Developing a Suitable Model for Water Uptake for Biodegradable Polymers Using Small Training Sets

Abstract

Prediction of the dynamic properties of water uptake across polymer libraries can accelerate polymer selection for a specific application. We first built semiempirical models using Artificial Neural Networks and all water uptake data, as individual input. These models give very good correlations (R 2 > 0.78 for test set) but very low accuracy on cross-validation sets (less than 19% of experimental points within experimental error). Instead, using consolidated parameters like equilibrium water uptake a good model is obtained (R 2 = 0.78 for test set), with accurate predictions for 50% of tested polymers. The semiempirical model was applied to the 56-polymer library of L-tyrosine-derived polyarylates, identifying groups of polymers that are likely to satisfy design criteria for water uptake. This research demonstrates that a surrogate modeling effort can reduce the number of polymers that must be synthesized and characterized to identify an appropriate polymer that meets certain performance criteria.

Prediction of Broad-Spectrum Pathogen Attachment to Coating Materials for Biomedical Devices

“…We generated 3839 constitutional, structural, and physicochemical descriptors that were dependent only on 2D structures. We and others − have shown that consideration of monomer or small oligomer structures alone can often provide good descriptions of polymer performance without consideration of other structural properties such as molecular weight, polydispersity, degree of branching copolymer block size, etc. Copolymer descriptors were calculated as a linear combination of monomer descriptors weighted by the proportion of each monomer in the copolymer .…”

Statistical degradation modelling of Poly(D,L-lactide-co-glycolide) copolymers for bioscaffold applications

“…In fact, we have to ensure that the scaffolds adequately replace the functions of tissues. It is also important to note that modelling can be useful to minimize the amount of experiments needed for characterizing a polymer library [ 33 ]. This can be tacked by applying statistical modelling, taking into account that polymer degradation is depended on multiple factors whose influence have to be accurately determined [ 34 , 35 ].…”

Adhesive and biodegradable membranes made of sustainable catechol-functionalized marine collagen and chitosan

“…Polar components lower than 5 mN m -1 are related to moderate cell spreading, whereas polar components higher than 15 mN m -1 favor cell spreading [39], suggesting that the blended membranes would promote cellular attachment. Another important parameter of biomaterials is their water uptake, which influences the material degradation, mechanical and adhesive properties, as well as biological response [40]. Moreover, the water uptake of a TE construct is important from an application point of view as it shows the ability of a construct to adsorb body fluids and transport nutrients to the site of implantation.…”

“…Degradation is also an important parameter to take into account for any material for tissue engineering, once the device should preserve its structural and mechanical integrity during the time needed for a specific tissue repair and then should be degraded progressively [40]. The in vitro degradation behavior of the membranes was studied for 60 days (Fig.…”