AI-Driven Materials Genome Strategy Accelerates Development of High-Performance Polyimide Films
Researchers have developed an AI-assisted materials-genome approach that rapidly designs ultra-tough polyimide films with balanced mechanical properties, potentially transforming aerospace and electronics manufacturing.
Materials scientists have long struggled to balance stiffness, strength, and toughness in thermosetting polyimide films, where improving one property typically compromises others. Traditional trial-and-error synthesis approaches have proven slow, costly, and limited in exploring complex molecular spaces. A research team from East China University of Science and Technology has now developed an AI-assisted materials-genome approach that enables rapid design of high-performance thermosetting polyimides with superior mechanical properties.
The study, published online on September 2, 2025, in the Chinese Journal of Polymer Science (DOI: 10.1007/s10118-025-3403-x), introduces a machine-learning model capable of predicting three key mechanical parameters—Young's modulus, tensile strength, and elongation at break—across thousands of candidate structures. By treating polymer structural fragments as molecular "genes," the researchers defined a vast chemical space of 1,720 phenylethynyl-terminated polyimides and used Gaussian process regression models trained on over 120 experimental datasets to screen for optimal combinations.
The approach successfully identified a new formulation called PPI-TB, whose performance surpassed well-known benchmark polyimides. The models achieved high predictive accuracy for all three mechanical metrics and were used to score every candidate for comprehensive mechanical performance. Molecular dynamics simulations validated the screening, showing that PPI-TB exhibited superior modulus, toughness, and strength indicators compared with established systems. Subsequent laboratory experiments on representative polyimides confirmed strong consistency between predicted and measured data.
Further analysis revealed key design principles: conjugated aromatic structures enhance stiffness, heteroatoms and heterocycles strengthen molecular interactions, and flexible silicon- or sulfur-containing units improve elongation. These insights demonstrate how integrating AI predictions with molecular interpretation can uncover structure-property relationships and accelerate polymer innovation. The original research is available at https://doi.org/10.1007/s10118-025-3403-x.
"By translating polymer fragments into genetic-like descriptors, we can treat molecular design like decoding a genome," said Prof. Li-Quan Wang, one of the corresponding authors of the study. "Machine learning not only predicts performance but also reveals which chemical 'genes' are driving it. This synergy between data science and chemistry allows us to explore material possibilities that would take decades by conventional means."
The implications for industry are substantial. Polyimide films are essential components in aerospace, flexible electronics, and micro-display technologies due to their thermal stability and insulation properties. The AI-driven materials-genome strategy provides a universal, scalable framework for designing polymers with targeted combinations of stiffness, strength, and flexibility—traits critical for microelectronics, aerospace composites, and flexible circuit substrates. By replacing years of experimental iteration with predictive modeling and virtual screening, this method drastically reduces development costs and time cycles. Beyond polyimides, the workflow could be adapted for other high-performance polymer classes, guiding the creation of lightweight, durable, and thermally stable materials that power future electronic and aerospace technologies.