Skip to main content

Advertisement

SpringerLink
Log in

Classification of Potent and Weak Penetration Enhancers Using Multiple Feature Selection Methods and Machine Learning Models

  • Original Article
  • Published:
Journal of Pharmaceutical Innovation Aims and scope Submit manuscript

Abstract

Purpose

Chemical penetration enhancers (CPEs) are important in transdermal drug delivery (TDDD) formulations because they assist drugs in moving across the stratum corneum. Hydrocortisone (0.1% hydrocortisone, propylene glycol), oestradiol (0.045 mg estradiol/0.015 mg levonorgestrel, propylene glycol), and testosterone (2% testosterone, propylene glycol) are some examples of marketing TDDD formulations. As the transdermal route for drug administration becomes a safer and more appealing alternative to hypodermic needles, the search for new CPEs and their development becomes more important. Thus, the current work was directed toward the rapid identification of potent CPEs through the development of robust machine learning (ML) classification models.

Methods

Two large penetration enhancer (PE) data sets reported to date such as hydrocortisone (139 PEs) and theophylline (101 PEs) were used to build classification models. In the present investigation, a combination of feature selection methods, i.e., Boruta and Recursive Feature Elimination (RFE), and machine learning (ML) algorithms such as support vector machine (SVM), random forest (RF), and artificial neural network (ANN) were employed to classify the potent and weak penetration enhancers of hydrocortisone and theophylline. The tenfold cross-validation and Y-randomization methods were used to evaluate the prediction performance of the developed models.

Results

Significant classification models were built for both data sets when the RFE method and RF algorithm were used. RF classifiers outperformed hydrocortisone and theophylline data sets with test set accuracy and Matthew’s correlation coefficient (MCC) greater than 0.78. Simultaneously, four important features required for the accurate classification of potent and weak PEs were identified, i.e., nHCsatu, minHCsatu, AATS4p, and GATS4e.

Conclusion

Our approach produced robust ML classification models that can be applied to prioritize PEs from large databases. Utilization of these ML models in virtual screening experiments could save time and effort in the identification of potential PEs.

Graphical Abstract

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

Data Availability

Data made available upon request.

Abbreviations

ML:

Machine learning

RFE:

Recursive Feature Elimination

RF:

Random forest

PEs:

Penetration enhancers

ER:

Enhancement RATIO

SVM:

Support vector machine

ANN:

Artificial neural network

AUC:

Area under curve

ROC:

Receiver operating characteristic curve

SC:

Stratum corneum

QSPR:

Quantitative structure–permeability relationship

TDDD:

Transdermal drug delivery

References

  1. Pailler-Mattei C, Bec S, Zahouani H. In vivo measurements of the elastic mechanical properties of human skin by indentation tests. Med Eng Phys. 2008;30(5):599–606.

    Article  PubMed  CAS  Google Scholar 

  2. Seki T, Morimoto K. Enhancing effects of medium chain aliphatic alcohols and esters on the permeation of 6-carboxyfluorescein and indomethacin through rat skin. Drug Deliv. 2003;10(4):289–93.

    Article  PubMed  CAS  Google Scholar 

  3. Williams A, Barry B. The enhancement index concept applied to terpene penetration enhancers for human skin and model lipophilic (oestradiol) and hydrophilic (5-fluorouracil) drugs. Int J Pharm. 1991;74(2–3):157–68.

    Article  CAS  Google Scholar 

  4. Sinha V, Kaur MP. Permeation enhancers for transdermal drug delivery. Drug Dev Ind Pharm. 2000;26(11):1131–40.

    Article  PubMed  CAS  Google Scholar 

  5. Willams A, Barry B. Permeation enhancer. Adv Drug Deliv Rev. 2012;64:128–37.

    Article  Google Scholar 

  6. Lundborg M, Wennberg CL, Narangifard A, et al. Predicting drug permeability through skin using molecular dynamics simulation. J Control Release. 2018;283:269–79.

    Article  PubMed  CAS  Google Scholar 

  7. Katz M, BJ P. Corticoid, vehicle, and skin interaction in percutaneous absorption. 1972.

  8. Ghafourian T, Zandasrar P, Hamishekar H, et al. The effect of penetration enhancers on drug delivery through skin: a QSAR study. J Control Release. 2004;99(1):113–25.

    Article  PubMed  CAS  Google Scholar 

  9. Iyer M, Zheng T, Hopfinger AJ, et al. QSAR analyses of skin penetration enhancers. J Chem Inf Model. 2007;47(3):1130–49.

    Article  PubMed  CAS  Google Scholar 

  10. Kalhapure RS, Salunke CL, Akamanchi KG. QSAR model for chemical penetration enhancers containing long hydrocarbon chain. Chemom Intell Lab Syst. 2012;118:267–70.

    Article  CAS  Google Scholar 

  11. Lim CW, Fujiwara S-I, Yamashita F, et al. Prediction of human skin permeability using a combination of molecular orbital calculations and artificial neural network. Biol Pharm Bull. 2002;25(3):361–366.

  12. Potts RO, Guy RH. A predictive algorithm for skin permeability: the effects of molecular size and hydrogen bond activity. Pharm Res. 1995;12(11):1628–33.

    Article  PubMed  CAS  Google Scholar 

  13. Pugh W, Wong R, Falson F, et al. Discriminant analysis as a tool to identify compounds with potential as transdermal enhancers. J Pharm Pharmacol. 2005;57(11):1389–96.

    Article  PubMed  CAS  Google Scholar 

  14. Cronin MT, Schultz TW. Pitfalls in QSAR. J Mol Struct (Thoechem). 2003;622(1–2):39–51.

    Article  CAS  Google Scholar 

  15. Buchwald P, Bodor N. A simple, predictive, structure-based skin permeability model. J Pharm Pharmacol. 2001;53(8):1087–98.

    Article  PubMed  CAS  Google Scholar 

  16. Barratt M. Quantitative structure-activity relationships for skin permeability. Toxicol In Vitro. 1995;9(1):27–37.

    Article  PubMed  CAS  Google Scholar 

  17. Abraham MH, Martins F, Mitchell RC. Algorithms for skin permeability using hydrogen bond descriptors: the problem of steroids. J Pharm Pharmacol. 1997;49(9):858–65.

    Article  PubMed  CAS  Google Scholar 

  18. Moss G, Shah A, Adams R, et al. The application of discriminant analysis and machine learning methods as tools to identify and classify compounds with potential as transdermal enhancers. Eur J Pharm Sci. 2012;45(1–2):116–27.

    Article  PubMed  CAS  Google Scholar 

  19. Welling SH, Clemmensen LK, Buckley ST, et al. In silico modelling of permeation enhancement potency in Caco-2 monolayers based on molecular descriptors and random forest. Eur J Pharm Biopharm. 2015;94:152–9.

    Article  PubMed  CAS  Google Scholar 

  20. Simon L, Abdelmalek B. Design of skin penetration enhancers using replacement methods for the selection of the molecular descriptors. Pharmaceutics. 2012;4(3):343–53.

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  21. Tenjarla SN, Kasina R, Puranajoti P, et al. Synthesis and evaluation of N-acetylprolinate esters—novel skin penetration enhancers. Int J Pharm. 1999;192(2):147–58.

    Article  PubMed  CAS  Google Scholar 

  22. Kim N, El-Khalili M, Henary M, et al. Percutaneous penetration enhancement activity of aromatic S, S-dimethyliminosulfuranes. Int J Pharm. 1999;187(2):219–29.

    Article  PubMed  CAS  Google Scholar 

  23. Song Y, Xiao C, Mendelsohn R, et al. Investigation of iminosulfuranes as novel transdermal penetration enhancers: enhancement activity and cytotoxicity. Pharm Res. 2005;22(11):1918–25.

    Article  PubMed  CAS  Google Scholar 

  24. Fincher TK, Yoo SD, Player MR, et al. In vitro evaluation of a series of N-dodecanoyl-L-amino acid methyl esters as dermal penetration enhancers. J Pharm Sci. 1996;85(9):920–3.

    Article  PubMed  CAS  Google Scholar 

  25. Fuhrman L Jr, Michniak B, Behl C, et al. Effect of novel penetration enhancers on the transdermal delivery of hydrocortisone: an in vitro species comparison. J Control Release. 1997;45(2):199–206.

    Article  CAS  Google Scholar 

  26. Michniak B, Player M, Godwin D, et al. Investigation of enhancer structure activity relationships in congeners of 2-(1-nonyl)-1, 3-dioxolane. Drug Deliv. 1995;2(2):117–22.

    Article  CAS  Google Scholar 

  27. Michniak B, Player M, Godwin D, et al. In vitro evaluation of azone analogs as dermal penetration enhancers: V. Miscellaneous compounds. Int J Pharm. 1998;161(2):169–78.

    Article  CAS  Google Scholar 

  28. El-Kattan AF, Asbill CS, Michniak BB. The effect of terpene enhancer lipophilicity on the percutaneous permeation of hydrocortisone formulated in HPMC gel systems. Int J Pharm. 2000;198(2):179–89.

    Article  PubMed  CAS  Google Scholar 

  29. Godwin DA, Player MR, Sowell JW, et al. Synthesis and investigation of urea compounds as transdermal penetration enhancers. Int J Pharm. 1998;167(1–2):165–75.

    Article  CAS  Google Scholar 

  30. Vávrová K, Hrabalek A, Doležal P, et al. L-Serine and glycine based ceramide analogues as transdermal permeation enhancers: polar head size and hydrogen bonding. Bioorg Med Chem Lett. 2003;13(14):2351–3.

    Article  PubMed  Google Scholar 

  31. Kopečná M, Macháček M, Nováčková A, et al. Esters of terpene alcohols as highly potent, reversible, and low toxic skin penetration enhancers. Sci Rep. 2019;9(1):1–12.

    Article  Google Scholar 

  32. Chen Y, Quan P, Liu X, et al. Novel chemical permeation enhancers for transdermal drug delivery. Asian J Pharm Sci. 2014;9(2):51–64.

    Article  Google Scholar 

  33. Yap CW. PaDEL-descriptor: an open source software to calculate molecular descriptors and fingerprints. J Comput Chem. 2011;32(7):1466–74.

    Article  PubMed  CAS  Google Scholar 

  34. Kuhn M. caret: Classification and Regression Training. Astrophysics Source Code Library, ascl: 2015. 1505.003.

  35. Xue Y, Yap CW, Sun LZ, et al. Prediction of P-glycoprotein substrates by a support vector machine approach. J Chem Inf Comput Sci. 2004;44(4):1497–505.

    Article  PubMed  CAS  Google Scholar 

  36. Xue Y, Li H, Ung C, et al. Classification of a diverse set of Tetrahymena pyriformis toxicity chemical compounds from molecular descriptors by statistical learning methods. Chem Res Toxicol. 2006;19(8):1030–9.

    Article  PubMed  CAS  Google Scholar 

  37. Lin H, Han L, Yap C, et al. Prediction of factor Xa inhibitors by machine learning methods. J Mol Graph Model. 2007;26(2):505–18.

    Article  PubMed  CAS  Google Scholar 

  38. Kursa MB, Rudnicki WR. Feature selection with the Boruta package. J Stat Softw. 2010;36(11):1–13.

    Article  Google Scholar 

  39. Boser BE, Guyon IM, Vapnik VN, editors. A training algorithm for optimal margin classifiers. Proceedings of the 5th Annual ACM Workshop on Computational Learning Theory. 1992.

  40. Tong S, Chang E, editors. Support vector machine active learning for image retrieval. Proceedings of the ninth ACM international conference on Multimedia; 2001.

  41. Yuan L-F, Ding C, Guo S-H, et al. Prediction of the types of ion channel-targeted conotoxins based on radial basis function network. Toxicol In Vitro. 2013;27(2):852–6.

    Article  PubMed  CAS  Google Scholar 

  42. Yao X, Panaye A, Doucet J, et al. Comparative classification study of toxicity mechanisms using support vector machines and radial basis function neural networks. Anal Chim Acta. 2005;535(1–2):259–73.

    Article  CAS  Google Scholar 

  43. Fernandez-Lozano C, Cuinas RF, Seoane JA, et al. Classification of signaling proteins based on molecular star graph descriptors using Machine Learning models. J Theor Biol. 2015;384:50–8.

    Article  PubMed  CAS  Google Scholar 

  44. Breiman L. Random forests. Mach Learn. 2001;45(1):5–32.

    Article  Google Scholar 

  45. Segal MR. Machine learning benchmarks and random forest regression. 2004.

  46. Karlik B, Olgac AV. Performance analysis of various activation functions in generalized MLP architectures of neural networks. International Journal of Artificial Intelligence and Expert Systems. 2011;1(4):111–22.

    Google Scholar 

  47. Riedmiller M, Braun H, editors. A direct adaptive method for faster backpropagation learning: The RPROP algorithm. IEEE international conference on neural networks; 1993: IEEE.

  48. Baldi P, Brunak S, Chauvin Y, et al. Assessing the accuracy of prediction algorithms for classification: an overview. Bioinformatics. 2000;16(5):412–24.

    Article  PubMed  CAS  Google Scholar 

Download references

Funding

This work was financially supported by the Department of Biotechnology (DBT), New Delhi (BT/ PR39876/BTIS/137/7/2021).

Author information

Authors and Affiliations

  1. Department of Pharmaceutical Sciences and Drug Research, Punjabi University, 147002, Patiala, Punjab, India

    Baddipadige Raju, Neha Verma, Gera Narendra, Om Silakari & Bharti Sapra

Authors
  1. Baddipadige Raju
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Neha Verma
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Gera Narendra
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Om Silakari
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Bharti Sapra
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Bharti Sapra.

Ethics declarations

Ethical Approval

No animals were harmed in this study.

Competing Interests

The authors declare no competing interests.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (DOCX 23 KB)

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Raju, B., Verma, N., Narendra, G. et al. Classification of Potent and Weak Penetration Enhancers Using Multiple Feature Selection Methods and Machine Learning Models. J Pharm Innov 18, 1778–1797 (2023). https://doi.org/10.1007/s12247-023-09757-y

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12247-023-09757-y

Keywords

Search

Navigation