View in EDS HTML Full Text PDF Full Text

Prediction and Interpretability Study of the Glass Transition Temperature of Polyimide Based on Machine Learning and Molecular Dynamics Simulations.

Saved in:
Bibliographic Details
Title: Prediction and Interpretability Study of the Glass Transition Temperature of Polyimide Based on Machine Learning and Molecular Dynamics Simulations.
Authors: Huo, Wenjia1 (AUTHOR), Liang, Boyang1 (AUTHOR), Wu, Xiang1 (AUTHOR), Zhang, Zhenchang1 (AUTHOR), Zhou, Weichao1 (AUTHOR), Wang, Haihong1 (AUTHOR), Ran, Xupeng1 (AUTHOR), Bai, Yaoyao1 (AUTHOR), Zheng, Rongrong1 (AUTHOR) zhengrongrong2006@126.com
Source: Polymers (20734360). Aug2025, Vol. 17 Issue 15, p2083. 23p.
Subjects: Glass transition temperature, Polyimides, Prediction models, Molecular dynamics, Hypothesis, Materials science, Data analysis, Machine learning
Abstract: The utilization of machine learning (ML) has brought more opportunities for the discovery of high-performance materials with specific properties to replace traditional engineering materials. The glass transition temperature (Tg) is a crucial characteristic of polyimide (PI). But small datasets can only partially reveal structural information and decrease the ability of the models to learn from the observed data. In this investigation, a dataset comprising 1261 PIs was assembled. A quantitative structure–property relationship targeting Tg was constructed using nine regression algorithms, with the Categorical Boosting demonstrating the highest accuracy, achieving a coefficient of determination of 0.895 for the test set. SHapley Additive exPlanations analysis identified the NumRotatableBonds descriptor had a significantly negative impact on Tg. Finally, all-atom molecular dynamics (MD) simulations calculated eight PI structures to verify the accuracy of the prediction model. The ML prediction was consistent with the MD simulation, with the lowest prediction deviation of approximately 6.75%, but the time and resource consumption were tremendously reduced. These findings emphasize the significance of utilizing extensive datasets for model training. This available and interpretable ML framework provides impressive acceleration over the MD simulation and serves as a reference for the structural design of PI with the desired Tg in the future. [ABSTRACT FROM AUTHOR]
Copyright of Polymers (20734360) is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 187311336
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Prediction and Interpretability Study of the Glass Transition Temperature of Polyimide Based on Machine Learning and Molecular Dynamics Simulations.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Huo%2C+Wenjia%22">Huo, Wenjia</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Liang%2C+Boyang%22">Liang, Boyang</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wu%2C+Xiang%22">Wu, Xiang</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhang%2C+Zhenchang%22">Zhang, Zhenchang</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhou%2C+Weichao%22">Zhou, Weichao</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wang%2C+Haihong%22">Wang, Haihong</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Ran%2C+Xupeng%22">Ran, Xupeng</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Bai%2C+Yaoyao%22">Bai, Yaoyao</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zheng%2C+Rongrong%22">Zheng, Rongrong</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> zhengrongrong2006@126.com</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Polymers+%2820734360%29%22">Polymers (20734360)</searchLink>. Aug2025, Vol. 17 Issue 15, p2083. 23p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Glass+transition+temperature%22">Glass transition temperature</searchLink><br /><searchLink fieldCode="DE" term="%22Polyimides%22">Polyimides</searchLink><br /><searchLink fieldCode="DE" term="%22Prediction+models%22">Prediction models</searchLink><br /><searchLink fieldCode="DE" term="%22Molecular+dynamics%22">Molecular dynamics</searchLink><br /><searchLink fieldCode="DE" term="%22Hypothesis%22">Hypothesis</searchLink><br /><searchLink fieldCode="DE" term="%22Materials+science%22">Materials science</searchLink><br /><searchLink fieldCode="DE" term="%22Data+analysis%22">Data analysis</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: The utilization of machine learning (ML) has brought more opportunities for the discovery of high-performance materials with specific properties to replace traditional engineering materials. The glass transition temperature (Tg) is a crucial characteristic of polyimide (PI). But small datasets can only partially reveal structural information and decrease the ability of the models to learn from the observed data. In this investigation, a dataset comprising 1261 PIs was assembled. A quantitative structure–property relationship targeting Tg was constructed using nine regression algorithms, with the Categorical Boosting demonstrating the highest accuracy, achieving a coefficient of determination of 0.895 for the test set. SHapley Additive exPlanations analysis identified the NumRotatableBonds descriptor had a significantly negative impact on Tg. Finally, all-atom molecular dynamics (MD) simulations calculated eight PI structures to verify the accuracy of the prediction model. The ML prediction was consistent with the MD simulation, with the lowest prediction deviation of approximately 6.75%, but the time and resource consumption were tremendously reduced. These findings emphasize the significance of utilizing extensive datasets for model training. This available and interpretable ML framework provides impressive acceleration over the MD simulation and serves as a reference for the structural design of PI with the desired Tg in the future. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Polymers (20734360) is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=187311336
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3390/polym17152083
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 23
        StartPage: 2083
    Subjects:
      – SubjectFull: Glass transition temperature
        Type: general
      – SubjectFull: Polyimides
        Type: general
      – SubjectFull: Prediction models
        Type: general
      – SubjectFull: Molecular dynamics
        Type: general
      – SubjectFull: Hypothesis
        Type: general
      – SubjectFull: Materials science
        Type: general
      – SubjectFull: Data analysis
        Type: general
      – SubjectFull: Machine learning
        Type: general
    Titles:
      – TitleFull: Prediction and Interpretability Study of the Glass Transition Temperature of Polyimide Based on Machine Learning and Molecular Dynamics Simulations.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Huo, Wenjia
      – PersonEntity:
          Name:
            NameFull: Liang, Boyang
      – PersonEntity:
          Name:
            NameFull: Wu, Xiang
      – PersonEntity:
          Name:
            NameFull: Zhang, Zhenchang
      – PersonEntity:
          Name:
            NameFull: Zhou, Weichao
      – PersonEntity:
          Name:
            NameFull: Wang, Haihong
      – PersonEntity:
          Name:
            NameFull: Ran, Xupeng
      – PersonEntity:
          Name:
            NameFull: Bai, Yaoyao
      – PersonEntity:
          Name:
            NameFull: Zheng, Rongrong
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 08
              Text: Aug2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 20734360
          Numbering:
            – Type: volume
              Value: 17
            – Type: issue
              Value: 15
          Titles:
            – TitleFull: Polymers (20734360)
              Type: main
ResultId 1