Skip to main content
SpringerLink
Log in

Deep Learning for Drug Development: Using CNNs in MIA-QSAR to Predict Plasma Protein Binding of Drugs

  • Research Article
  • Applications of Machine Learning and A.I. in Pharmaceutical Development and Technology
  • Published:
AAPS PharmSciTech Aims and scope Submit manuscript

Abstract

Predicting plasma protein binding (PPB) is crucial in drug development due to its profound impact on drug efficacy and safety. In our study, we employed a convolutional neural network (CNN) as a tool to extract valuable information from the molecular structures of 100 different drugs. These extracted features were then used as inputs for a feedforward network to predict the PPB of each drug. Through this approach, we successfully obtained 10 specific numerical features from each drug’s molecular structure, which represent fundamental aspects of their molecular composition. Leveraging the CNN’s ability to capture these features significantly improved the precision of our predictions. Our modeling results revealed impressive accuracy, with an R2 train value of 0.89 for the training dataset, a \({Q}_{\mathrm{cv}}^{2}\) of 0.98, a \({Q}^{2}\) of 0.931 for the external validation dataset, and a low cross-validation mean squared error (CV-MSE) of 0.0213. These metrics highlight the effectiveness of our deep learning techniques in the fields of pharmacokinetics and drug development. This study makes a substantial contribution to the expanding body of research exploring the application of artificial intelligence (AI) and machine learning in drug development. By adeptly capturing and utilizing molecular features, our method holds promise for enhancing drug efficacy and safety assessments in pharmaceutical research. These findings underscore the potential for future investigations in this exciting and transformative field.

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

Similar content being viewed by others

References

  1. Bohnert T, Gan L-S. Plasma protein binding: from discovery to development. J Pharm Sci. 2013;102(9):2953–94.

    Article  CAS  PubMed  Google Scholar 

  2. Wallace S, Whiting B. Factors affecting drug binding in plasma of elderly patients. Br J Clin Pharmacol. 1976;3(2):327–30.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  3. Howard ML, Hill JJ, Galluppi GR, McLean MA. Plasma protein binding in drug discovery and development. Comb Chem High Throughput Screen. 2010;13(2):170–87.

    Article  CAS  PubMed  Google Scholar 

  4. Seyfinejad B, Ozkan SA, Jouyban A. Recent advances in the determination of unbound concentration and plasma protein binding of drugs: analytical methods. Talanta. 2021;225:122052.

    Article  CAS  PubMed  Google Scholar 

  5. Trainor GL. The importance of plasma protein binding in drug discovery. Expert Opin Drug Disc. 2007;2(1):51–64.

    Article  CAS  Google Scholar 

  6. Barigye SJ, de Freitas MP. Ten years of the MIA-QSAR strategy: historical development and applications. Int J Quant Struct-Prop Relationsh (IJQSPR). 2016;1(1):64–77.

    Article  CAS  Google Scholar 

  7. Bitencourt M, Freitas MP, Rittner R. The MIA-QSAR method for the prediction of bioactivities of possible acetylcholinesterase inhibitors. Archiv der Pharmazie. 2012;345(9):723–8.

    Article  CAS  PubMed  Google Scholar 

  8. Antunes JE, Freitas MP, da Cunha EF, Ramalho TC, Rittner R. In silico prediction of novel phosphodiesterase type-5 inhibitors derived from Sildenafil, Vardenafil and Tadalafil. Bioorg Med Chem. 2008;16(16):7599–606.

    Article  CAS  PubMed  Google Scholar 

  9. Matsuzaka Y, Uesawa Y. A molecular image-based novel quantitative structure-activity relationship approach, deepsnap-deep learning and machine learning. Curr Issues Mol Biol. 2021;42(1):455–72.

    PubMed  Google Scholar 

  10. Khaouane A, Ferhat S, Hanini S. A novel methodology for human plasma protein binding: prediction, validation, and applicability domain. Pharm Biomed Res. 2022;8(4):311–22.

    Article  CAS  Google Scholar 

  11. Li J, Yanagisawa K, Yoshikawa Y, Ohue M, Akiyama Y. Plasma protein binding prediction focusing on residue-level features and circularity of cyclic peptides by deep learning. Bioinformatics. 2022;38(4):1110–7.

    Article  CAS  PubMed  Google Scholar 

  12. Torng W, Altman RB. Graph convolutional neural networks for predicting drug-target interactions. J Chem Inf Model. 2019;59(10):4131–49.

    Article  CAS  PubMed  Google Scholar 

  13. Yuan Y, Chang S, Zhang Z, Li Z, Li S, Xie P, et al. A novel strategy for prediction of human plasma protein binding using machine learning techniques. Chemom Intell Lab Syst. 2020;199:103962.

    Article  CAS  Google Scholar 

  14. Venkatraman V. FP-ADMET: a compendium of fingerprint-based ADMET prediction models. J Cheminform. 2021;13(1):1–12.

    Article  CAS  Google Scholar 

  15. Lou C, Yang H, Wang J, Huang M, Li W, Liu G, et al. IDL-PPBopt: a strategy for prediction and optimization of human plasma protein binding of compounds via an interpretable deep learning method. J Chem Inf Model. 2022;62(11):2788–99.

    Article  CAS  PubMed  Google Scholar 

  16. Anderson PO, Knoben JE. Handbook of Clinical Drug Data. McGraw Hill; 2021.

  17. Goodman LS. Goodman and Gilman’s The Pharmacological Basis of Therapeutics. McGraw-Hill, New York; 1996.

  18. PubChem. (2022). Retrieved fromhttps://pubchem.ncbi.nlm.nih.gov/.

  19. Wishart DSKC, Guo AC, Shrivastava S, Hassanali M, Stothard P, Chang Z, Woolsey J. Drugbank: a comprehensive resource for in silico drug discovery and exploration. Nucleic Acids Res. 2006;34(Database issue):D668-72. 16381955.

    Article  CAS  PubMed  Google Scholar 

  20. ChemDraw Pro 12.0. PerkinElmer. Software.

  21. Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Adv Neural Inf Process. 2012;25.

  22. Lu S, Lu Z, Zhang Y-D. Pathological brain detection based on AlexNet and transfer learning. J Comput Sci. 2019;30:41–7.

    Article  Google Scholar 

  23. Khandani MK, Mikhael WB. A study on network size reduction using sparse input representation in time delay neural networks. 2020 IEEE 63rd International Midwest Symposium on Circuits and Systems (MWSCAS): IEEE; 2020. p. 864-7.

  24. Alippi C, Roveri M. Virtual k-fold cross validation: an effective method for accuracy assessment. The 2010 International Joint Conference on Neural Networks (IJCNN): IEEE; 2010. p. 1-6.

  25. Kubat M, Kubat J. An introduction to machine learning. Springer; 2017.

  26. Alexander DL, Tropsha A, Winkler DA. Beware of R 2: simple, unambiguous assessment of the prediction accuracy of QSAR and QSPR models. J Chem Inf Model. 2015;55(7):1316–22.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  27. MathWorks. MATLAB R2019b. Natick, Massachusetts: The MathWorks Inc., 2019.

  28. Sun L, Yang H, Li J, Wang T, Li W, Liu G, et al. In silico prediction of compounds binding to human plasma proteins by QSAR models. ChemMedChem. 2018;13(6):572–81.

    Article  CAS  PubMed  Google Scholar 

  29. Kumar R, Sharma A, Siddiqui MH, Tiwari RK. Prediction of drug-plasma protein binding using artificial intelligence based algorithms. Comb Chem High Throughput Screen. 2018;21(1):57–64.

    Article  CAS  PubMed  Google Scholar 

  30. Ghafourian T, Amin Z. QSAR models for the prediction of plasma protein binding. BioImpacts: BI. 2013;3(1):21.

    CAS  PubMed  PubMed Central  Google Scholar 

  31. Moda TL, Montanari CA, Andricopulo AD. In silico prediction of human plasma protein binding using hologram QSAR. Lett Drug Des Disc. 2007;4(7):502–9.

    Article  CAS  Google Scholar 

  32. Roy K, Kar S, Ambure P. On a simple approach for determining applicability domain of QSAR models. Chemom Intell Lab Syst. 2015;145:22–9.

    Article  CAS  Google Scholar 

  33. Hanser T, Barber C, Marchaland J, Werner S. Applicability domain: towards a more formal definition. SAR QSAR Environ Res. 2016;27(11):865–81.

    Article  CAS  Google Scholar 

  34. Sushko I, Novotarskyi S, Körner R, Pandey AK, Kovalishyn VV, Prokopenko VV, et al. Applicability domain for in silico models to achieve accuracy of experimental measurements. J Chemom. 2010;24(3–4):202–8.

    Article  CAS  Google Scholar 

  35. Organisation for Economic Co-operation and Development (OECD). Guidance Document on the Validation of (Quantitative) Structure-Activity Relationship [(Q)SAR] Models. OECD Series on Testing and Assessment, no69. Paris: OECD Publishing available from http://www.oecd.org.; 2014.

Download references

Funding

This research received no external funding. All costs associated with the study were borne by the authors. The absence of funding did not impact the design, execution, data analysis, interpretation, or the decision to submit the manuscript for publication.

Author information

Authors and Affiliations

  1. Laboratory of Biomaterial and Transport Phenomena (LBMPT), University of Médéa, pole urbain, 26000, Médéa, Algeria

    Affaf Khaouane, Latifa Khaouane, Samira Ferhat & Salah Hanini

Authors
  1. Affaf Khaouane
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Latifa Khaouane
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Samira Ferhat
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Salah Hanini
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

AK, LK, SF, and SH contributed significantly to the conception, design, execution, and interpretation of the research. The following is a detailed description of each author’s contributions:

Dr. AK:

  • Conceived and designed the study.

  • Collected and analyzed the data.

  • Interpreted the results and drafted the manuscript.

Pr. LK:

  • Assisted in the study’s design and data collection.

  • Contributed to data analysis and interpretation.

  • Reviewed and revised the manuscript critically for important intellectual content.

Pr. SF:

  • Provided substantial input during the study design phase.

  • Assisted in data interpretation and critically reviewed the manuscript.

Pr. SH:

  • Contributed to data collection and analysis.

  • Assisted in drafting and revising the manuscript.

All authors have read and approved the final version of the manuscript and take public responsibility for its content. The order of authorship reflects their relative contributions to the research and writing process.

Corresponding author

Correspondence to Affaf Khaouane.

Ethics declarations

Conflict of Interest

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.

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

Khaouane, A., Khaouane, L., Ferhat, S. et al. Deep Learning for Drug Development: Using CNNs in MIA-QSAR to Predict Plasma Protein Binding of Drugs. AAPS PharmSciTech 24, 232 (2023). https://doi.org/10.1208/s12249-023-02686-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1208/s12249-023-02686-6

Keywords

Search

Navigation