Polygrammar: Grammar for Digital Polymer Representation and Generation

Abstract

Polymers are widely studied materials with diverse properties and applications determined by molecular structures. It is essential to represent these structures clearly and explore the full space of achievable chemical designs. However, existing approaches cannot offer comprehensive design models for polymers because of their inherent scale and structural complexity. Here, a parametric, context-sensitive grammar designed specifically for polymers (PolyGrammar) is proposed. Using the symbolic hypergraph representation and 14 simple production rules, PolyGrammar can represent and generate all valid polyurethane structures. An algorithm is presented to translate any polyurethane structure from the popular Simplified Molecular-Input Line-entry System (SMILES) string format into the PolyGrammar representation. The representative power of PolyGrammar is tested by translating a dataset of over 600 polyurethane samples collected from the literature. Furthermore, it is shown that PolyGrammar can be easily extended to other copolymers and homopolymers. By offering a complete, explicit representation scheme and an explainable generative model with validity guarantees, PolyGrammar takes an essential step toward a more comprehensive and practical system for polymer discovery and exploration.As the first bridge between formal languages and chemistry, PolyGrammar also serves as a critical blueprint to inform the design of similar grammars for other chemistries, including organic and inorganic molecules.

Computational Approaches for Organic Semiconductors: From Chemical and Physical Understanding to Predicting New Materials

“…The model generated a distribution of molecules with a mean T1 of 3.02 eV, with over 58% of molecules satisfying the target condition, as shown in Figure . Recent generative models , are using SELFIES instead of SMILES, as the validity of SELFIES is always guaranteed but not SMILES. Generative models based on flow, − diffusion,, and generative adversarial networks (GANs) − are used in molecular design, but their application in the discovery of OSC materials is currently limited.…”

Emerging Trends in Machine Learning: A Polymer Perspective

“…57 More recently, PolyGrammar was developed to describe polyurethanes using a hypergraph representation. 58 However, there is not yet a method to generate fingerprints that encode the stochasticity for all varieties of polymers. The issue of polymer stochasticity is acute for copolymers, polyolefins, and complicated polymer architectures.…”

“…A key advance in capturing the stochasticity of polymers is the development of an extension of simplified molecular-input line-entry system (SMILES) to polymers known as BigSMILES, as shown in Figure . More recently, PolyGrammar was developed to describe polyurethanes using a hypergraph representation . However, there is not yet a method to generate fingerprints that encode the stochasticity for all varieties of polymers.…”

An extensible platform for enabling artificial intelligence guided design of catalysts and materials

“…40 PolyGrammar was developed to facilitate both representation and generation of polymer structures through a context-sensitive grammar that combines a hypergraph representation and production rules to create polymer structures, however is currently implemented for only polyurethane structures. 41 Other approaches have focused on representing the polymeric structures as graphs, with nodes on the graph defined by SMILES and edges defining the stochastic connections. 7,42,43 For all polymer structural representation systems, its relationship with experimentally measured property values in the overall data structure is highly important for fully defining the stochastic properties of the polymer itself and establishing structure-property relationships.…”

“…1,10,14,15,60 Much of the focus of generative modeling for polymer structures has been on homopolymers 10,14,60 or simple copolymers derived from polycondensation or polyaddition reactions. 15,41 Additionally, relatively few of these studies have carried out subsequent experimental synthesis and validation of the generated structures. 15 Thus, while existing reports are successful in generating new repeat units for polymer structures, there is no guarantee that these generated polymers are experimentally accessible.…”