Periodic Topological Deep Learning for Polymer Design and Discovery

2026-05-26

AI Summary

Traditional machine learning struggles to effectively model the periodic structures and many-body interactions inherent in polymers, limiting efficient exploration across vast chemical spaces. This work proposes a deep learning framework based on periodic Vietoris–Rips complexes, employing a hierarchical simplicial message passing (HSMP) encoder to explicitly integrate multiscale higher-order topological features. For the first time, this approach incorporates both periodic topology and high-order interactions into polymer representations, overcoming the limitations of conventional graph neural networks that rely solely on monomer identities and bonding information. The method significantly outperforms existing models in predicting electronic, optical, physical, and thermal properties, and successfully predicts—and experimentally validates—the enhancement of glass transition temperature through ester–amide substitution and α-methylation.

Abstract

Polymers underpin applications across energy, healthcare, and materials science, yet their vast chemical space makes systematic discovery challenging. Most machine learning approaches represent polymers as molecular graphs of a single repeating unit, thereby missing both the periodicity of polymer chains and many-body interactions beyond pairwise bonds. We introduce Periodic-TDL, a deep learning framework built on periodic Vietoris-Rips complexes that capture many-body interactions across multiple spatial scales, followed by a hierarchical simplicial message-passing (HSMP) encoder that propagates information from long-range interactions to covalent bonds, yielding representations enriched by higher-order topological features. Periodic-TDL outperforms all state-of-the-art models across polymer property prediction tasks spanning electronic, optical, physical, and thermal targets. Furthermore, we quantitatively validate how ester-to-amide substitution and $α$-methylation enhance thermal stability. Using a computationally synthesized dataset of 48,208 structures-generated via systematic substitution of acrylate and acrylamide polymers-we observed a mean $T_g$ increase of $\sim 55^\circ$C for ester-to-amide substitutions and $\sim 14^\circ$C for backbone $α$-methylation across matched polymer pairs. To verify these predicted trends, we use our Periodic-TDL model to analyze six novel polymer pairs from independent experimental measurements, including three newly synthesized polymers previously unreported in the literature. The experimental data successfully confirmed the model's predictions. Ultimately, these findings demonstrate that Periodic-TDL captures the underlying physical effects of specific functional group modifications, rather than merely optimizing predictive performance on benchmark datasets.

Problem

• polymer design
• periodicity
• many-body interactions
• topological representation
• property prediction

Innovation

• Periodic Topological Deep Learning
• Vietoris-Rips complexes
• many-body interactions
• hierarchical simplicial message-passing
• polymer property prediction