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.
Sign in to start a discussion.
More Papers Like This
Machine Learning-Driven Multi-Objective Optimization of Enzyme Combinations for Plastic Degradation: An Ensemble Framework Integrating Sequence Features and Network Topology
Researchers developed a machine learning framework to identify optimal enzyme combinations for breaking down polyester plastics. The study integrated kinetic data, protein sequence features, and network analysis to predict effective enzyme-substrate relationships, offering a computational approach to accelerating the discovery of enzymatic solutions for plastic waste degradation.
Revealing factors influencing polymer degradation with rank-based machine learning
Researchers developed a machine learning platform using a ranking-based algorithm to predict and compare how easily different polymer materials biodegrade, integrating three different experimental datasets with varying conditions. Analysis revealed key molecular factors that control degradability, offering guidance for designing more environmentally friendly plastics.
De Novo Design of Multiple Microplastic-Binding Peptideswith a Protein Language Model-Guided Generative Adversarial Network
Researchers used a protein language model combined with a generative adversarial network to design novel peptides predicted to bind multiple types of plastic simultaneously. The AI-generated peptides showed high predicted affinity for polystyrene, polyethylene terephthalate, and polyethylene, offering a new eco-friendly approach for detecting or capturing mixed-plastic microplastic pollution.
Feasibility of Utilizing Machine Learning to Identify a More Sustainable Alternative to Polyester in Textiles
Researchers used machine learning trained on the PI1M polymer dataset of over one million compounds to identify sustainable alternatives to polyester in textiles, predicting key material properties including glass transition temperature, density, melting temperature, oxygen permeability, and bulk modulus. The study found that artificial neural networks could screen polymer candidates for environmental compatibility while maintaining performance characteristics comparable to polyester.
Machine intelligence-accelerated discovery of all-natural plastic substitutes
Researchers combined robotics and machine learning to rapidly discover biodegradable plastic substitutes made entirely from natural ingredients, using an automated system to test 286 material combinations and build a predictive model that can design new materials to order. This approach dramatically speeds up the search for alternatives to petroleum-based plastics that contribute to microplastic pollution.