Predicting polymerization reactions via transfer learning using chemical language models

• DOI: 10.1038/s41524-024-01304-8
• Publication Date: 2024-06-04T15:28:02Z
• Authors: Brenda S. Ferrari; Matteo Manica; Ronaldo Giro; Teodoro Laino; Mathias B. Steiner
• Keywords: Chemical Physics (physics.chem-ph); QA76.75-76.765; Condensed Matter - Materials Science; Physics - Chemical Physics; TA401-492; Materials Science (cond-mat.mtrl-sci); FOS: Physical sciences; Computer software; 02 engineering and technology; 0210 nano-technology; Materials of engineering and construction. Mechanics of materials

AbstractPolymers are candidate materials for a wide range of sustainability applications such as carbon capture and energy storage. However, computational polymer discovery lacks automated analysis of reaction pathways and stability assessment through retro-synthesis. Here, we report an extension of transformer-based language models to polymerization for both reaction and retrosynthesis tasks. To that end, we have curated a polymerization dataset for vinyl polymers covering reactions and retrosynthesis for representative homo-polymers and co-polymers. Overall, we obtain a forward model Top-4 accuracy of 80% and a backward model Top-4 accuracy of 60%. We further analyze the model performance with representative polymerization examples and evaluate its prediction quality from a materials science perspective. To enable validation and reuse, we have made our models and data available in public repositories.