Ocultar
Mostrar todos
Predicción de la afinidad de ligandos antagonistas por receptores de adenosina A2A usando árboles de decisión
Resumen
Las enfermedades neurodegenerativas están siendo tratadas mediante la modulación de los receptores de adenosina con antagonistas más eficaces, seguros y selectivos. El objetivo del estudio consistió en desarrollar una metodología para obtener modelos de clasificación sobre la base de algoritmos de árboles de decisión y descriptores de 0D a 2D de familias no congenéricas de compuestos orgánicos para predecir cualitativamente la afinidad ligando-RAA2A. Para ello se construyó y curó una base de datos no congenérica de 315 antagonistas con su constante de inhibición en nano molar, etiquetados como potentes y débiles. Se utilizaron los programas Dragon e ISIDA/QSPR para calcular descriptores moleculares y se obtuvieron cinco grupos de descriptores. En cada grupo se seleccionaron 50 descriptores usando el criterio mRMR. La base de datos se dividió en series de Entrenamiento, Prueba y Externa mediante una selección aleatoria y un análisis de clúster k-means generalizado. Se desarrollaron y validaron clasificadores utilizando el programa WEKA. Los resultados fueron analizados mediante las pruebas estadísticas de Friedman y Wilcoxon. Se comprobó la influencia significativa del parámetro m del algoritmo J48 en la predictividad, para los modelos que usaron los descriptores de los grupos aug.a-b e hyb.aug.a del ISIDA/QSPR. El modelo de mejor desempeño se obtuvo de los descriptores seleccionados del grupo ISIDA-todos con un valor de m=6 y alcanzó 90.6% de predicción sobre la serie Externa. La metodología desarrollada para obtener modelos de clasificación sobre la base de algoritmos de árboles de decisión y descriptores de 0D a 2D de familias no congenéricas de compuestos orgánicos es efectiva para predecir cualitativamente la afinidad ligando-RAA2A con una exactitud, especificidad y selectividad superiores al 90%.
Palabras clave: aprendizaje automatizado; clasificación; modelación; QSAR
Palabras clave
Referencias
Bacilieri M, Ciancetta A, Paoletta S, Federico S, Cosconati S, Cacciari B, Taliani S, Da Settimo F, Novellino E, Klotz KN, Spalluto G, Moro S (2013) Revisiting a Receptor-Based Pharmacophore Hypothesis for Human A 2A Adenosine Receptor Antagonists. Journal of Chemical Information and Modeling 53(7): 1620-1637; doi: 10.1021/ci300615u
Braga R, Alves V, Silva M, Muratov E, Fourches D, Tropsha A (2014) Tuning hERG Out: antitarget QSAR models for drug development. Curr Top Med Chem14: 1399–1415; doi: 10.2174/1568026614666140506124442
ChemAxon (2015) ChemSuit. Disponible en: http://www.chemaxon.com. Consultado 23/04/2017
Cheong SL, Dolzhenko A, Kachler S, Paoletta S, Federico S, Cacciari B, Dolzhenko A, Klotz KN, Moro S, Spalluto G, Pastorin G (2010) 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. Journal of Medicinal Chemistry 53(8): 3361-3375; doi: 10.1021/jm100049f
Colotta V, Catarzi D, Varano F, Capelli F, Lenzi O, Filacchioni G, Martini C, Trincavelli L, Ciampi O, Pugliese AM, Pedata F, Schiesaro A, Morizzo E, Moro S (2007) New 2-Arylpyrazolo (3,4-c) quinoline Derivatives as Potent and Selective Human A 3 Adenosine Receptor Antagonists. Synthesis, Pharmacological Evaluation, and Ligand−Receptor Modeling Studies. Journal of Medicinal Chemistry 50(17): 4061-4074; doi: 10.1021/jm070123v
Colotta V. Catarzi D, Varano F, Lenzi O, Filacchioni G, Martini C, Trincavelli L, Ciampi O, Traini C, Pugliese AM, Pedata F, Morizzo E, Moro S (2008) 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. Bioorganic & Medicinal Chemistry 16(11): 6086-6102; doi: 10.1016/j.bmc.2008.04.039
Colotta V, Lenzi O, Catarzi D, Varano F, Filacchioni G, Martini C, Trincavelli L, Ciampi O, Pugliese AM, Traini C, Pedata F, Morizzo E, Moro S (2009) Pyrido (2,3-e)-1,2,4-triazolo (4,3- a )pyrazin-1-one as a New Scaffold To Develop Potent and Selective Human A 3 Adenosine Receptor Antagonists. Synthesis, Pharmacological Evaluation, and Ligand−Receptor Modeling Studies. Journal of Medicinal Chemistry 52(8): 2407-2419; doi: 10.1021/jm8014876
Cosimelli B, Greco G, Ehlardo M, Novellino E, Da Settimo F, Taliani S, La Motta C, Bellandi M, Tuccinardi T, Martinelli A, Ciampi O, Trincavelli ML, Martini C (2008) Derivatives of 4-Amino-6-hydroxy-2-mercaptopyrimidine as Novel, Potent, and Selective A 3 Adenosine Receptor Antagonists. Journal of Medicinal Chemistry 51(6): 1764-1770; doi: 10.1021/jm701159t
Cristalli G, Camaioni E, Costanzi S, Vittori S, Volpini R, Klotz KN (1998) Characterization of potent ligands at human recombinant adenosine receptors. Drug Development Research 45(3-4): 176-181; doi: 10.1002/(SICI)1098-2299(199811/12)45:3/4<176::AID-DDR14>3.0.CO;2-G
Cronin MTD (2010) Quantitative Structure–Activity Relationships (QSARs) – Applications and Methodology. En: Puzyn T, Leszczynski J, Cronin MT (Eds). Recent Advances in QSAR Studies, pp. 3-11. Springer Netherlands, Dordrecht; doi: 10.1007/978-1-4020-9783-6_1
Da Settimo F, Primofiore G, Taliani S, Marini AM, La Motta C, Simorini F, Salerno S, Sergianni V, Tuccinardi T, Martinelli A, Cosimelli B, Greco G, Novellino E, Ciampi O, Trincavelli ML, Martini C (2007) 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. Journal of Medicinal Chemistry 50(23): 5676-5684; doi: 10.1021/jm0708376
Diniz C, Borges F, Santana L, Uriarte E, Oliveira JMA, Gonçalves J, Fresco P (2008) Ligands and therapeutic perspectives of adenosine A(2A) receptors. Current pharmaceutical design 14(17): 1698-1722; doi: 10.2174/138161208784746842
Drabczyńska A, Müller CE, Schiedel A, Schumacher B, Karolak-Wojciechowska J, Fruziński A, Zobnina W, Yuzlenko O, Kieć-Kononowicz K (2007) Phenylethyl-substituted pyrimido (2,1-f)purinediones and related compounds: Structure–activity relationships as adenosine A1 and A2A receptor ligands. Bioorganic & Medicinal Chemistry 15(22): 6956-6974; doi: 10.1016/j.bmc.2007.07.051
Fan F, Toledo WD, Hamadeh HK, Dunn RT (2019) The integration of pharmacophore-based 3D QSAR modeling and virtual screening in safety profiling: A case study to identify antagonistic activities against adenosine receptor, A2A, using 1,897 known drugs. PLOS ONE 14(1): e0204378; doi: 10.1371/journal.pone.0204378
Fourches D, Muratov E, Tropsha A (2010) Trust, But Verify: On the Importance of Chemical Structure Curation in Cheminformatics and QSAR Modeling Research. Journal of Chemical Information and Modeling 50(7): 1189-1204; doi: 10.1021/ci100176x
Franco PE (2011) Modelo de multiclasificador basado en selección de rasgos para predecir la afinidad de antagonistas por receptores de adenosina A2B. Tesis de Diploma, Universidad Central Marta Abreu de Las Villas, Santa Clara, Cuba
Gao ZG, Jacobson KA (2007) Emerging adenosine receptor agonists. Expert Opinion on Emerging Drugs 12(3): 479-492; doi: 10.1517/14728214.12.3.479
Gaspar A, Reis J, Kachler S, Paoletta S, Uriarte E, Klotz KN, Moro S, Borges F (2012) Discovery of novel A3 adenosine receptor ligands based on chromone scaffold. Biochemical Pharmacology 84(1): 21-29; doi: 10.1016/j.bcp.2012.03.007
Gomes MN, Braga RC, Grzelak EM, Neves BJ, Muratov E, Ma R (2017) QSAR-driven design, synthesis and discovery of potent chalcone derivatives with antitubercular activity. Eur J Med Chem 137: 126–138; doi: 10.1016/j.ejmech.2017.05.026
González MP, Terán C, Teijeira M (2008) Search for new antagonist ligands for adenosine receptors from QSAR point of view. How close are we? Medicinal Research Reviews 28(3): 329-371; doi: 10.1002/med.20108
Hanchuan P, Fuhui L, Ding C (2005) Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy. IEEE Transactions on Pattern Analysis and Machine Intelligence 27(8): 1226-1238; doi: 10.1109/TPAMI.2005.159
Hawkins DM (2004) The Problem of Overfitting. Journal of Chemical Information and Computer Sciences 44(1): 1-12; doi: 10.1021/ci0342472
Kalash L, Val C, Azuaje J, Loza MI, Svensson F, Zoufir A, Mervin L, Ladds G, Brea J, Glen R, Sotelo E, Bender A (2017) Computer-aided design of multi-target ligands at A1R, A2AR and PDE10A, key proteins in neurodegenerative diseases. Journal of Cheminformatics 9(1): 67; doi: 10.1186/s13321-017-0249-4
Kase H (2000) Introductory Remarks: Adenosine A2A Receptor Antagonists. En: Kase H, Richardson PJ, Jenner P (Eds). Adenosine Receptors and Parkinson’s Disease, pp. 1-15. Elsevier, London; doi: 10.1016/B978-012400405-4/50002-2
Khanfar MA, Al-Qtaishat S, Habash M, Taha MO (2016) Discovery of potent adenosine A2a antagonists as potential anti-Parkinson disease agents. Non-linear QSAR analyses integrated with pharmacophore modeling. Chemico-Biological Interactions 254: 93-101; doi: 10.1016/j.cbi.2016.05.023
Klotz KN, Hessling J, Hegler J, Owman C, Kull B, Fredholm BB, Lohse MJ (1997) Comparative pharmacology of human adenosine receptor subtypes – characterization of stably transfected receptors in CHO cells. Naunyn-Schmiedeberg’s Archives of Pharmacology 357(1): 1-9; doi: 10.1007/PL00005131
Klotz KN, Kachler S, Lambertucci C, Vittori S, Volpini R, Cristalli G (2003) 9-Ethyladenine derivatives as adenosine receptor antagonists: 2- and 8-substitution results in distinct selectivities. Naunyn-Schmiedeberg’s Archives of Pharmacology 367(6): 629-634; doi: 10.1007/s00210-003-0749-9
Lambertucci C, Antonini I, Buccioni M, Ben DD, Kachare DD, Volpini R, Klotz KN, Cristalli G (2009) 8-Bromo-9-alkyl adenine derivatives as tools for developing new adenosine A2A and A2B receptors ligands. Bioorganic & Medicinal Chemistry 17(7): 2812-2822; doi: 10.1016/j.bmc.2009.02.030
Lenzi O, Colotta V, Catarzi D, Varano F, Filacchioni G, Martini C, Trincavelli L, Ciampi O, Varani K, Marighetti F, Morizzo E, Moro S (2006) 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. Journal of Medicinal Chemistry 49(13): 3916-3925; doi: 10.1021/jm060373w
Michielan L, Bacilieri M, Schiesaro A, Bolcato C, Pastorin G, Spalluto G, Cacciari B, Klotz KN, Kaseda C, Moro S (2008) 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 A 2A Receptor. Journal of Chemical Information and Modeling 48(2): 350-363; doi: 10.1021/ci700300w
Michielan L, Bolcato C, Federico S, Cacciari B, Bacilieri M, Klotz KN, Kachler S, Pastorin G, Cardin R, Sperduti A, Spalluto G, Moro S (2009a) Combining selectivity and affinity predictions using an integrated Support Vector Machine (SVM) approach: An alternative tool to discriminate between the human adenosine A2A and A3 receptor pyrazolo-triazolo-pyrimidine antagonists binding sites. Bioorganic & Medicinal Chemistry 17(14): 5259-5274; doi: 10.1016/j.bmc.2009.05.038
Michielan L, Stephanie F, Terfloth L, Hristozov D, Cacciari B, Klotz KN, Spalluto G, Gasteiger J, Moro S (2009b) Exploring Potency and Selectivity Receptor Antagonist Profiles Using a Multilabel Classification Approach: The Human Adenosine Receptors as a Key Study. Journal of Chemical Information and Modeling 49(12): 2820-2836; doi: 10.1021/ci900311j
Mitchell TM (1997) Machine Learning. WCB/McGraw-Hill Science, London; ISBN: 0070428077
Morales A, Pérez A, Gaspar A, Reis J, Cagide F, Vina D, Cordeiro N, Borges F (2013) Combining QSAR classification models for predictive modeling of human monoamine oxidase inhibitors. European Journal of Medicinal Chemistry 59: 75-90
Moro S, Bacilieri M, Cacciari B, Bolcato C, Cusan C, Pastorin G, Klotz KN, Spalluto G (2006) 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. Bioorganic & Medicinal Chemistry 14(14): 4923-4932; doi: 10.1016/j.bmc.2006.03.010
Müller CE, Jacobson KA (2011) Recent developments in adenosine receptor ligands and their potential as novel drugs. Biochimica et Biophysica Acta (BBA) - Biomembranes 1808(5): 1290-1308; doi: 10.1016/j.bbamem.2010.12.017
Mustyala KK, Chitturi AR, Naikal James PS, Vuruputuri U (2012) Pharmacophore mapping and in silico screening to identify new potent leads for A 2A adenosine receptor as antagonists. Journal of Receptors and Signal Transduction 32(2): 102-113; doi: 10.3109/10799893.2012.660532
Novellino E, Cosimelli B, Ehlardo M, Greco G, Iadanza M, Lavecchia A, Rimoli MG, Sala A, Da Settimo A, Primofiore G, Da Settimo F, Taliani S, La Motta C, Klotz KN, Tuscano D, Trincavelli ML, Martini C (2005) 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. Journal of Medicinal Chemistry 48(26): 8253-8260; doi: 10.1021/jm050792d
OECD (2004) OECD principles for the validation, for regulatory purposes, of (Quantitative) Structure-Activity Relatinship models. Disponible en: https://www.oecd.org/chemicalsafety/risk-assessment/37849783.pdf. Consultado 28/05/2018
Pérez A (2010) Nuevas aportaciones al desarrollo de modelos QSAR/QSPR para la predicción de la mutagenicidad de contaminantes ambientales y su interacción con sustancias activas presentes en el medio. Tesis de doctorado, Universidad Católica San Antonio, Murcia, España
Pourbasheer E, Shokouhi Tabar S, Masand VH, Aalizadeh R, Ganjali MR (2015) 3D-QSAR and docking studies on adenosine A 2A receptor antagonists by the CoMFA method. SAR and QSAR in Environmental Research 26(6): 461-477; doi: 10.1080/1062936X.2015.1049666
Quinlan JR (1993) C4.5: Programs for Machine Learning. Morgan Kaufmann Publishers Inc, San Francisco; ISBN: 1558602402
Quinlan JR (1986) Induction of decision trees. Machine Learning 1(1): 81-106; doi: 10.1007/BF00116251
Rahman A (2009) The Role of Adenosine in Alzheimers Disease. Current Neuropharmacology 7(3): 207-216; doi: 10.2174/157015909789152119
Roy K, Kar S, Das RN (2015) Understanding the Basics of QSAR for Applications in Pharmaceutical Sciences and Risk Assessment. Elsevier, London; doi: 10.1016/C2014-0-00286-9
Sheskin DJ (2000) Handbook of parametric and nonparametric statistical procedures. Chapman & Hall/CRC, Boca Raton; ISBN: 158488133X
Sousa JB, Diniz C (2017) The Adenosinergic System as a Therapeutic Target in the Vasculature: New Ligands and Challenges. Molecules 22: 752
Taylor JB, Triggle DJ (2007) Comprehensive Medicinal Chemistry II. Elsevier, London; ISBN: 978-0-08-045044-5
Talete SRL (2010) DRAGON Professional. Disponible en: http://www.talete.mi.it/. Consultado 18/06/2017
Taliani S, La Motta C, Mugnaini L, Simorini F, Salerno S, Marini AM, Da Settimo F, Cosconati S, Cosimelli B, Greco G, Limongelli V, Marinelli L, Novellino E, Ciampi O, Daniele S, Trincavelli ML, Martini C (2010) Novel N 2 -Substituted Pyrazolo (3,4-d) pyrimidine Adenosine A3 Receptor Antagonists: Inhibition of A 3 -Mediated Human Glioblastoma Cell Proliferation. Journal of Medicinal Chemistry 53(10): 3954-3963; doi: 10.1021/jm901785w
Taliani S, Trincavelli ML, Cosimelli B, Laneri S, Severi E, Barresi E, Pugliesi I, Daniele S, Giacomelli C, Greco G, Novellino E, Martini C, Da Settimo F (2013) Modulation of A2Badenosine receptor by 1-Benzyl-3-ketoindole derivatives. European Journal of Medicinal Chemistry 69: 331-337; doi: 10.1016/j.ejmech.2013.09.001
Todeschini R, Consonni V (2009) Molecular Descriptors for Chemoinformatics. Wiley‐VCH Verlag GmbH & Co. KGaA, London; doi: 10.1002/9783527628766
Varnek A, Solov’ev VP (2010) Programa ISIDA (In Silico Design and Data Analysis). Disponible en: http://infochim.u-strasbg.fr/spip.php?rubrique41. Consultado 16/07/2018
Wilson CN, Mustafa SJ (2009) Adenosine Receptors in Health and Disease. Springer, Berlin; doi: 10.1007/978-3-540-89615-9
Witten IH, Frank E, Hall MA (2011) Data Mining: Practical Machine Learning Tools and Techniques. Morgan Kaufmann, New Zealand; ISBN: 978-0-12-374856-0
Zhang L, Liu T, Wang X, Wang J, Li G, Li Y, Yang L, Wang Y (2014) Insight into the binding mode and the structural features of the pyrimidine derivatives as human A2A adenosine receptor antagonists. Biosystems 115: 13-22; doi: 10.1016/j.biosystems.2013.04.003
Copyright (c) 2019 Biotecnología Vegetal
Biotecnología Vegetal eISSN 2074-8647, RNPS: 2154. ISSN 1609-1841, RNPS: 0397 Editada por: Instituto de Biotecnología de las Plantas. Universidad Central Marta Abreu de Las Villas. Carretera a Camajuaní km 5.5, Santa Clara, Villa Clara, Cuba CP 54 830 Tel: 53 42200124, e-mail: info@ibp.co.cu
Biotecnología Vegetal está bajo una Licencia Creative Commons Atribución-NoComercial 4.0 Internacional.