Drug repurposing for obsessive-compulsive disorder using deep learning-based binding affinity prediction models

Thomas Papikinos; Marios Krokidis; Aris Vrahatis; Panagiotis Vlamos; Themis P. Exarchos; Thomas Papikinos; Marios Krokidis; Aris Vrahatis; Panagiotis Vlamos; Themis P. Exarchos

doi:10.3934/Neuroscience.2024013

AIMS Neuroscience

2024, Volume 11, Issue 2: 203-211. doi: 10.3934/Neuroscience.2024013

Previous Article Next Article

Research article Special Issues

Drug repurposing for obsessive-compulsive disorder using deep learning-based binding affinity prediction models

Bioinformatics and Human Electrophysiology Laboratory, Department of Informatics, Ionian University, Corfu, Greece

Received: 28 December 2023 Revised: 29 May 2024 Accepted: 04 June 2024 Published: 26 June 2024

Obsessive-compulsive disorder (OCD) is a chronic psychiatric disease in which patients suffer from obsessions compelling them to engage in specific rituals as a temporary measure to alleviate stress. In this study, deep learning-based methods were used to build three models which predict the likelihood of a molecule interacting with three biological targets relevant to OCD, SERT, D2, and NMDA. Then, an ensemble model based on those models was created which underwent external validation on a large drug database using random sampling. Finally, case studies of molecules exhibiting high scores underwent bibliographic validation showcasing that good performance in the ensemble model can indicate connection with OCD pathophysiology, suggesting that it can be used to screen molecule databases for drug-repurposing purposes.
- drug repurposing,
- drug repositioning,
- obsessive-compulsive disorder,
- OCD,
- deep learning,
- drug-target interaction prediction,
- binding affinity prediction
Citation: Thomas Papikinos, Marios Krokidis, Aris Vrahatis, Panagiotis Vlamos, Themis P. Exarchos. Drug repurposing for obsessive-compulsive disorder using deep learning-based binding affinity prediction models[J]. AIMS Neuroscience, 2024, 11(2): 203-211. doi: 10.3934/Neuroscience.2024013

Related Papers:

Abstract

Obsessive-compulsive disorder (OCD) is a chronic psychiatric disease in which patients suffer from obsessions compelling them to engage in specific rituals as a temporary measure to alleviate stress. In this study, deep learning-based methods were used to build three models which predict the likelihood of a molecule interacting with three biological targets relevant to OCD, SERT, D2, and NMDA. Then, an ensemble model based on those models was created which underwent external validation on a large drug database using random sampling. Finally, case studies of molecules exhibiting high scores underwent bibliographic validation showcasing that good performance in the ensemble model can indicate connection with OCD pathophysiology, suggesting that it can be used to screen molecule databases for drug-repurposing purposes.

Availability

All code and data used in this study as well as the results are available at https://github.com/tompapgr/OCD-Drug-Repurposing.

Conflict of interest

The authors declare no conflicts of interest.

Author contributions

Conceptualization, TP, TPE; methodology, TP, TPE; validation, TP, MK, AV, PV; formal analysis, TE, TPE; investigation, TP, PV; data curation, TP, MK, AV; writing—original draft preparation, TP, TPE; writing—review and editing, TPE, PV. All authors have read and agreed to the published version of the manuscript.

References

[1]	Schaduangrat N, Lampa S, Simeon S, et al. (2020) Towards reproducible computational drug discovery. J Cheminform 12. https://doi.org/10.1186/s13321-020-0408-x
[2]	Rudrapal M, Khairnar SJ, Jadhav AG Drug Repurposing (DR): An Emerging Approach in Drug Discovery. in Drug Repurposing - Hypothesis, Molecular Aspects and Therapeutic Applications (2020). https://doi.org/10.5772/intechopen.93193
[3]	Moraca F, Marzano S, D'Amico F, et al. (2022) Ligand-based drug repurposing strategy identified SARS-CoV-2 RNA G-quadruplex binders. Chem Comm 85. https://doi.org/10.1039/D2CC03135C
[4]	Huang K, Fu T, Glass LM, et al. (2020) DeepPurpose: a deep learning library for drug–target interaction prediction. Bioinformatics 36: 5545-5547. https://doi.org/10.1093/bioinformatics/btaa1005
[5]	Ramsundar B, Eastman P, Walters P, et al. (2019) Deep Learning for the Life Sciences.O'Reilly Media, Inc.
[6]	Zhu Z, Shi C, Zhang Z, et al. (2022) TorchDrug: A Powerful and Flexible Machine Learning Platform for Drug Discovery. arXiv : 2202.08320.
[7]	American Psychiatric Association, in Diagnostic and statistical manual of mental disorders: DSM-52013: 237-242. https://doi.org/10.1176/appi.books.9780890425596
[8]	Pittenger C (2021) Pharmacotherapeutic strategies and new targets in OC. The Neurobiology and Treatment of OCD: Accelerating Progress. Current Topics in Behavioral Neurosciences. Cham: Springer. https://doi.org/10.1007/7854_2020_204
[9]	Ramasubbu R, Ravindran A, Lapierre Y (2000) Serotonin and Dopamine Antagonism in Obsessive-Compulsive Disorder: Effect of Atypical Antipsychotic Drugs. Pharmacopsychiatry 33: 236-238. https://doi.org/10.1055/s-2000-8360
[10]	Moresco RM, Pietra L, Henin M, et al. (2007) Fluvoxamine treatment and D2 receptors: a pet study on OCD drug-naïve patients. Neuropsychopharmacology 32: 197-205. https://doi.org/10.1038/sj.npp.1301199
[11]	Gilson MK, Liu T, Baitaluk M, et al. (2016) BindingDB in 2015: A public database for medicinal chemistry, computational chemistry and systems pharmacology. Nucleic Acids Res 44: D1045-D1053. https://doi.org/10.1093/nar/gkv1072
[12]	Mysinger MM, Carchia M, Irwin JJ, et al. (2012) Directory of Useful Decoys, Enhanced (DUD-E): Better Ligands and Decoys for Better Benchmarking. J Med Chem 55: 6582-6594. https://doi.org/10.1021/jm300687e
[13]	Weininger D (1988) SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules. J Chem Inf Comput Sci 28: 31-36. https://doi.org/10.1021/ci00057a005
[14]	KD value: a quantitative measurement of antibody affinity. [Online]. Available: https://www.abcam.com/primary-antibodies/kd-value-a-quantitive-measurement-of-antibody-affinity
[15]	Gilmer J, Schoenholz SS, Riley PF, et al. (2017) Neural Message Passing for Quantum Chemistry. arXiv : 1704.01212.
[16]	Sarfraz N, Okuampa D, Hansen H, et al. (2022) pitolisant, a novel histamine-3 receptor competitive antagonist, and inverse agonist, in the treatment of excessive daytime sleepiness in adult patients with narcolepsy. Health Psychol Res 10. https://doi.org/10.52965/001c.34222
[17]	Butler MG (2011) Prader-Willi Syndrome: Obesity due to Genomic Imprinting. Curr Genomics 12: 204-215. https://doi.org/10.2174/138920211795677877
[18]	Crinò A, Fintini D, Bocchini S, et al. (2018) Obesity management in Prader–Willi syndrome: current perspectives. Diabet Metab Synd Ob 11: 579-593. https://doi.org/10.2147/DMSO.S141352
[19]	FY2007 List of Approved Products: New Drugs (2013) [Online]. Available from: https://web.archive.org/web/20130119182609/http://www.pmda.go.jp/english/service/pdf/list/NewdrugsFY2007.pdf
[20]	Nagoshi Y, Tominaga T, Fukui K (2016) Blonanserin Augmentation for Treatment-Resistant Somatic Symptom Disorder: A Case Series. Clin Neuropharmacol 39: 112-114. https://doi.org/10.1097/WNF.0000000000000134
[21]	Zhang T-T, Xue R, Wang X, et al. (2018) Network-based drug repositioning: A novel strategy for discovering potential antidepressants and their mode of action. Eur Neuropsychopharm 28: 1137-1150. https://doi.org/10.1016/j.euroneuro.2018.07.096
[22]	Biperiden Uses, Side Effects & Warnings. [Online]. Available: https://www.drugs.com/mtm/biperiden.html
[23]	Poyurovsky M, Meerovich I, Weizman A (1995) Beneficial effect of low-dose mianserin on fluvoxamine-induced akathisia in an obsessive-compulsive patient. Int Clin Psychopharm 10: 111-114. https://doi.org/10.1097/00004850-199506000-00008
[24]	Jaskari MO (1979) Observations on mianserin in the treatment of obsessive neuroses. Curr Med Res Opin 6: 128-131. https://doi.org/10.1185/03007998009114812

Reader Comments

Your name:*

Email:*
© 2024 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)