Gribova, Varvara (University of Strasbourg)


Layer-by-layer (LbL) coating is a method for surface modification based on the electrostatic interactions between two polyelectrolytes. LbL coatings are used for multiple biomedical applications, because natural polyelectrolytes presenting good biocompatibility can be used for LbL film build-up. It is possible to develop antibacterial surfaces, smart healing materials, and coatings for tissue engineering. Moreover, LbL coatings can be used for loading drugs or other bioactive molecules, which allows their local delivery. Even though the mechanisms of LbL film development are well-established, the empirical manner of polycation/polyanion selection is an impediment on rapid new coating development, while the current health crisis has shown the importance of accelerated development of biomedical solutions such as antiviral coatings.

In this work, we hypothesize that using the current state of the art data science techniques, we can determine how different parameters affect coating thickness and predict the thickness of the new coatings. To do so, we used historical and generated data for predictive model development using machine learning, an approach which uses algorithms that improve upon training on large datasets and is able to find complex patterns, make predictions and decisions.

Using literature data and newly generated experimental results, we first analyzed the relative impact of 23 coating parameters on the coating thickness. Next, a predictive model has been developed using aforementioned parameters and molecular descriptors of polymers from DeepChem library. Model performance was limited because of insufficient number of data points in the training set, due to the scarce availability of data in the literature.

We demonstrate, for the first time, utilization of machine learning for prediction of LbL coating properties (1). It can decrease the time necessary to obtain functional coating with desired properties, as well as decrease experimental costs and enable the fast first response to crisis situations (such as pandemics) where coatings can positively contribute. Besides coating thickness, which was selected as an output value in this study, machine learning approach can be potentially used to predict functional properties of multilayer coatings, e.g. biocompatibility, cell adhesive, antibacterial, antiviral or anti-inflammatory properties.

1. Gribova, V. et al., Sci. Rep. 11, 18702 (2021)"


Presentation materials

There are no materials yet.