivatives as adenosine receptor antagonists: 2- and 8-substitution results in distinct selectivities , 2003, Naunyn-Schmiedeberg's Archives of Pharmacology.

[14]  M. C. Vega,et al.  Antiprotozoan lead discovery by aligning dry and wet screening: prediction, synthesis, and biological assay of novel quinoxalinones. , 2014, Bioorganic & medicinal chemistry.

[15]  Isidro Cortes-Ciriano,et al.  Prediction of the potency of mammalian cyclooxygenase inhibitors with ensemble proteochemometric modeling , 2015, Journal of Cheminformatics.

[16]  S. Moro,et al.  The significance of 2-furyl ring substitution with a 2-(para-substituted) aryl group in a new series of pyrazolo-triazolo-pyrimidines as potent and highly selective hA(3) adenosine receptors antagonists: new insights into structure-affinity relationship and receptor-antagonist recognition. , 2010, Journal of medicinal chemistry.

[17]  Christopher I. Bayly,et al.  Evaluating Virtual Screening Methods: Good and Bad Metrics for the "Early Recognition" Problem , 2007, J. Chem. Inf. Model..

[18]  Ann Nowé,et al.  GA(M)E-QSAR: A Novel, Fully Automatic Genetic-Algorithm-(Meta)-Ensembles Approach for Binary Classification in Ligand-Based Drug Design , 2012, J. Chem. Inf. Model..

[19]  Alexander Tropsha,et al.  Trust, But Verify: On the Importance of Chemical Structure Curation in Cheminformatics and QSAR Modeling Research , 2010, J. Chem. Inf. Model..

[20]  E. Novellino,et al.  5-amino-2-phenyl[1,2,3]triazolo[1,2-a][1,2,4]benzotriazin-1-one: a versatile scaffold to obtain potent and selective A3 adenosine receptor antagonists. , 2007, Journal of medicinal chemistry.

[21]  Nina Nikolova-Jeliazkova,et al.  QSAR Applicability Domain Estimation by Projection of the Training Set in Descriptor Space: A Review , 2005, Alternatives to laboratory animals : ATLA.

[22]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machines , 2002 .

[23]  Walter Cabri,et al.  Synthesis of (E)-8-(3-chlorostyryl)caffeine analogues leading to 9-deazaxanthine derivatives as dual A(2A) antagonists/MAO-B inhibitors. , 2013, Journal of medicinal chemistry.

[24]  Maykel Cruz-Monteagudo,et al.  Toward the computer-aided discovery of FabH inhibitors. Do predictive QSAR models ensure high quality virtual screening performance? , 2014, Molecular Diversity.

[25]  S. Moro,et al.  New 2-arylpyrazolo[3,4-c]quinoline derivatives as potent and selective human A3 adenosine receptor antagonists. Synthesis, pharmacological evaluation, and ligand-receptor modeling studies. , 2007, Journal of medicinal chemistry.

[26]  S. Moro,et al.  4-amido-2-aryl-1,2,4-triazolo[4,3-a]quinoxalin-1-ones as new potent and selective human A3 adenosine receptor antagonists. synthesis, pharmacological evaluation, and ligand-receptor modeling studies. , 2006, Journal of medicinal chemistry.

[27]  Neal Castagnoli,et al.  Dual-target-directed drugs that block monoamine oxidase B and adenosine A2A receptors for Parkinson’s disease , 2011, Neurotherapeutics.

[28]  Sonja Hinz,et al.  Dual targeting of adenosine A(2A) receptors and monoamine oxidase B by 4H-3,1-benzothiazin-4-ones. , 2013, Journal of medicinal chemistry.

[29]  Markus Lill,et al.  Virtual screening in drug design. , 2013, Methods in molecular biology.

[30]  Kenji Matsuno,et al.  Identification of a New Series of STAT3 Inhibitors by Virtual Screening. , 2010, ACS medicinal chemistry letters.

[31]  Stefano Moro,et al.  Linear and Nonlinear 3D-QSAR Approaches in Tandem with Ligand-Based Homology Modeling as a Computational Strategy To Depict the Pyrazolo-Triazolo-Pyrimidine Antagonists Binding Site of the Human Adenosine A2A Receptor , 2008, J. Chem. Inf. Model..

[32]  Maykel Cruz-Monteagudo,et al.  Activity cliffs in drug discovery: Dr Jekyll or Mr Hyde? , 2014, Drug discovery today.

[33]  K. Klotz,et al.  8-Bromo-9-alkyl adenine derivatives as tools for developing new adenosine A2A and A2B receptors ligands. , 2009, Bioorganic & medicinal chemistry.

[34]  H. Akaike,et al.  Information Theory and an Extension of the Maximum Likelihood Principle , 1973 .

[35]  Predicting dual-targeting anti-influenza agents using multi-models , 2015, Molecular Diversity.

[36]  E. Novellino,et al.  Novel N2-substituted pyrazolo[3,4-d]pyrimidine adenosine A3 receptor antagonists: inhibition of A3-mediated human glioblastoma cell proliferation. , 2010, Journal of medicinal chemistry.

[37]  R. Polikar,et al.  Ensemble based systems in decision making , 2006, IEEE Circuits and Systems Magazine.

[38]  Richard Morphy,et al.  From magic bullets to designed multiple ligands. , 2004, Drug discovery today.

[39]  C. J. Van der Schyf,et al.  Inhibition of monoamine oxidase B by selective adenosine A2A receptor antagonists. , 2003, Bioorganic & medicinal chemistry.

[40]  Rafael Garcia,et al.  Bio-AIMS Collection of Chemoinformatics Web Tools based on Molecular Graph Information and Artificial Intelligence Models. , 2015, Combinatorial chemistry & high throughput screening.

[41]  Xin Chen,et al.  Discovery of Novel Pim-1 Kinase Inhibitors by a Hierarchical Multistage Virtual Screening Approach Based on SVM Model, Pharmacophore, and Molecular Docking , 2011, J. Chem. Inf. Model..

[42]  Francisco Torrens,et al.  Discovery of novel anti-inflammatory drug-like compounds by aligning in silico and in vivo screening: the nitroindazolinone chemotype. , 2011, European journal of medicinal chemistry.

[43]  E. Novellino,et al.  Modulation of A2B adenosine receptor by 1-Benzyl-3-ketoindole derivatives. , 2013, European journal of medicinal chemistry.

[44]  Egon L. Willighagen,et al.  RRegrs: an R package for computer-aided model selection with multiple regression models , 2015, Journal of Cheminformatics.

[45]  E. Novellino,et al.  2-(Benzimidazol-2-yl)quinoxalines: a novel class of selective antagonists at human A(1) and A(3) adenosine receptors designed by 3D database searching. , 2005, Journal of medicinal chemistry.

[46]  Robert P. Sheridan,et al.  Protocols for Bridging the Peptide to Nonpeptide Gap in Topological Similarity Searches , 2001, J. Chem. Inf. Comput. Sci..

[47]  P. Rousseeuw.  Silhouettes: a graphical aid to the interpretation and validation of cluster analysis , 1987 .

[48]  Fernanda Borges,et al.  Classifier Ensemble Based on Feature Selection and Diversity Measures for Predicting the Affinity of A2B Adenosine Receptor Antagonists , 2013, J. Chem. Inf. Model..

[49]  F. Wilcoxon.  Individual Comparisons by Ranking Methods , 1945 .

[50]  A. Sperduti,et al.  Combining selectivity and affinity predictions using an integrated Support Vector Machine (SVM) approach: An alternative tool to discriminate between the human adenosine A(2A) and A(3) receptor pyrazolo-triazolo-pyrimidine antagonists binding sites. , 2009, Bioorganic & medicinal chemistry.

[51]  Cristian R. Munteanu,et al.  Graph-Based Processing of Macromolecular Information , 2015 .

[52]  K. Klotz,et al.  Characterization of potent ligands at human recombinant adenosine receptors , 1998 .

[53]  E. Uriarte,et al.  Discovery of novel A3 adenosine receptor ligands based on chromone scaffold. , 2012, Biochemical pharmacology.

[54]  Lei Yang,et al.  Classification of Cytochrome P450 Inhibitors and Noninhibitors Using Combined Classifiers , 2011, J. Chem. Inf. Model..

[55]  Dimitar Hristozov,et al.  Exploring Potency and Selectivity Receptor Antagonist Profiles Using a Multilabel Classification Approach: The Human Adenosine Receptors as a Key Study , 2009, J. Chem. Inf. Model..

[56]  A Lavecchia,et al.  Virtual screening strategies in drug discovery: a critical review. , 2013, Current medicinal chemistry.

[57]  Osmar Norberto de Souza,et al.  Discovery of New Inhibitors of Mycobacterium tuberculosis InhA Enzyme Using Virtual Screening and a 3D-Pharmacophore-Based Approach , 2013, J. Chem. Inf. Model..

[58]  Andreas Bender,et al.  Recognizing Pitfalls in Virtual Screening: A Critical Review , 2012, J. Chem. Inf. Model..

[59]  S. Moro,et al.  Synthesis, ligand-receptor modeling studies and pharmacological evaluation of novel 4-modified-2-aryl-1,2,4-triazolo[4,3-a]quinoxalin-1-one derivatives as potent and selective human A3 adenosine receptor antagonists. , 2008, Bioorganic & medicinal chemistry.

[60]  Tian Zhu,et al.  Hit identification and optimization in virtual screening: practical recommendations based on a critical literature analysis. , 2013, Journal of medicinal chemistry.

[61]  Leonardo L. G. Ferreira,et al.  Molecular Docking and Structure-Based Drug Design Strategies , 2015, Molecules.

[62]  Julie Clark,et al.  Discovery of Novel Antimalarial Compounds Enabled by QSAR-Based Virtual Screening , 2013, J. Chem. Inf. Model..

[63]  Chang-Guo Zhan,et al.  Proteasome inhibitors with pyrazole scaffolds from structure-based virtual screening. , 2015, Journal of medicinal chemistry.

[64]  Pedro Larrañaga,et al.  A review of feature selection techniques in bioinformatics , 2007, Bioinform..

[65]  Francisco Orallo,et al.  Inhibitory effects of cis- and trans-resveratrol on noradrenaline and 5-hydroxytryptamine uptake and on monoamine oxidase activity. , 2006, Biochemical and biophysical research communications.

[66]  Fuhui Long,et al.  Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy , 2003, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[67]  C. Müller,et al.  Synthesis and structure-activity relationships of 3,7-dimethyl-1-propargylxanthine derivatives, A2A-selective adenosine receptor antagonists. , 1997, Journal of medicinal chemistry.

[68]  I. Tetko,et al.  ISIDA - Platform for Virtual Screening Based on Fragment and Pharmacophoric Descriptors , 2008 .