We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
A machine learning approach to designing tough and degradable polyamides based on multiblock structures
Summary
Researchers applied Gaussian process regression and multi-objective machine learning optimization to design multiblock polyamides composed of Nylon6 and alpha-amino acid segments that simultaneously achieve high toughness and biodegradability. The approach successfully identified amino acid sequences yielding polymers with both desirable mechanical properties and degradability, demonstrating a data-driven pathway for overcoming the trade-off between performance and environmental sustainability in biodegradable plastics.
The development of environmentally friendly plastics is receiving renewed attention for a sustainable society. The trade-off between toughness and degradability is one of the issues associated with biodegradable polymers, which prevents these materials from being broadly utilised. However, designing biodegradable polymers that overcome these issues is often difficult. In this study, we demonstrate that machine-learning techniques can contribute to the development of multiblock polyamides composed of Nylon6 and alpha-amino acid segments that are satisfactorily mechanically tough and degradable. Multi-objective optimisation based on Gaussian process regression suggested appropriate alpha-amino acid sequences for polyamides endowed with both properties. Physical factors associated with the sequence as well as higher-order multiblock-derived structures were revealed to be essential for endowing these polymers with satisfactory properties. Furthermore, these materials are degradable in natural muddy water. Our method provides a useful approach for designing and understanding environmentally friendly plastics and other materials with multiple properties.