Can I read Predictive Modeling as a Tool to Assess Polymer–polymer and Polymer–drug Interactions for Tissue Engineering Applications on EtoBox?

Predictive Modeling as a Tool to Assess Polymer–polymer and Polymer–drug Interactions for Tissue Engineering Applications by Lakshmi Yaneesha Sujeeun; Nowsheen Goonoo; Kaylina Marie Moutou; Shakuntala Baichoo; Archana Bhaw-Luximon is a scholarly article available to read on EtoBox.

What is Predictive Modeling as a Tool to Assess Polymer–polymer and Polymer–drug Interactions for Tissue Engineering Applications about?

The success of tissue engineering scaffolds for wound healing relies on balanced physicochemical properties and the addition of small molecules. These two require an in-depth understanding of the interactions between the different components of the scaffolds for favorable and synergistic actions. Thus, the choice of polymeric blends is crucial to tune the properties of the resulting scaffolds. Miscibility of the polymer blends can be used to assess polymer-polymer interactions for effective scaffold engineering and cell-material interactions. The focus of this study was to apply machine learning (ML) methods to classify and predict the miscibility of polymer blends, namely poly(hydroxybutyrate-co-valerate)/fucoidan (PHBV/FUC), polyhydroxybutyrate/kappa-carrageenan (PHB/KCG), and cellulose acetate/polyamide (CA/PA). Physicochemical parameters assessed through Fourier transform infrared spectroscopy (FTIR), thermal analysis, and mechanical properties were used as input data. Depending on blend film compositions, the polymers were either partially miscible or completely immiscible. Six supervised classification algorithms were trained on the data with Scikit-learn. The random forest c

Author

Lakshmi Yaneesha Sujeeun; Nowsheen Goonoo; Kaylina Marie Moutou; Shakuntala Baichoo; Archana Bhaw-Luximon

Publisher

Springer Science and Business Media LLC

Published

2023

Language

EN