APPLICATION OF THE MACHINE AND DEEP LEARNING METHODS FOR THE CLASSIFICATION OF CANNABINOID- AND CATHINONE-DERIVED COMPOUNDS

Authors

  • WIDYA DWI ARYATI Laboratory of Biomedical Computation and Drug Design, Faculty of Pharmacy, Universitas Indonesia, Depok, West Java, Indonesia
  • MUHAMMAD SIDDIQ WINARKO Laboratory of Biomedical Computation and Drug Design, Faculty of Pharmacy, Universitas Indonesia, Depok, West Java, Indonesia
  • GERRY MAY SUSANTO Laboratory of Biomedical Computation and Drug Design, Faculty of Pharmacy, Universitas Indonesia, Depok, West Java, Indonesia
  • ARRY YANUAR Laboratory of Biomedical Computation and Drug Design, Faculty of Pharmacy, Universitas Indonesia, Depok, West Java, Indonesia

DOI:

https://doi.org/10.22159/ijap.2020.v12s1.FF005

Keywords:

Deep learning, Cannabinoid, Cathinone, Pharmacophore modeling, Psychoactive substance

Abstract

Objective: New psychoactive substances (NPS) have been rapidly developed to avoid legal entanglement. In 2013–2018, the number of cathinonederived
compounds increased from 30 to 89. In 2016, of 56 NPS compounds, 21 were identified as cannabinoid-derived; only 43 were regulated in
the narcotics law. Artificial intelligence, such as machine and deep learning, is a method of data processing and object recognition, including human
poses and image classifications.
Methods: Herein, the machine and deep learning methods for cathinone- and cannabinoid-derived compound classification were compared using
pharmacophore modeling as the reference method. For classifying cathinone-derived compounds, the structure was transformed into fingerprints,
which was used as a learning parameter for the machine and deep learning methods. Contrarily, the physicochemical properties and fingerprint shape
were utilized as learning materials for the deep learning method to classify the cannabinoid-derived substances.
Results: Consequently, in the cathinone-derived compound classification, the deep learning method produced the accuracy and Cohen kappa values
of 0.9932 and 0.992, respectively. Furthermore, such values in the pharmacophore modeling method were higher than those in the machine learning
method (0.911 and 0.708 vs. 0.718 and 0.673, respectively). In the cannabinoid-derived compound classification, the deep learning method with the
fingerprint form had the highest accuracy and Cohen kappa values (0.9904 and 0.9876). Such values in this method with the descriptor form were
higher than those in the pharmacophore modeling method (0.8958 and 0.8622 vs. 0.68 and 0.396, respectively).
Conclusion: The deep learning method has the potential in the NPS classification.

Downloads

Download data is not yet available.

References

1. Baumann MH. Awash in a sea of “bath salts”: Implications for
biomedical research and public health. Addiction 2014;109:1577-9.
2. Shadiq GF. Law enforcement of new psychoactive subtances narcotics
crime based on law number 35 year 2009 concerning narcotics
[Penegakan hukum terhadap tindak pidana narkotika new psychoactive
subtances berdasarkan undang-undang nomor 35 tahun 2009 tentang
narkotika]. J Wawasan Yuridika 2017;1:35-53.
3. Scientific Working Group for the Analysis of the Seized Drugs.
Available form: http://www.swgdrug.org . [Last accessed 2019 Aug 08].
4. Badan Narkotika Nasional. Prevention and Eradication of Drug Abuse
and Illicit Trafficking [Pencegahan dan pemberantasan penyalahgunaan
dan peredaran gelap narkoba]. Vol. 4. Jakarta: Badan Narkotika
Nasional; 2016.
5. Sumitha SK, Pattammady VS, Sambathkumar R. Pharmacology of
noval cannabinoids. Int J Pharm Pharm Sci 2019;12:1-5.
6. Eckert H, Bajorath J. Molecular similarity analysis in virtual screening:
Foundations, limitations and novel approaches. Drug Discov Today
2007;12:225-33.
7. Wolber G, Langer T. LigandScout: 3-D pharmacophores derived from
protein-bound ligands and their use as virtual screening filters. J Chem
Inf Model 2005;45:160-9.
8. KNIME-Open for Innovation. Knime.com. Available form: https://
www.knime.com . [Last accessed 2019 Aug 08].
9. Cho J, Lee K, Shin E, Choy G, Do S. How much data is needed to
train a medical image deep learning system to achieve necessary high
accuracy? 2015;ArXiv:1511.06348.
10. Viera AJ, Garrett JM. Understanding interobserver agreement: The
kappa statistic. Fam Med 2005;37:360-3.
11. Freitas AA, Lavington SH. Mining Very Large Databases with Parallel
Processing. Boston: Kluwer Academic Publishers; 2000.
12. Gulli A, Pal S. Deep Learning with Keras. Birmingham: Packt
Publishing; 2017.
13. Simonsen KL, Churchill GA, Aquadro CF. Properties of statistical tests
of neutrality for DNA polymorphism data. Genetics 1995;141:413-29.
14. Bennett ER, Clausen J, Linkov E, Linkov I. Predicting physical
properties of emerging compounds with limited physical and chemical
data: QSAR model uncertainty and applicability to military munitions.
Chemosphere 2009;77:1412-8.
15. Polamreddy P, Vishwakarma V, Mahto MK. Combinatorial
pharmacophore modeling and atom based 3D QSAR studies of
benzothiadiazines

Published

23-03-2020

How to Cite

ARYATI, W. D., WINARKO, M. S., SUSANTO, G. M., & YANUAR, A. (2020). APPLICATION OF THE MACHINE AND DEEP LEARNING METHODS FOR THE CLASSIFICATION OF CANNABINOID- AND CATHINONE-DERIVED COMPOUNDS. International Journal of Applied Pharmaceutics, 12(1), 47–50. https://doi.org/10.22159/ijap.2020.v12s1.FF005

Issue

Section

Original Article(s)

Most read articles by the same author(s)

1 2 > >>