In EDS ansehen

ERRα-Predictor: A Framework of Ensemble Models for Prediction of ERRα Binders, Antagonists, and Agonists Using Artificial Intelligence

Gespeichert in:
Bibliographische Detailangaben
Titel: ERRα-Predictor: A Framework of Ensemble Models for Prediction of ERRα Binders, Antagonists, and Agonists Using Artificial Intelligence
Autoren: Le Xiong, Jiahao Xu, Hongbo Yu, Weihua Li, Xinmin Li, Wenxiang Song, Jingwei Zhang, Yun Tang, Guixia Liu
Publikationsjahr: 2025
Schlagwörter: Biophysics, Biochemistry, Molecular Biology, Biotechnology, Computational Biology, Biological Sciences not elsewhere classified, Mathematical Sciences not elsewhere classified, Information Systems not elsewhere classified, representative structural modifications, related receptor α, matthews correlation coefficient, https :// github, various machine learning, substructure extraction techniques, model applicability domains, three datasets using, predict three datasets, comprehensive predictive models, based topological information, constructed ensemble models, three datasets, ensemble models, various databases, analytical techniques, test sets, significant importance, promising target, open source, molecule ligands, model prediction
Beschreibung: Estrogen-related receptor α (ERRα) is considered a promising target for the treatment of cancer and metabolic diseases. The development of comprehensive predictive models for ERRα binders, antagonists, and agonists is of significant importance. In this study, we collected and curated publicly available ERRα ligands from various databases (PubChem, ChEMBL, ExCAPE-DB, BindingDB, and IUPHAR). Based on these data, we first constructed baseline models using different sampling methods and various machine learning and graph neural network approaches. Building upon these results, we then developed the final ERRα-Predictor models, which integrated one-dimensional Simplified Molecular Input Line Entry System (SMILES) sequences and graph-based topological information, to predict three datasets: binders, antagonists, and agonists. Overall, the ERRα-Predictor models achieved promising performance, with the Matthews correlation coefficient (MCC) on the test sets of the three datasets being 0.633, 0.560, and 0.545, respectively. Additionally, we applied the models to challenging external validation sets while considering the definition of the model applicability domains. In addition to the accuracy of the model prediction, we also conducted interpretative explorations using Shapley additive explanations (SHAP) and GNNExplainer, respectively. Furthermore, we studied the representative structural modifications and substructures of the three datasets using the matched molecular pair analysis (MMPA) method and substructure extraction techniques. Based on these findings, the data collated in this study, along with the constructed ensemble models and analytical techniques, provide an effective and reliable framework for the prediction and analysis of ERRα small-molecule ligands. All code for ERRα-Predictor is open source and available at https://github.com/lxiongZ/ERRalpha-Predictor.
Publikationsart: article in journal/newspaper
Sprache: unknown
DOI: 10.1021/acs.jcim.5c01106.s001
Verfügbarkeit: https://doi.org/10.1021/acs.jcim.5c01106.s001
https://figshare.com/articles/journal_contribution/ERR_-Predictor_A_Framework_of_Ensemble_Models_for_Prediction_of_ERR_Binders_Antagonists_and_Agonists_Using_Artificial_Intelligence/29443292
Rights: CC BY-NC 4.0
Dokumentencode: edsbas.16A853AF
Datenbank: BASE
FullText Text:
  Availability: 0
Header DbId: edsbas
DbLabel: BASE
An: edsbas.16A853AF
RelevancyScore: 997
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 996.707214355469
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: ERRα-Predictor: A Framework of Ensemble Models for Prediction of ERRα Binders, Antagonists, and Agonists Using Artificial Intelligence
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Le+Xiong%22">Le Xiong</searchLink><br /><searchLink fieldCode="AR" term="%22Jiahao+Xu%22">Jiahao Xu</searchLink><br /><searchLink fieldCode="AR" term="%22Hongbo+Yu%22">Hongbo Yu</searchLink><br /><searchLink fieldCode="AR" term="%22Weihua+Li%22">Weihua Li</searchLink><br /><searchLink fieldCode="AR" term="%22Xinmin+Li%22">Xinmin Li</searchLink><br /><searchLink fieldCode="AR" term="%22Wenxiang+Song%22">Wenxiang Song</searchLink><br /><searchLink fieldCode="AR" term="%22Jingwei+Zhang%22">Jingwei Zhang</searchLink><br /><searchLink fieldCode="AR" term="%22Yun+Tang%22">Yun Tang</searchLink><br /><searchLink fieldCode="AR" term="%22Guixia+Liu%22">Guixia Liu</searchLink>
– Name: DatePubCY
  Label: Publication Year
  Group: Date
  Data: 2025
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Biophysics%22">Biophysics</searchLink><br /><searchLink fieldCode="DE" term="%22Biochemistry%22">Biochemistry</searchLink><br /><searchLink fieldCode="DE" term="%22Molecular+Biology%22">Molecular Biology</searchLink><br /><searchLink fieldCode="DE" term="%22Biotechnology%22">Biotechnology</searchLink><br /><searchLink fieldCode="DE" term="%22Computational+Biology%22">Computational Biology</searchLink><br /><searchLink fieldCode="DE" term="%22Biological+Sciences+not+elsewhere+classified%22">Biological Sciences not elsewhere classified</searchLink><br /><searchLink fieldCode="DE" term="%22Mathematical+Sciences+not+elsewhere+classified%22">Mathematical Sciences not elsewhere classified</searchLink><br /><searchLink fieldCode="DE" term="%22Information+Systems+not+elsewhere+classified%22">Information Systems not elsewhere classified</searchLink><br /><searchLink fieldCode="DE" term="%22representative+structural+modifications%22">representative structural modifications</searchLink><br /><searchLink fieldCode="DE" term="%22related+receptor+α%22">related receptor α</searchLink><br /><searchLink fieldCode="DE" term="%22matthews+correlation+coefficient%22">matthews correlation coefficient</searchLink><br /><searchLink fieldCode="DE" term="%22https+%3A%2F%2F+github%22">https :// github</searchLink><br /><searchLink fieldCode="DE" term="%22various+machine+learning%22">various machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22substructure+extraction+techniques%22">substructure extraction techniques</searchLink><br /><searchLink fieldCode="DE" term="%22model+applicability+domains%22">model applicability domains</searchLink><br /><searchLink fieldCode="DE" term="%22three+datasets+using%22">three datasets using</searchLink><br /><searchLink fieldCode="DE" term="%22predict+three+datasets%22">predict three datasets</searchLink><br /><searchLink fieldCode="DE" term="%22comprehensive+predictive+models%22">comprehensive predictive models</searchLink><br /><searchLink fieldCode="DE" term="%22based+topological+information%22">based topological information</searchLink><br /><searchLink fieldCode="DE" term="%22constructed+ensemble+models%22">constructed ensemble models</searchLink><br /><searchLink fieldCode="DE" term="%22three+datasets%22">three datasets</searchLink><br /><searchLink fieldCode="DE" term="%22ensemble+models%22">ensemble models</searchLink><br /><searchLink fieldCode="DE" term="%22various+databases%22">various databases</searchLink><br /><searchLink fieldCode="DE" term="%22analytical+techniques%22">analytical techniques</searchLink><br /><searchLink fieldCode="DE" term="%22test+sets%22">test sets</searchLink><br /><searchLink fieldCode="DE" term="%22significant+importance%22">significant importance</searchLink><br /><searchLink fieldCode="DE" term="%22promising+target%22">promising target</searchLink><br /><searchLink fieldCode="DE" term="%22open+source%22">open source</searchLink><br /><searchLink fieldCode="DE" term="%22molecule+ligands%22">molecule ligands</searchLink><br /><searchLink fieldCode="DE" term="%22model+prediction%22">model prediction</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: Estrogen-related receptor α (ERRα) is considered a promising target for the treatment of cancer and metabolic diseases. The development of comprehensive predictive models for ERRα binders, antagonists, and agonists is of significant importance. In this study, we collected and curated publicly available ERRα ligands from various databases (PubChem, ChEMBL, ExCAPE-DB, BindingDB, and IUPHAR). Based on these data, we first constructed baseline models using different sampling methods and various machine learning and graph neural network approaches. Building upon these results, we then developed the final ERRα-Predictor models, which integrated one-dimensional Simplified Molecular Input Line Entry System (SMILES) sequences and graph-based topological information, to predict three datasets: binders, antagonists, and agonists. Overall, the ERRα-Predictor models achieved promising performance, with the Matthews correlation coefficient (MCC) on the test sets of the three datasets being 0.633, 0.560, and 0.545, respectively. Additionally, we applied the models to challenging external validation sets while considering the definition of the model applicability domains. In addition to the accuracy of the model prediction, we also conducted interpretative explorations using Shapley additive explanations (SHAP) and GNNExplainer, respectively. Furthermore, we studied the representative structural modifications and substructures of the three datasets using the matched molecular pair analysis (MMPA) method and substructure extraction techniques. Based on these findings, the data collated in this study, along with the constructed ensemble models and analytical techniques, provide an effective and reliable framework for the prediction and analysis of ERRα small-molecule ligands. All code for ERRα-Predictor is open source and available at https://github.com/lxiongZ/ERRalpha-Predictor.
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: article in journal/newspaper
– Name: Language
  Label: Language
  Group: Lang
  Data: unknown
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.1021/acs.jcim.5c01106.s001
– Name: URL
  Label: Availability
  Group: URL
  Data: https://doi.org/10.1021/acs.jcim.5c01106.s001<br />https://figshare.com/articles/journal_contribution/ERR_-Predictor_A_Framework_of_Ensemble_Models_for_Prediction_of_ERR_Binders_Antagonists_and_Agonists_Using_Artificial_Intelligence/29443292
– Name: Copyright
  Label: Rights
  Group: Cpyrght
  Data: CC BY-NC 4.0
– Name: AN
  Label: Accession Number
  Group: ID
  Data: edsbas.16A853AF
PLink https://erproxy.cvtisr.sk/sfx/access?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsbas&AN=edsbas.16A853AF
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1021/acs.jcim.5c01106.s001
    Languages:
      – Text: unknown
    Subjects:
      – SubjectFull: Biophysics
        Type: general
      – SubjectFull: Biochemistry
        Type: general
      – SubjectFull: Molecular Biology
        Type: general
      – SubjectFull: Biotechnology
        Type: general
      – SubjectFull: Computational Biology
        Type: general
      – SubjectFull: Biological Sciences not elsewhere classified
        Type: general
      – SubjectFull: Mathematical Sciences not elsewhere classified
        Type: general
      – SubjectFull: Information Systems not elsewhere classified
        Type: general
      – SubjectFull: representative structural modifications
        Type: general
      – SubjectFull: related receptor α
        Type: general
      – SubjectFull: matthews correlation coefficient
        Type: general
      – SubjectFull: https :// github
        Type: general
      – SubjectFull: various machine learning
        Type: general
      – SubjectFull: substructure extraction techniques
        Type: general
      – SubjectFull: model applicability domains
        Type: general
      – SubjectFull: three datasets using
        Type: general
      – SubjectFull: predict three datasets
        Type: general
      – SubjectFull: comprehensive predictive models
        Type: general
      – SubjectFull: based topological information
        Type: general
      – SubjectFull: constructed ensemble models
        Type: general
      – SubjectFull: three datasets
        Type: general
      – SubjectFull: ensemble models
        Type: general
      – SubjectFull: various databases
        Type: general
      – SubjectFull: analytical techniques
        Type: general
      – SubjectFull: test sets
        Type: general
      – SubjectFull: significant importance
        Type: general
      – SubjectFull: promising target
        Type: general
      – SubjectFull: open source
        Type: general
      – SubjectFull: molecule ligands
        Type: general
      – SubjectFull: model prediction
        Type: general
    Titles:
      – TitleFull: ERRα-Predictor: A Framework of Ensemble Models for Prediction of ERRα Binders, Antagonists, and Agonists Using Artificial Intelligence
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Le Xiong
      – PersonEntity:
          Name:
            NameFull: Jiahao Xu
      – PersonEntity:
          Name:
            NameFull: Hongbo Yu
      – PersonEntity:
          Name:
            NameFull: Weihua Li
      – PersonEntity:
          Name:
            NameFull: Xinmin Li
      – PersonEntity:
          Name:
            NameFull: Wenxiang Song
      – PersonEntity:
          Name:
            NameFull: Jingwei Zhang
      – PersonEntity:
          Name:
            NameFull: Yun Tang
      – PersonEntity:
          Name:
            NameFull: Guixia Liu
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-locals
              Value: edsbas
            – Type: issn-locals
              Value: edsbas.oa
ResultId 1