Number of the records: 1  

Balancing Predictive Relevance of Ligand Biochemical Activities

  1. 1.
    0565234 - ÚGN 2023 RIV CH eng C - Conference Paper (international conference)
    Pecha, Marek
    Balancing Predictive Relevance of Ligand Biochemical Activities.
    Uncertainty and impresision in decision making and decision support: new advances, challenges, and perspectives. Vol. 338. Cham: Springer International Publishing AG, 2022 - (Atanassov, K.; Atanassova, V.; Kacprzyk, J.; Kaluszko, A.; Krawczak, M.; Owsinski, J.; Sotirov, S.; Sotirova, E.; Szmidt, E.; Zadrozny, S.), s. 338-348. ISBN 978-303095928-9. ISSN 2367-3370. E-ISSN 2367-3389.
    [National Conference on Operationaland Systems Research, BOS-2020 /16./ and 19th International Workshop on Intuitionistic Fuzzy Sets and Generalized Nets, IWIFSGN-2020. Warsaw (PL), 10.12.2020-15.12.2020]
    Institutional support: RVO:68145535
    Keywords : balancing predictive relevance models * uncalibrated models * Platt’s scaling
    OECD category: Applied mathematics
    https://link.springer.com/chapter/10.1007/978-3-030-95929-6_26

    In this paper, we present a technique for balancing predictive relevance models related to supervised modelling ligand biochemical activities to biological targets. We train uncalibrated models employing conventional supervised machine learning technique, namely Support Vector Machines. Unfortunately, SVMs have a serious drawback. They are sensitive to imbalanced datasets, outliers and high multicollinearity among training samples, which could be a cause of preferencing one group over another. Thus, an additional calibration could be required for balancing a predictive relevance of models. As a technique for this balancing, we propose the Platt’s scaling. The achieved results were demonstrated on single-target models trained on datasets exported from the ExCAPE database. Unlike traditional used machine techniques, we focus on decreasing uncertainty employing deterministic solvers.
    Permanent Link: https://hdl.handle.net/11104/0336802

     
    FileDownloadSizeCommentaryVersionAccess
    UGN_0565234.pdf5293.4 KBOtherrequire
     
Number of the records: 1  

  This site uses cookies to make them easier to browse. Learn more about how we use cookies.