PolyGLOT: Graph-Token Language Modeling for Unified Polymer Property Prediction and Programmable Generation
- 1Department of Mechanical Engineering
- 2University of Wisconsin–Madison Madison
Abstract
Polymer design benefits from representations that combine efficient sequence modeling with explicit access to molecular graph structure. String representations provide compact sequences but most remain sensitive to syntax and connectivity errors, whereas sequential graph generation becomes more costly as molecular graphs grow. We introduce PolyGLOT (Polymer Graph Language of Tokens), which represents a linear homopolymer repeat unit as a reconstructable sequence of mostly small molecular subgraphs. A graph encoder embeds each graph token, and a common Transformer backbone is pretrained by masked-token prediction and subsequently fine-tuned for property prediction or causal generation. PolyGLOT achieves competitive property-prediction performance while learning a hierarchy from local graph chemistry to context-dependent token states and property-organized polymer representations. Its attachment-constrained decoder produces valid repeat-unit graphs by construction, and the typically small token size makes local graph operations tractable. Beyond direct generation, the same graph-token interface supports expansion beyond the fixed vocabulary, property-guided local editing, required-substructure control, and small-molecule structural-precedent analysis. These results show that PolyGLOT provides a unified and extensible representation for polymer property prediction, generation, and downstream design.
Related
- A 1-Bit Programmable Transmissive Metasurface for Far-Field Holography and Near-Field OAM Generation
- Lost in Chemical Space: Local Open-Source Large Language Models Display Model-Dependent Adherence to Reference Data in Molecular Generation
- The Limited Contribution of Structural Information Relative to Language-Model Signal in Data-Limited Cryptic Pocket Prediction
- How Chemical Evidence Shapes Mechanistic Reasoning and Prediction by Large Language Models: Fine-Grained Inference in Nucleoside-Derived Supramolecular Gelation
- Bridging the Literature-to-Laboratory Gap with Language Models and Active Learning for Reaction Feasibility Prediction and Autonomous Exploration
BibTeX
@misc{yue2026polyglot,
title = {{PolyGLOT: Graph-Token Language Modeling for Unified Polymer Property Prediction and Programmable Generation}},
author = {Tianle Yue and Ying Li},
howpublished = {ChemRxiv},
year = {2026},
month = sep,
doi = {10.26434/chemrxiv.15008299/v1},
url = {https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008299/v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - PolyGLOT: Graph-Token Language Modeling for Unified Polymer Property Prediction and Programmable Generation
AU - Tianle Yue
AU - Ying Li
PY - 2026
DA - 2026/09/04
PB - ChemRxiv
DO - 10.26434/chemrxiv.15008299/v1
UR - https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008299/v1
AB - Polymer design benefits from representations that combine efficient sequence modeling with explicit access to molecular graph structure. String representations provide compact sequences but most remain sensitive to syntax and connectivity errors, whereas sequential graph generation becomes more costly as molecular graphs grow. We introduce PolyGLOT (Polymer Graph Language of Tokens), which represents a linear homopolymer repeat unit as a reconstructable sequence of mostly small molecular subgraphs. A graph encoder embeds each graph token, and a common Transformer backbone is pretrained by masked-token prediction and subsequently fine-tuned for property prediction or causal generation. PolyGLOT achieves competitive property-prediction performance while learning a hierarchy from local graph chemistry to context-dependent token states and property-organized polymer representations. Its attachment-constrained decoder produces valid repeat-unit graphs by construction, and the typically small token size makes local graph operations tractable. Beyond direct generation, the same graph-token interface supports expansion beyond the fixed vocabulary, property-guided local editing, required-substructure control, and small-molecule structural-precedent analysis. These results show that PolyGLOT provides a unified and extensible representation for polymer property prediction, generation, and downstream design.
ER -