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...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-08-01
|
| Series: | Advanced Science |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/advs.202101864 |
| _version_ | 1797819777248395264 |
|---|---|
| author | Minghao Guo Wan Shou Liane Makatura Timothy Erps Michael Foshey Wojciech Matusik |
| author_facet | Minghao Guo Wan Shou Liane Makatura Timothy Erps Michael Foshey Wojciech Matusik |
| author_sort | Minghao Guo |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-13T09:27:36Z |
| format | Article |
| id | doaj.art-d3852cf8a0404b469829c2146e2045c5 |
| institution | Directory Open Access Journal |
| issn | 2198-3844 |
| language | English |
| last_indexed | 2024-03-13T09:27:36Z |
| publishDate | 2022-08-01 |
| publisher | Wiley |
| record_format | Article |
| series | Advanced Science |
| spelling | doaj.art-d3852cf8a0404b469829c2146e2045c52023-05-26T08:56:00ZengWileyAdvanced Science2198-38442022-08-01923n/an/a10.1002/advs.202101864Polygrammar: Grammar for Digital Polymer Representation and GenerationMinghao Guo0Wan Shou1Liane Makatura2Timothy Erps3Michael Foshey4Wojciech Matusik5Computer Science and Artificial Intelligence Lab Massachusetts Institute of Technology Cambridge MA 02139 USAComputer Science and Artificial Intelligence Lab Massachusetts Institute of Technology Cambridge MA 02139 USAComputer Science and Artificial Intelligence Lab Massachusetts Institute of Technology Cambridge MA 02139 USAComputer Science and Artificial Intelligence Lab Massachusetts Institute of Technology Cambridge MA 02139 USAComputer Science and Artificial Intelligence Lab Massachusetts Institute of Technology Cambridge MA 02139 USAComputer Science and Artificial Intelligence Lab Massachusetts Institute of Technology Cambridge MA 02139 USAAbstract 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.https://doi.org/10.1002/advs.202101864context‐sensitive grammargenerative modelpolymer representation |
| spellingShingle | Minghao Guo Wan Shou Liane Makatura Timothy Erps Michael Foshey Wojciech Matusik Polygrammar: Grammar for Digital Polymer Representation and Generation Advanced Science context‐sensitive grammar generative model polymer representation |
| title | Polygrammar: Grammar for Digital Polymer Representation and Generation |
| title_full | Polygrammar: Grammar for Digital Polymer Representation and Generation |
| title_fullStr | Polygrammar: Grammar for Digital Polymer Representation and Generation |
| title_full_unstemmed | Polygrammar: Grammar for Digital Polymer Representation and Generation |
| title_short | Polygrammar: Grammar for Digital Polymer Representation and Generation |
| title_sort | polygrammar grammar for digital polymer representation and generation |
| topic | context‐sensitive grammar generative model polymer representation |
| url | https://doi.org/10.1002/advs.202101864 |
| work_keys_str_mv | AT minghaoguo polygrammargrammarfordigitalpolymerrepresentationandgeneration AT wanshou polygrammargrammarfordigitalpolymerrepresentationandgeneration AT lianemakatura polygrammargrammarfordigitalpolymerrepresentationandgeneration AT timothyerps polygrammargrammarfordigitalpolymerrepresentationandgeneration AT michaelfoshey polygrammargrammarfordigitalpolymerrepresentationandgeneration AT wojciechmatusik polygrammargrammarfordigitalpolymerrepresentationandgeneration |