An Encoder-Decoder Foundation Chemical Language Model for Generative Polymer Design
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917030800654336 |
|---|---|
| author | Sahu, Harikrishna Xiong, Wei Savit, Anagha Shukla, Shivank S Ramprasad, Rampi |
| author_facet | Sahu, Harikrishna Xiong, Wei Savit, Anagha Shukla, Shivank S Ramprasad, Rampi |
| contents | Traditional machine learning has advanced polymer discovery, yet direct generation of chemically valid and synthesizable polymers without exhaustive enumeration remains a challenge. Here we present polyT5, an encoder-decoder chemical language model based on the T5 architecture, trained to understand and generate polymer structures. polyT5 enables both property prediction and the targeted generation of polymers conditioned on desired property values. We demonstrate its utility for dielectric polymer design, seeking candidates with dielectric constant >3, bandgap >4 eV, and glass transition temperature >400 K, alongside melt-processability and solubility requirements. From over 20,000 generated promising candidates, one was experimentally synthesized and validated, showing strong agreement with predictions. To further enhance usability, we integrated polyT5 within an agentic AI framework that couples it with a general-purpose LLM, allowing natural language interaction for property prediction and generative design. Together, these advances establish a versatile and accessible framework for accelerated polymer discovery. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_18860 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | An Encoder-Decoder Foundation Chemical Language Model for Generative Polymer Design Sahu, Harikrishna Xiong, Wei Savit, Anagha Shukla, Shivank S Ramprasad, Rampi Materials Science Soft Condensed Matter Traditional machine learning has advanced polymer discovery, yet direct generation of chemically valid and synthesizable polymers without exhaustive enumeration remains a challenge. Here we present polyT5, an encoder-decoder chemical language model based on the T5 architecture, trained to understand and generate polymer structures. polyT5 enables both property prediction and the targeted generation of polymers conditioned on desired property values. We demonstrate its utility for dielectric polymer design, seeking candidates with dielectric constant >3, bandgap >4 eV, and glass transition temperature >400 K, alongside melt-processability and solubility requirements. From over 20,000 generated promising candidates, one was experimentally synthesized and validated, showing strong agreement with predictions. To further enhance usability, we integrated polyT5 within an agentic AI framework that couples it with a general-purpose LLM, allowing natural language interaction for property prediction and generative design. Together, these advances establish a versatile and accessible framework for accelerated polymer discovery. |
| title | An Encoder-Decoder Foundation Chemical Language Model for Generative Polymer Design |
| topic | Materials Science Soft Condensed Matter |
| url | https://arxiv.org/abs/2510.18860 |