Research Article

Machine learning study: from the toxicity studies to tetrahydrocannabinol effects on Parkinson's disease

Mehmet Ali Yucel

Ibrahim Ozcelik

Oztekin Algul

Department of Pharmaceutical Chemistry, Faculty of Pharmacy, Erzincan Binali Yildirim University, Erzincan, 24100, Turkey

Department of Pharmaceutical Chemistry, Faculty of Pharmacy, Mersin University, Mersin, 33169, Turkey

Search for more papers by this author

Ibrahim Ozcelik

https://orcid.org/0000-0002-4291-6442

Department of Pharmaceutical Chemistry, Faculty of Pharmacy, Erzincan Binali Yildirim University, Erzincan, 24100, Turkey

Search for more papers by this author

Oztekin Algul

*Author for correspondence:

E-mail Address: oztekinalgul@mersin.edu.tr

https://orcid.org/0000-0001-5685-7511

Department of Pharmaceutical Chemistry, Faculty of Pharmacy, Erzincan Binali Yildirim University, Erzincan, 24100, Turkey

Department of Pharmaceutical Chemistry, Faculty of Pharmacy, Mersin University, Mersin, 33169, Turkey

Search for more papers by this author

Published Online:21 Mar 2023https://doi.org/10.4155/fmc-2022-0181

View article

Abstract

Aim: Investigating molecules having toxicity and chemical similarity to find hit molecules. Methods: The machine learning (ML) model was developed to predict the arylhydrocarbon receptor activity of anti-Parkinson's and US FDA-approved drugs. The ML algorithm was a support vector machine, and the dataset was Tox21. Results: The ML model predicted apomorphine in anti-Parkinson's drugs and 73 molecules in FDA-approved drugs as active. The authors were curious if there is any molecule like apomorphine in these 73 molecules. A fingerprint similarity analysis of these molecules was conducted and found tetrahydrocannabinol (THC). Molecular docking studies of THC for dopamine receptor 1 (affinity = -8.2 kcal/mol) were performed. Conclusion: THC may affect dopamine receptors directly and could be useful for Parkinson's disease.

Plain language summary

Arylhydrocarbon receptor has tissue-specific roles in xenobiotic metabolism, the immune system, inflammation and cancer. Studies showed that carbidopa and dopamine are agonists of arylhydrocarbon receptor. Parkinson's disease is a neurodegenerative disease and depends on the dopamine system's dysregulation. There is a strong relationship between the dopamine system and cannabinoids. In this study, the possibility of the agonist effect of tetrahydrocannabinol on dopamine receptors was investigated by a machine learning method.

Tweetable abstract

A machine learning model was developed to predict AHR activity of anti-Parkinson's and US FDA-approved drugs separately. The model predicted apomorphine in anti-Parkinson's drugs, 73 molecules in FDA-approved drugs and tetrahydrocannabinol as active.

Graphical abstract

Keywords:

Papers of special note have been highlighted as: • of interest; •• of considerable interest

References

1. Lin L, Dai Y, Xia Y. An overview of aryl hydrocarbon receptor ligands in the last two decades (2002–2022): a medicinal chemistry perspective. Eur. J. Med. Chem. 244, 114845 (2022).
Medline CASGoogle Scholar
2. Denison MS, Nagy SR. Activation of the aryl hydrocarbon receptor by structurally diverse exogenous and endogenous chemicals. Ann. Rev. Pharmacol. Toxicol. 43(1), 309–334 (2003).
Medline CASGoogle Scholar
3. Stejskalova L, Dvorak Z, Pavek P. Endogenous and exogenous ligands of aryl hydrocarbon receptor: current state of art. Curr. Drug Metab. 12(2), 198–212 (2011).
Medline CASGoogle Scholar
4. Dvořák Z, Poulíková K, Mani S. Indole scaffolds as a promising class of the aryl hydrocarbon receptor ligands. Eur. J. Med. Chem. 215, 113231 (2021).
Medline CASGoogle Scholar
5. Harrill JA, Hukkanen RR, Lawson M et al. Knockout of the aryl hydrocarbon receptor results in distinct hepatic and renal phenotypes in rats and mice. Toxicol. Appl. Pharmacol. 272(2), 503–518 (2013).
Medline CASGoogle Scholar
6. Neavin D, Liu D, Ray B, Weinshilboum R. The role of the aryl hydrocarbon receptor (AHR) in immune and inflammatory diseases. Int. J. Mol. Sci. 19(12), 3851 (2018).
MedlineGoogle Scholar
7. Dietrich C. Antioxidant functions of the aryl hydrocarbon receptor. Stem Cells Int. 2016, 1–10 (2016).
Google Scholar
8. Gutiérrez-Vázquez C, Quintana FJ. Regulation of the immune response by the aryl hydrocarbon receptor. Immunity 48(1), 19–33 (2018).
Medline CASGoogle Scholar
9. Busbee PB, Rouse M, Nagarkatti M, Nagarkatti PS. Use of natural AHR ligands as potential therapeutic modalities against inflammatory disorders. Nutr. Rev. 71(6), 353–369 (2013).
MedlineGoogle Scholar
10. Baricza E, Tamási V, Marton N, Buzás EI, Nagy G. The emerging role of aryl hydrocarbon receptor in the activation and differentiation of Th17 cells. Cell. Mol. Life Sci. 73(1), 95–117 (2016).
Medline CASGoogle Scholar
11. Gasiewicz TA, Henry EC, Collins LL. Expression and activity of aryl hydrocarbon receptors in development and cancer. Crit. Rev. Eukaryot. Gene Expr. 18(4), 279–321 (2008).
Medline CASGoogle Scholar
12. Liu Y, Lv J, Liu J et al. Mucus production stimulated by IFN-AHR signaling triggers hypoxia of COVID-19. Cell Res. 30(12), 1078–1087 (2020).
Medline CASGoogle Scholar
13. Giovannoni F, Bosch I, Polonio CM et al. AHR is a Zika virus host factor and a candidate target for antiviral therapy. Nat. Neurosci. 23(8), 939–951 (2020).
Medline CASGoogle Scholar
14. Di Meglio P, Duarte JH, Ahlfors H et al. Activation of the aryl hydrocarbon receptor dampens the severity of inflammatory skin conditions. Immunity 40(6), 989–1001 (2014).
MedlineGoogle Scholar
15. Kuzu B, Hepokur C, Turkmenoglu B, Burmaoglu S, Algul O. Design, synthesis and in vitro antiproliferation activity of some 2-aryl and -heteroaryl benzoxazole derivatives. Future Med. Chem. 14(14), 1027–1048 (2022).
CASGoogle Scholar
16. Panche AN, Diwan AD, Chandra SR. Flavonoids: an overview. J. Nutr. Sci. 5, e47 (2016).
Medline CASGoogle Scholar
17. Mondal A, Gandhi A, Fimognari C, Atanasov AG, Bishayee A. Alkaloids for cancer prevention and therapy: current progress and future perspectives. Eur. J. Pharmacol. 858, 172472 (2019).
Medline CASGoogle Scholar
18. O'Donnell EF, Saili KS, Koch DC et al. The anti-inflammatory drug leflunomide is an agonist of the aryl hydrocarbon receptor. PLOS ONE 5(10), e13128 (2010).
MedlineGoogle Scholar
19. Vyhlídalová B, Krasulová K, Pečinková P et al. Antimigraine drug avitriptan is a ligand and agonist of human aryl hydrocarbon receptor that induces CYP1A1 in hepatic and intestinal cells. Int. J. Mol. Sci. 21(8), 2799 (2020).
Medline CASGoogle Scholar
20. Volkova M, Palmeri M, Russell KS, Russell RR. Activation of the aryl hydrocarbon receptor by doxorubicin mediates cytoprotective effects in the heart. Cardiovasc. Res. 90(2), 305–314 (2011).
Medline CASGoogle Scholar
21. Ogura J, Miyauchi S, Shimono K et al. Carbidopa is an activator of aryl hydrocarbon receptor with potential for cancer therapy. Biochem. J. 474(20), 3391–3402 (2017). • This publication investigates the effect of carbidopa, which is one of the dopamine derivatives on arylhydrocarbon receptor (AHR).
Medline CASGoogle Scholar
22. Prud'homme GJ, Glinka Y, Toulina A, Ace O, Subramaniam V, Jothy S. Breast cancer stem-like cells are inhibited by a non-toxic aryl hydrocarbon receptor agonist. PLOS ONE 5(11), e13831 (2010).
MedlineGoogle Scholar
23. Patel A, Zhang S, Shrestha AK, Maturu P, Moorthy B, Shivanna B. Omeprazole induces heme oxygenase-1 in fetal human pulmonary microvascular endothelial cells via hydrogen peroxide-independent Nrf2 signaling pathway. Toxicol. Appl. Pharmacol. 311, 26–33 (2016).
Medline CASGoogle Scholar
24. Issa NT, Stathias V, Schürer S, Dakshanamurthy S. Machine and deep learning approaches for cancer drug repurposing. Semin. Cancer Biol. 68, 132–142 (2021).
Medline CASGoogle Scholar
25. Yang X, Wang Y, Byrne R, Schneider G, Yang S. Concepts of artificial intelligence for computer-assisted drug discovery. Chem. Rev. 119(18), 10520–10594 (2019).
Medline CASGoogle Scholar
26. Keiser MJ, Setola V, Irwin JJ et al. Predicting new molecular targets for known drugs. Nature 462(7270), 175–181 (2009).
Medline CASGoogle Scholar
27. Deshmukh AL, Chandra S, Singh DK, Siddiqi MI, Banerjee D. Identification of human flap endonuclease 1 (FEN1) inhibitors using a machine learning based consensus virtual screening. Mol. Biosyst. 13(8), 1630–1639 (2017).
Medline CASGoogle Scholar
28. Algamal ZY, Lee MH, Al-Fakih AM, Aziz M. High-dimensional QSAR prediction of anticancer potency of imidazo[4,5-b]pyridine derivatives using adjusted adaptive LASSO. J. Chemom. 29(10), 547–556 (2015).
CASGoogle Scholar
29. Alam S, Khan F. 3D-QSAR studies on maslinic acid analogs for anticancer activity against breast cancer cell line MCF-7. Sci. Rep. 7(1), 6019 (2017).
MedlineGoogle Scholar
30. Taha MO, Al-Sha'er MA, Khanfar MA, Al-Nadaf AH. Discovery of nanomolar phosphoinositide 3-kinase gamma (PI3Kγ) inhibitors using ligand-based modeling and virtual screening followed by in vitro analysis. Eur. J. Med. Chem. 84, 454–465 (2014).
Medline CASGoogle Scholar
31. Zhu K, Shen C, Tang C, Zhou Y, He C, Zuo Z. Improvement in the screening performance of potential aryl hydrocarbon receptor ligands by using supervised machine learning. Chemosphere 265, 129099 (2021).
Medline CASGoogle Scholar
32. Moukheiber L, Mangione W, Moukheiber M et al. Identifying protein features and pathways responsible for toxicity using machine learning and Tox21: implications for predictive toxicology. Molecules. 27(9), 3021 (2022).
Medline CASGoogle Scholar
33. Jin U-H, Lee S-O, Sridharan G et al. Microbiome-derived tryptophan metabolites and their aryl hydrocarbon receptor-dependent agonist and antagonist activities. Mol. Pharmacol. 85(5), 777–788 (2014).
MedlineGoogle Scholar
34. Park H, Jin U, Karki K et al. Dopamine is an aryl hydrocarbon receptor agonist. Biochem. J. 477(19), 3899–3910 (2020). • This publication investigates the effect of dopamine on AHR.
Medline CASGoogle Scholar
35. di Iorio G, Lupi M, Sarchione F et al. The endocannabinoid system: a putative role in neurodegenerative diseases. Int. J. High Risk Behav. Addict. 2(3), 100–106 (2013).
MedlineGoogle Scholar
36. More SV, Choi D-K. Promising cannabinoid-based therapies for Parkinson's disease: motor symptoms to neuroprotection. Mol. Neurodegener. 10(1), 17 (2015).
MedlineGoogle Scholar
37. Han Q-W, Yuan Y-H, Chen N-H. The therapeutic role of cannabinoid receptors and its agonists or antagonists in Parkinson's disease. Prog. Neuropsychopharmacol. Biol. Psychiatry 96, 109745 (2020).
Medline CASGoogle Scholar
38. Connolly BS, Lang AE. Pharmacological treatment of Parkinson disease. JAMA 311(16), 1670 (2014).
MedlineGoogle Scholar
39. Armstrong MJ, Okun MS. Diagnosis and treatment of Parkinson disease. JAMA 323(6), 548 (2020).
MedlineGoogle Scholar
40. Thomas R. The US Federal Tox21 Program: A strategic and operational plan for continued leadership. ALTEX 35(2), 163–168 (2018). https://ntp.niehs.nih.gov/whatwestudy/tox21/index.html
MedlineGoogle Scholar
41. Hearst MA, Dumais ST, Osuna E, Platt J, Scholkopf B. Support vector machines. IEEE Intel. Syst. 13(4), 18–28 (1998).
Google Scholar
42. Heikamp K, Bajorath J. Support vector machines for drug discovery. Expert Opin. Drug Discov. 9(1), 93–104 (2014).
Medline CASGoogle Scholar
43. Yucel MA. Comparing machine learning models for acetylcholine esterase inhibitors. Bioorganic and Medicinal Chemistry Reports 5 (2), 20–27 (2022).
Google Scholar
44. Cervantes J, Garcia-Lamont F, Rodríguez-Mazahua L, Lopez A. A comprehensive survey on support vector machine classification: applications, challenges and trends. Neurocomputing 408, 189–215 (2020).
Google Scholar
45. Pisner DA, Schnyer DM. Support vector machine. In: Machine Learning. Mechelli AVieira S (Eds). Academic Press, 101–121 (2020). https://www.sciencedirect.com/science/article/pii/B9780128157398000067
Google Scholar
46. Ramsundar B, Eastman P, Walters P, Pande V, Leswing K, Wu Z. Deep Learning for the Life Sciences O'Reilly Media Inc., CA, USA (2019).
Google Scholar
47. Landrum G. RDKit: open-source cheminformatics (2006). http://www.rdkit.org/
Google Scholar
48. Scheuermann TH, Tomchick DR, Machius M, Guo Y, Bruick RK, Gardner KH. Artificial ligand binding within the HIF2α PAS-B domain of the HIF2 transcription factor. Proc. Natl Acad. Sci. 106(2), 450–455 (2009).
Medline CASGoogle Scholar
49. Berman HM. The Protein Data Bank. Nucleic Acids Res. 28(1), 235–242 (2000).
Medline CASGoogle Scholar
50. Pettersen EF, Goddard TD, Huang CC et al. UCSF Chimera?A visualization system for exploratory research and analysis. J. Comput. Chem. 25(13), 1605–1612 (2004).
Medline CASGoogle Scholar
51. Holt PA, Chaires JB, Trent JO. Molecular docking of intercalators and groove-binders to nucleic acids using Autodock and Surflex. J. Chem. Inf. Model. 48(8), 1602–1615 (2008).
Medline CASGoogle Scholar
52. Trott O, Olson AJ. AutoDock Vina: improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreading. J. Comput. Chem. 31(2), 455–461 (2009).
Google Scholar
53. Zhuang Y, Xu P, Mao C et al. Structural insights into the human D1 and D2 dopamine receptor signaling complexes. Cell 184(4), 931–942.e18 (2021).
Medline CASGoogle Scholar
54. Hu W, Sorrentino C, Denison MS, Kolaja K, Fielden MR. Induction of Cyp1a1 is a nonspecific biomarker of aryl hydrocarbon receptor activation: results of large scale screening of pharmaceuticals and toxicants in vivo and in vitro. Mol. Pharmacol. 71(6), 1475–1486 (2007).
Medline CASGoogle Scholar
55. Carroll CB, Zeissler M-L, Hanemann CO, Zajicek JP. Δ⁹ -tetrahydrocannabinol (Δ⁹ -THC) exerts a direct neuroprotective effect in a human cell culture model of Parkinson's disease. Neuropathol. Appl. Neurobiol. 38(6), 535–547 (2012).
Medline CASGoogle Scholar
56. Moldzio R, Unterberger A, Krewenka C, Kranner B, Radad K. Neuroprotective effects of delta-9-tetrahydrocannabinol against FeSO₄- and H₂O₂-induced cell damage on dopaminergic neurons in primary mesencephalic cell culture. Planta Med. 8(3), e88–e95 (2021).
Google Scholar
57. Barkus E, Morrison PD, Vuletic D et al. Does intravenous Δ9-tetrahydrocannabinol increase dopamine release? A SPET study. J. Psychopharmacol. 25(11), 1462–1468 (2011).
Medline CASGoogle Scholar
58. Pacher P, Kunos G. Modulating the endocannabinoid system in human health and disease - successes and failures. FEBS Journal. 280(9), 1918–1943 (2013).
Medline CASGoogle Scholar
59. Fernández-Ruiz J, Moro MA, Martínez-Orgado J. Cannabinoids in neurodegenerative disorders and stroke/brain trauma: from preclinical models to clinical applications. Neurotherapeutics 12(4), 793–806 (2015).
Medline CASGoogle Scholar
60. Tiwari PC, Pal R. The potential role of neuroinflammation and transcription factors in Parkinson disease. Dialogues Clin. Neurosci. 19(1), 71–80 (2017).
MedlineGoogle Scholar
61. Orr CF, Rowe DB, Halliday GM. An inflammatory review of Parkinson's disease. Prog. Neurobiol. 68(5), 325–340 (2002).
Medline CASGoogle Scholar
62. More SV, Kumar H, Kim IS, Song S-Y, Choi D-K. Cellular and molecular mediators of neuroinflammation in the pathogenesis of Parkinson's disease. Mediators Inflamm. 2013, 1–12 (2013).
Google Scholar
63. Jenner P. Oxidative stress in Parkinson's disease. Ann. Neurol. 53(Suppl. 3), S26–S38 (2003).
Medline CASGoogle Scholar
64. Fernández-Ruiz J, Hernández M, Ramos JA. Cannabinoid–dopamine interaction in the pathophysiology and treatment of CNS disorders. CNS Neurosci. Ther. 16(3), e72–e91 (2010).
Medline CASGoogle Scholar
65. Bloomfield MAP, Ashok AH, Volkow ND, Howes OD. The effects of Δ9-tetrahydrocannabinol on the dopamine system. Nature 539(7629), 369–377 (2016). •• This publication investigates the effect of dopamine on AHR.
Medline CASGoogle Scholar
66. Bahji A, Breward N, Duff W et al. Cannabinoids in the management of behavioral, psychological, and motor symptoms of neurocognitive disorders: a mixed studies systematic review. J. Cannabis Res. 4(1), 11 (2022).
MedlineGoogle Scholar
67. Lall N. Medicinal Plants for Cosmetics, Health and Diseases. CRC Press, FL, USA (2022).
Google Scholar
68. Morgese MG, Cassano T, Cuomo V, Giuffrida A. Anti-dyskinetic effects of cannabinoids in a rat model of Parkinson's disease: role of CB1 and TRPV1 receptors. Exp. Neurol. 208(1), 110–119 (2007).
Medline CASGoogle Scholar

Vol. 15, No. 4

Metrics

Downloaded 61 times

History

Received 27 July 2022

Accepted 7 February 2023

Published online 21 March 2023

Published in print February 2023

Information

Keywords

Financial & competing interests disclosure

This study was carried out within the scope of the 2022 Graduation Research Project of the Faculty of Pharmacy of the Erzincan Binali Yıldırım University. The authors have no other relevant affiliations or financial involvement with any organization or entity with a financial interest in or financial conflict with the subject matter or materials discussed in the manuscript apart from those disclosed.

No writing assistance was utilized in the production of this manuscript.

PDF download