Chemoinformatic regression methods and their applicability domain
Molecular Informatics · 2024-07 · 43 (7)
DOI: 10.1002/minf.202400018 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Molecular Informatics, online erschienen am 28.05.2024. Verfasst von Thomas-Martin Dutschmann und 2 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Medicinal and Pharmaceutical Chemistry, University of Technology Braunschweig, 38106, Braunschweig, Germany. Hauptthemen laut MEDLINE: Cheminformatics. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 153 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
The growing interest in chemoinformatic model uncertainty calls for a summary of the most widely used regression techniques and how to estimate their reliability. Regression models learn a mapping from the space of explanatory variables to the space of continuous output values. Among other limitations, the predictive performance of the model is restricted by the training data used for model fitting. Identification of unusual objects by outlier detection methods can improve model performance. Additionally, proper model evaluation necessitates defining the limitations of the model, often called the applicability domain. Comparable to certain classifiers, some regression techniques come with built‐in methods or augmentations to quantify their (un)certainty, while others rely on generic procedures. The theoretical background of their working principles and how to deduce specific and general definitions for their domain of applicability shall be explained.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Institute of Medicinal and Pharmaceutical Chemistry, University of Technology Braunschweig, 38106, Braunschweig, Germany.
ORCID-Profile: Thomas-Martin Dutschmann
Zitieren
APA
Dutschmann, T. M., Schlenker, V., & Baumann, K. (2024). Chemoinformatic regression methods and their applicability domain. Molecular Informatics, 43(7). https://doi.org/10.1002/minf.202400018
Vancouver
Dutschmann TM, Schlenker V, Baumann K. Chemoinformatic regression methods and their applicability domain. Molecular Informatics. 2024;43(7). doi:10.1002/minf.202400018
BibTeX
@article{Dutschmann2024,
author = {Dutschmann, Thomas-Martin and Schlenker, Valerie and Baumann, Knut},
title = {Chemoinformatic regression methods and their applicability domain},
journal = {Molecular Informatics},
year = {2024},
volume = {43},
number = {7},
doi = {10.1002/minf.202400018}
}
EUVIMED