AI-Driven Materials Genome Strategy Accelerates Design of High-Performance Polyimide Films

Materials scientists have long struggled to balance competing mechanical properties in thermosetting polyimide films, where improving stiffness often reduces toughness and enhancing one characteristic typically compromises others. A research team from East China University of Science and Technology has developed an AI-assisted materials-genome approach that enables rapid design of high-performance thermosetting polyimides with simultaneously high Young's modulus, tensile strength, and elongation at break.

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 across thousands of candidate structures. The researchers treated polymer structural fragments—dianhydride, diamine, and end-capping units—as molecular "genes," defining a vast chemical space of 1,720 phenylethynyl-terminated polyimides. This genomic approach allowed them to screen and identify optimal formulations with balanced mechanical performance.

The team constructed Gaussian process regression models trained on over 120 experimental datasets of polyimide films, achieving high predictive accuracy (R² ≈ 0.70–0.74) for all three mechanical metrics. The models scored every candidate for comprehensive mechanical performance, leading to the identification of a new formulation called PPI-TB. Molecular dynamics simulations validated the screening results, showing that PPI-TB exhibited superior modulus (3.48 GPa), toughness, and strength indicators compared with established benchmark polyimides PETI-1 and O-O-3. Subsequent laboratory experiments on representative polyimides confirmed strong consistency between predicted and measured data.

Further analysis revealed key design principles driving the material performance. Conjugated aromatic structures were found to enhance stiffness, heteroatoms and heterocycles strengthened molecular interactions, and flexible Si- or S-containing units improved 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.

This AI-driven materials-genome strategy provides a universal, scalable framework for designing polymers with targeted combinations of stiffness, strength, and flexibility—traits essential to microelectronics, aerospace composites, and flexible circuit substrates. Polyimide films are critical components in aerospace, flexible electronics, and micro-display technologies due to their thermal stability and insulation properties. By replacing years of experimental iteration with predictive modeling and virtual screening, this method drastically reduces development costs and time cycles.

The implications for multiple industries are substantial. In aerospace, where lightweight, durable materials are paramount, this approach could accelerate the development of advanced composites for aircraft and spacecraft components. For flexible electronics and micro-display technologies, the ability to rapidly design polyimides with optimal mechanical properties could enable new generations of bendable screens, wearable devices, and advanced circuit substrates. Beyond polyimides, the workflow could be adapted for other high-performance polymer classes, guiding the creation of thermally stable materials that power future electronic and aerospace technologies.

This research represents a significant advancement in materials science methodology, demonstrating how artificial intelligence and genomic approaches can transform traditional discovery processes. The integration of machine learning with molecular design not only predicts performance but also reveals the fundamental chemical principles driving material behavior, opening new possibilities for accelerated innovation across multiple high-tech industries.