Screening Diels-Alder reaction space to identify candidate reactions for self-healing polymer applications

Plastics are essential in modern society, but their susceptibility to damage limits their lifespan and performance, and results in unsustainable waste production. Self-healing polymers based on thermally reversible Diels-Alder (DA) reactions offer a potential solution by enabling thermally controlled repair through bond-breaking and reformation. However, discovering new suitable DA monomer combinations has largely relied on intuition and trial-and-error so far. Here, we present two dataset of DA reactions obtained at xTB and M06-2X/def2-TZVP level, counting 23,327 and 1,582 reactions (geometries of the monomers, transitions and products) respectively.

These datasets enabled use to develop a hierarchical workflow that integrates machine learning (ML) with automated reaction profile calculations to efficiently screen DA reactions for self-healing polymer applications. Using our in-house TS-tools software, we generate high-throughput reaction profiles at the semi-empirical xTB level. Refining only a small fraction with DFT, we are able to train an ML model that predicts reaction characteristics with almost chemical accuracy. Adding a graph-based ML model to the workflow for pre-screening enables expansion to reaction spaces of hundreds of thousands, even millions, of reactions, at a marginal cost. Finally, we leverage our model to screen a diverse database of commercially available natural products and identify a wide range of promising diene-dienophile combinations. Overall, this hybrid ML–computational chemistry approach enables data-efficient discovery of thermally responsive DA reactions, advancing the rational design of self-healing polymers with tunable properties.

For more details on the generation of the datasets and the results obtained for their analysis, see: DOI: