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.
Similar content being viewed by others
References
Bohnert T, Gan L-S. Plasma protein binding: from discovery to development. J Pharm Sci. 2013;102(9):2953–94.
Wallace S, Whiting B. Factors affecting drug binding in plasma of elderly patients. Br J Clin Pharmacol. 1976;3(2):327–30.
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.
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.
Trainor GL. The importance of plasma protein binding in drug discovery. Expert Opin Drug Disc. 2007;2(1):51–64.
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.
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.
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.
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.
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.
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.
Torng W, Altman RB. Graph convolutional neural networks for predicting drug-target interactions. J Chem Inf Model. 2019;59(10):4131–49.
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.
Venkatraman V. FP-ADMET: a compendium of fingerprint-based ADMET prediction models. J Cheminform. 2021;13(1):1–12.
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.
Anderson PO, Knoben JE. Handbook of Clinical Drug Data. McGraw Hill; 2021.
Goodman LS. Goodman and Gilman’s The Pharmacological Basis of Therapeutics. McGraw-Hill, New York; 1996.
PubChem. (2022). Retrieved fromhttps://pubchem.ncbi.nlm.nih.gov/.
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.
ChemDraw Pro 12.0. PerkinElmer. Software.
Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Adv Neural Inf Process. 2012;25.
Lu S, Lu Z, Zhang Y-D. Pathological brain detection based on AlexNet and transfer learning. J Comput Sci. 2019;30:41–7.
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.
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.
Kubat M, Kubat J. An introduction to machine learning. Springer; 2017.
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.
MathWorks. MATLAB R2019b. Natick, Massachusetts: The MathWorks Inc., 2019.
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.
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.
Ghafourian T, Amin Z. QSAR models for the prediction of plasma protein binding. BioImpacts: BI. 2013;3(1):21.
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.
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.
Hanser T, Barber C, Marchaland J, Werner S. Applicability domain: towards a more formal definition. SAR QSAR Environ Res. 2016;27(11):865–81.
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.
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.
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
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
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.
About this article
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
Received:
Accepted:
Published:
DOI: https://doi.org/10.1208/s12249-023-02686-6