2023/10/17 by Ferrari, Brenda S., Manica, Matteo, Giro, Ronaldo +2 · 1 citation
#Chemical Physics (physics.chem-ph) #FOS: Physical sciences #Materials Science (cond-mat.mtrl-sci)
paper · doi:10.48550/arxiv.2310.11423
Polymers 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 the first extension of transformer-based language models to polymerization reactions for both forward 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 and retro-synthesis examples and evaluate its prediction quality from a materials science perspective.