Exploring high-performance viscosity index improver polymers via high-throughput molecular dynamics and explainable AI
Abstract Data-driven material innovation has the potential to revolutionize the traditional Edisonian process and significantly shorten development cycles. However, the scarcity of data in materials science and the poor interpretability of machine learning pose serious obstacles to the adoption of t...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-03-01
|
| Series: | npj Computational Materials |
| Online Access: | https://doi.org/10.1038/s41524-025-01539-z |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850045920471678976 |
|---|---|
| author | Rui Zhou Luyao Bao Weifeng Bu Feng Zhou |
| author_facet | Rui Zhou Luyao Bao Weifeng Bu Feng Zhou |
| author_sort | Rui Zhou |
| collection | DOAJ |
| description | Abstract Data-driven material innovation has the potential to revolutionize the traditional Edisonian process and significantly shorten development cycles. However, the scarcity of data in materials science and the poor interpretability of machine learning pose serious obstacles to the adoption of this new paradigm. Here, we propose a pipeline that integrates data production, virtual screening, and theoretical innovation using high-throughput all-atom molecular dynamics (MD) as a data flywheel. Using this pipeline, we explored high-performance viscosity index improver polymers and constructed a dataset of 1166 entries for viscosity index improvers (VII) started from only five types of polymers. Under multi-objective constraints, 366 potential high-viscosity-temperature performance polymers were identified, and six representative polymers were validated through direct MD simulations. Starting from high-dimensional physical features, we conducted an unbiased systematic analysis of the quantitative structure-property relationships for polymers VII, providing an explicit mathematical model with promising application in VII industry. This work demonstrates the advanced capabilities and reliability of the pipeline proposed here in initiating material innovation cycles in data-scarce fields, and the establishment of the VII dataset and models will serve as a critical starting point for the data-driven design of high viscosity-temperature performance polymers. |
| format | Article |
| id | doaj-art-1f1e4d8be13e409284103630cb4c1036 |
| institution | DOAJ |
| issn | 2057-3960 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Computational Materials |
| spelling | doaj-art-1f1e4d8be13e409284103630cb4c10362025-08-20T02:54:36ZengNature Portfolionpj Computational Materials2057-39602025-03-0111111310.1038/s41524-025-01539-zExploring high-performance viscosity index improver polymers via high-throughput molecular dynamics and explainable AIRui Zhou0Luyao Bao1Weifeng Bu2Feng Zhou3Key Laboratory of Nonferrous Metals Chemistry and Resources Utilization of Gansu Province, State Key Laboratory of Applied Organic Chemistry, and College of Chemistry and Chemical Engineering, Lanzhou UniversityState Key Laboratory of Solid Lubrication, Lanzhou Institute of Chemical Physics, Chinese Academy of SciencesKey Laboratory of Nonferrous Metals Chemistry and Resources Utilization of Gansu Province, State Key Laboratory of Applied Organic Chemistry, and College of Chemistry and Chemical Engineering, Lanzhou UniversityState Key Laboratory of Solid Lubrication, Lanzhou Institute of Chemical Physics, Chinese Academy of SciencesAbstract Data-driven material innovation has the potential to revolutionize the traditional Edisonian process and significantly shorten development cycles. However, the scarcity of data in materials science and the poor interpretability of machine learning pose serious obstacles to the adoption of this new paradigm. Here, we propose a pipeline that integrates data production, virtual screening, and theoretical innovation using high-throughput all-atom molecular dynamics (MD) as a data flywheel. Using this pipeline, we explored high-performance viscosity index improver polymers and constructed a dataset of 1166 entries for viscosity index improvers (VII) started from only five types of polymers. Under multi-objective constraints, 366 potential high-viscosity-temperature performance polymers were identified, and six representative polymers were validated through direct MD simulations. Starting from high-dimensional physical features, we conducted an unbiased systematic analysis of the quantitative structure-property relationships for polymers VII, providing an explicit mathematical model with promising application in VII industry. This work demonstrates the advanced capabilities and reliability of the pipeline proposed here in initiating material innovation cycles in data-scarce fields, and the establishment of the VII dataset and models will serve as a critical starting point for the data-driven design of high viscosity-temperature performance polymers.https://doi.org/10.1038/s41524-025-01539-z |
| spellingShingle | Rui Zhou Luyao Bao Weifeng Bu Feng Zhou Exploring high-performance viscosity index improver polymers via high-throughput molecular dynamics and explainable AI npj Computational Materials |
| title | Exploring high-performance viscosity index improver polymers via high-throughput molecular dynamics and explainable AI |
| title_full | Exploring high-performance viscosity index improver polymers via high-throughput molecular dynamics and explainable AI |
| title_fullStr | Exploring high-performance viscosity index improver polymers via high-throughput molecular dynamics and explainable AI |
| title_full_unstemmed | Exploring high-performance viscosity index improver polymers via high-throughput molecular dynamics and explainable AI |
| title_short | Exploring high-performance viscosity index improver polymers via high-throughput molecular dynamics and explainable AI |
| title_sort | exploring high performance viscosity index improver polymers via high throughput molecular dynamics and explainable ai |
| url | https://doi.org/10.1038/s41524-025-01539-z |
| work_keys_str_mv | AT ruizhou exploringhighperformanceviscosityindeximproverpolymersviahighthroughputmoleculardynamicsandexplainableai AT luyaobao exploringhighperformanceviscosityindeximproverpolymersviahighthroughputmoleculardynamicsandexplainableai AT weifengbu exploringhighperformanceviscosityindeximproverpolymersviahighthroughputmoleculardynamicsandexplainableai AT fengzhou exploringhighperformanceviscosityindeximproverpolymersviahighthroughputmoleculardynamicsandexplainableai |