Smart design nano-hybrid formulations by machine learning

Raquel Barbosa; Gabriel Câmara; Fabio Veritate; Tulio Moura; Fernanda Raffin; Marcelo Fernandes

doi:10.3390/IECP2020-08700

Abstract:

Nano-hybrid systems have been presented as an attractive platform for drug delivery. These systems combine organic and inorganic materials in self-assembled structures¹. Laponite (inorganic network, LAP) nanoparticles are disk-like synthetic clays, biocompatible and guest compounds have been explored for hybridization with polymers or small molecules to improve to attach drugs^2–4. Poloxamines (organic compound) are an amphiphilic four-arm (X-shape) block copolymers of poly(ethylene oxide)-poly (propylene oxide)-poly(ethylene oxide) with a pH-sensitive and thermosensitive properties, being very attractive as a drug delivery system^5,6. In this context, this work aimed to prepare and compared nano-hybrid formulation by physical behavior assays and their ability to increase the solubility of the βLAP, a low solubility drug model. The methodology of analysis of data used in this work consisted of Multilayer Perceptron (MLP), Support Vector Machine (SVM), both machine learning (ML) models^7–9. However, response surface analysis (RMS) was also used and compared with other methods applied. The samples were prepared by mixing the components at different concentrations (1-20%, w/w) plus LAP (0-3%, w/w). The βLAP was added in excess in all formulations. The ML techniques obtained better correlation coefficients adjustment than RSM. In addition, RSM techniques use only predefined regression models. ML's response surfaces are generated from a training process based on experimental data that it is a tremendous advantage compared to RMS¹⁰. All methods (RMS, SVM, and MLP) show T1304 (over 10%) and 1.5% LAP, or systems with only LAP (1.5%), with a 50 and 100-fold increase in βLAP solubilisation, respectively. Further, the models provided a second-order polynomial equation to predict the βLAP solubility in different blends concentrations. In silico tools promoted a fine-tuning and near experimental data shown to be an excellent strategy for use in the development of news nano-hybrid platforms.

References

1. Faustini, M.; Nicole, L.; Ruiz-Hitzky, E.; Sanchez, C. History of Organic–Inorganic Hybrid Materials: Prehistory, Art, Science, and Advanced Applications. Advanced Functional Materials 2018, 28 (27), 1704158.

2. Aguzzi, C.; Cerezo, P.; Viseras, C.; Caramella, C. Use of Clays as Drug Delivery Systems: Possibilities and Limitations. Applied Clay Science 2007, 36 (1–3), 22–36.

3. Haraguchi, K.; Farnworth, R.; Ohbayashi, A.; Takehisa, T. Compositional Effects on Mechanical Properties of Nanocomposite Hydrogels Composed of Poly (N, N-Dimethylacrylamide) and Clay. Macromolecules 2003, 36 (15), 5732–5741.

4. Chang, C.-W.; van Spreeuwel, A.; Zhang, C.; Varghese, S. PEG/Clay Nanocomposite Hydrogel: A Mechanically Robust Tissue Engineering Scaffold. Soft Matter 2010, 6 (20), 5157–5164

5. Schmolka, I. R. A Review of Block Polymer Surfactants. Journal of the American Oil Chemists’ Society 1977, 54 (3), 110–116.

6. Alexandridis, P. Poly (Ethylene Oxide)/Poly (Propylene Oxide) Block Copolymer Surfactants. Current opinion in colloid & interface science 1997, 2 (5), 478–489.

7. Pereira, A. K. V.; Barbosa, R. de M.; Fernandes, M. A. C.; Finkler, L.; Finkler, C. L. L. Comparative Analyses of Response Surface Methodology and Artificial Neural Networks on Incorporating Tetracaine into Liposomes. Brazilian Journal of Pharmaceutical Sciences 2020, 56.

8. Sun, Y.; Peng, Y.; Chen, Y.; Shukla, A. J. Application of Artificial Neural Networks in the Design of Controlled Release Drug Delivery Systems. Advanced Drug Delivery Reviews 2003, 55 (9), 1201–1215.

9. Ekins, S.; Puhl, A. C.; Zorn, K. M.; Lane, T. R.; Russo, D. P.; Klein, J. J.; Hickey, A. J.; Clark, A. M. Exploiting Machine Learning for End-to-End Drug Discovery and Development. Nature materials 2019, 18 (5), 435.

10. Che Sulaiman, I. S.; Basri, M.; Fard Masoumi, H. R.; Ashari, S. E.; Basri, H.; Ismail, M. Predicting the Optimum Compositions of a Transdermal Nanoemulsion System Containing an Extract of Clinacanthus Nutans Leaves (L.) for Skin Antiaging by Artificial Neural Network Model. Journal of Chemometrics 2017, 31 (7), e2894.