Abstract
With the advancement of combinatorial chemistry and big data, drug repositioning has boomed. In this sense, machine learning and artificial intelligence techniques offer a priori information to identify the most promising candidates. In this study, we combine QSAR and docking methodologies to identify compounds with potential inhibitory activity of vasoactive metalloproteases for the treatment of cardiovascular diseases. To develop this study, we used a database of 191 thermolysin inhibitor compounds, which is the largest as far as we know. First, we use Dragon's molecular descriptors (0-3D) to develop classification models using Bayesian networks (Naive Bayes) and artificial neural networks (Multilayer Perceptron). The obtained models are used for virtual screening of small molecules in the international DrugBank database. Second, docking experiments are carried out for all three enzymes using the Autodock Vina program, to identify possible interactions with the active site of human metalloproteases. As a result, high-performance artificial intelligence QSAR models are obtained for training and prediction sets. These allowed the identification of 18 compounds with potential inhibitory activity and an adequate oral bioavailability profile, which were evaluated using docking. Four of them showed high binding energies for the three enzymes, and we propose them as potential dual ACE/NEP inhibitors for the control of blood pressure. In summary, the in silico strategies used here constitute an important tool for the early identification of new antihypertensive drug candidates, with substantial savings in time and money.
Graphic abstract
Similar content being viewed by others
References
Tetko IV, Engkvist O, Koch U, Reymond JL, Chen H (2016) BIGCHEM: challenges and opportunities for big data analysis in chemistry. Mol Inf 35:615–621. https://doi.org/10.1002/minf.201600073
Wouters OJ, McKee M, Luyten J (2020) Estimated research and development investment needed to bring a new medicine to market, 2009–2018. JAMA 323(9):844–853. https://doi.org/10.1001/jama.2020.1166
DiMasi JA, Grabowski HG, Hansen RW (2016) Innovation in the pharmaceutical industry: new estimates of R&D costs. J Health Econ 47:20–33
Mei Y, Yang B (2018) Rational application of drug promiscuity in medicinal chemistry. Future Med Chem 10(15):1835–1851
Gupta MN, Alam A, Hasnain SE (2020) Protein promiscuity in drug discovery, drug-repurposing and antibiotic resistance. Biochimie 175:50–57. https://doi.org/10.1016/j.biochi.2020.05.004
Schmidt J, Marques MRG, Botti S, Marques MAL (2019) Recent advances and applications of machine learning in solidstate materials science. Comput Mater 83:1–36. https://doi.org/10.1038/s41524-019-0221-0
Roth GA, Mensah GA, Johnson CO (2020) Global burden of cardiovascular diseases and risk factors, 1990–2019: update from the GBD 2019 study. JACC 76(25):2982–3021. https://doi.org/10.1016/j.jacc.2020.11.010
Coates D (2003) The angiotensin converting enzyme (ACE). Int J Biochem Cell Biol 35:769–773
Sahli S, Stump B, Welti T, Schweizer WB, Diederich F, Blum-Kaelin D, Aebi JD, Bohm HJ (2005) A new class of inhibitors for the metalloprotease neprilysin based on a central imidazole scaffold. Helv Chim Acta 88(4):707–730
Corti R, Burnett JC, Rouleau JL, Ruschitzka F, Lüscher TF (2001) Vasopeptidase inhibitors a new therapeutic concept in cardiovascular disease? Circulation 104:1856–1862
Inguimbert N, Dhôtel H, Poras H, Coric P, Fournié-Zaluski MC, Roques BP (2004) Vasopeptidases inhibitors of ACE, NEP and ECE. PharmaChem 3:41–45
Cañizares-Carmenate Y, Mena-Ulecia K, Perera-Sardiña Y, Torrens F, Castillo-Garit JA (2019) An approach to identify new antihypertensive agents using thermolysin as model: in silico study based on QSARINS and docking. Arab J Chem 12(8):4861–4877. https://doi.org/10.1016/j.arabjc.2016.1010.1003
Benchetrit T, Fournie-Zaluski MC, Roques BP (1987) Relationship between the inhibitory potencies of thiorphan and retrothiorphan enantiomers on thermolysin and neutral endopeptidase 24.11 and their interactions with the thermolysin active site by computer modelling. Biochem Biophys Res Commun 147(3):1034–1040
Feder J, Brougham LR, Wildi BS (1974) Inhibition of thermolysin by dipeptides. Biochemistry 13(6):1186–1189
Gonnella NC, Bohacek R, Zhang X, Kolossvary I, Paris CG, Melton R, Winter C, Hu S, Ganu V (1995) Bioactive conformation of stromelysin inhibitors determined by transferred nuclear Overhauser effects. Biophysics 92:462–466
Holmquist B, Vallee BL (1974) Metal substitutions and inhibition of thermolysin: spectra of the cobalt enzyme. J Biol Chem 249(14):4601–4607
Nishino N, Powers JC (1978) Peptide hydroxamic acids as inhibitors of thermolysin. Biochemistry 17(14):2846–2850
Nishino N, Powers JC (1979) design of potent reversible inhibitors for thermolysin. Peptides containing zinc coordinating ligands and their use in affinity chromatography. Biochemistry 18(20):4340–4347
Talete S (2007) DRAGON for windows (software for molecular descriptor calculation). Version 5.5. http://www.talete.mi.it/.
Todeschini R, Consonni V (2009) Molecular descriptors for chemoinformatics, vol I & II. Wiley, Weinheim
StatSoft I (2004) STATISTICA (data analysis software system), version 7. www.statsoft.com
Castillo-Garit JA, del Toro-Cortés O, Vega MC, Rolón M, Rojas de Arias A, Casañola-Martin GM, Escario JA, Gómez-Barrio A, Marrero-Ponce Y, Torrens F, Abad C (2015) Bond-based bilinear indices for computational discovery of novel trypanosomicidal drug-like compounds through virtual screening. Eur J Med Chem 96:238–244
Jaworska J, Nikolova-Jeliazkova N (2007) How can structural similarity analysis help in category formation? SAR QSAR Environ Res 18(3–4):195–207
Castillo-Garit JA, Casañola-Martin GM, Barigye SJ, Pham-The H, Torrens F, Torreblanca A (2017) Machine learning-based models to predict modes of toxic action of phenols to Tetrahymena pyriformis. SAR QSAR Environ Res 28(9):735–747
DrugBank (www.drugbank.ca) Drug Bank database. University of Alberta, Canada,
Lipinski CA, Lombardo F, Dominy BW, Feeney PJ (2001) Experimental and computational approaches to estimate solubility and permeability in drug discovery and development settings. Adv Drug Deliv Rev 46:3–26
Stewart JJP (1989) Optimization of parameters for semiempirical methods I. Method J Comput Chem 10:209–220
Schmidt MW, Baldridge KK, Boatz JA, Gordon MS, Jensen JH, Koseki S, Nguyen KA, Su SJ, Windus TL, Dupuis M (1993) General atomic and molecular electronic structure system. J Comput Chem 14:1167–1189
Krimmer S, Klebe G (2015) Thermodynamics of protein-ligand interactions as a reference for computational analysis: how to assess accuracy, reliability and relevance of experimental data. J Comput Aided Mol Des 29:867–883
Glossop MS, Bazin RJ, Dack KN, Fox DNA, MacDonald GA, Mills M, Owen DR, Phillips C, Reeves KA, Ringer TJ (2011) Synthesis and evaluation of heteroarylalanine diacids as potent and selective neutral endopeptidase inhibitors. Bioorg Med Chem Lett 21(11):3404–3406
Natesh R, Schwager SLU, Sturrock ED, Acharya KR (2003) Crystal structure of the human angiotensin-converting enzyme–lisinopril complex. Nature 421:551–554
Morris GM, Huey R, Lindstrom W, Sanner MF, Belew RK, Goodsell DS, Olson AJ (2009) AutoDock4 and AutoDockTools4: automated docking with selective receptor flexibility. J Comput Chem 30:2785–2791
Trott O, Olson AJ (2010) AutoDock Vina: improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreading. J Comput Chem 31:455–461
Quesada-Romero L, Mena-Ulecia K, Tiznado W, Caballero J (2014) Insights into the Interactions between Maleimide Derivates and GSK3β Combining Molecular Docking and QSAR. PLoS One 9(7):e102212
Mena-Ulecia K, Tiznado W, Caballero J (2015) Study of the differential activity of thrombin inhibitors using docking, QSAR, molecular dynamics, and MM-GBSA. PLoS One 10:e0142774
Juers DH, Kim J, Matthews BW, Sieburth SM (2005) Structural analysis of silanediols as transition-state-analogue inhibitors of the benchmark metalloprotease thermolysin. Biochemistry 44(50):16524–16528. https://doi.org/10.1021/bi051346v
Roques BP (2001) Insights into peptide and protein function: a convergent approach12. J Pept Sci 7(2):63–73. https://doi.org/10.1002/psc.315
Gohlke H, Hendlich M, Klebe G (2000) Knowledge-based scoring function to predict protein-ligand interactions. J Mol Biol 295:337–356
Ashraf MS, Vongpatanasin W (2006) Estrogen and hypertension. Curr Hypert Rep 8(5):368–376. https://doi.org/10.1007/s11906-006-0080-1
Acknowledgements
Y. Cañizares-Carmenate and J. A. Castillo-Garit acknowledges to CELFI for the scholarships to participate in the course: Computational Biology Oriented to the Drugs Design (Universidad de Buenos Aires Nov/2016). F. Torrens acknowledges an internal aid from the Universidad Católica de Valencia San Vicente Mártir for support; K. Mena acknowledges to Fondecyt N° 11180650
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Electronic supplementary material
Below is the link to the electronic supplementary material.
Appendix
Appendix
See Table 3.
Rights and permissions
About this article
Cite this article
Cañizares-Carmenate, Y., Mena-Ulecia, K., MacLeod Carey, D. et al. Machine learning approach to discovery of small molecules with potential inhibitory action against vasoactive metalloproteases. Mol Divers 26, 1383–1397 (2022). https://doi.org/10.1007/s11030-021-10260-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11030-021-10260-0