polyBERT: a chemical language model to enable fully machine-driven ultrafast polymer informatics
Abstract Polymers are a vital part of everyday life. Their chemical universe is so large that it presents unprecedented opportunities as well as significant challenges to identify suitable application-specific candidates. We present a complete end-to-end machine-driven polymer informatics pipeline t...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-07-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-023-39868-6 |
| _version_ | 1827899810727854080 |
|---|---|
| author | Christopher Kuenneth Rampi Ramprasad |
| author_facet | Christopher Kuenneth Rampi Ramprasad |
| author_sort | Christopher Kuenneth |
| collection | DOAJ |
| description | Abstract Polymers are a vital part of everyday life. Their chemical universe is so large that it presents unprecedented opportunities as well as significant challenges to identify suitable application-specific candidates. We present a complete end-to-end machine-driven polymer informatics pipeline that can search this space for suitable candidates at unprecedented speed and accuracy. This pipeline includes a polymer chemical fingerprinting capability called polyBERT (inspired by Natural Language Processing concepts), and a multitask learning approach that maps the polyBERT fingerprints to a host of properties. polyBERT is a chemical linguist that treats the chemical structure of polymers as a chemical language. The present approach outstrips the best presently available concepts for polymer property prediction based on handcrafted fingerprint schemes in speed by two orders of magnitude while preserving accuracy, thus making it a strong candidate for deployment in scalable architectures including cloud infrastructures. |
| first_indexed | 2024-03-12T23:22:40Z |
| format | Article |
| id | doaj.art-cf08bcaaa38b496ca1dd9f3c137c723a |
| institution | Directory Open Access Journal |
| issn | 2041-1723 |
| language | English |
| last_indexed | 2024-03-12T23:22:40Z |
| publishDate | 2023-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj.art-cf08bcaaa38b496ca1dd9f3c137c723a2023-07-16T11:22:01ZengNature PortfolioNature Communications2041-17232023-07-0114111110.1038/s41467-023-39868-6polyBERT: a chemical language model to enable fully machine-driven ultrafast polymer informaticsChristopher Kuenneth0Rampi Ramprasad1School of Materials Science and Engineering, Georgia Institute of TechnologySchool of Materials Science and Engineering, Georgia Institute of TechnologyAbstract Polymers are a vital part of everyday life. Their chemical universe is so large that it presents unprecedented opportunities as well as significant challenges to identify suitable application-specific candidates. We present a complete end-to-end machine-driven polymer informatics pipeline that can search this space for suitable candidates at unprecedented speed and accuracy. This pipeline includes a polymer chemical fingerprinting capability called polyBERT (inspired by Natural Language Processing concepts), and a multitask learning approach that maps the polyBERT fingerprints to a host of properties. polyBERT is a chemical linguist that treats the chemical structure of polymers as a chemical language. The present approach outstrips the best presently available concepts for polymer property prediction based on handcrafted fingerprint schemes in speed by two orders of magnitude while preserving accuracy, thus making it a strong candidate for deployment in scalable architectures including cloud infrastructures.https://doi.org/10.1038/s41467-023-39868-6 |
| spellingShingle | Christopher Kuenneth Rampi Ramprasad polyBERT: a chemical language model to enable fully machine-driven ultrafast polymer informatics Nature Communications |
| title | polyBERT: a chemical language model to enable fully machine-driven ultrafast polymer informatics |
| title_full | polyBERT: a chemical language model to enable fully machine-driven ultrafast polymer informatics |
| title_fullStr | polyBERT: a chemical language model to enable fully machine-driven ultrafast polymer informatics |
| title_full_unstemmed | polyBERT: a chemical language model to enable fully machine-driven ultrafast polymer informatics |
| title_short | polyBERT: a chemical language model to enable fully machine-driven ultrafast polymer informatics |
| title_sort | polybert a chemical language model to enable fully machine driven ultrafast polymer informatics |
| url | https://doi.org/10.1038/s41467-023-39868-6 |
| work_keys_str_mv | AT christopherkuenneth polybertachemicallanguagemodeltoenablefullymachinedrivenultrafastpolymerinformatics AT rampiramprasad polybertachemicallanguagemodeltoenablefullymachinedrivenultrafastpolymerinformatics |