MultiOmicsAgent: Guided Extreme Gradient-Boosted Decision Trees-Based Approaches for Biomarker-Candidate Discovery in Multiomics Data
Journal of Proteome Research · 2025
DOI: 10.1021/acs.jproteome.4c01066 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Proteome Research, 2025. Verfasst von Jens Settelmeier und 11 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Translational Medicine at the Department of Health Sciences and Technology, ETH, Zurich 8093, Switzerland. Hauptthemen laut MEDLINE: Decision Trees, Biomarkers, Software, Proteomics. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Personalized Health and Related Technologies from ETH Domain.
Abstract (Originalsprache)
MultiOmicsAgent (MOAgent) is an innovative, Python-based open-source tool for biomarker discovery, utilizing machine learning techniques, specifically extreme gradient-boosted decision trees, to process multiomics data. With its cross-platform compatibility, user-oriented graphical interface, and well-documented API, MOAgent not only meets the needs of both coding professionals and those new to machine learning but also addresses common data analysis challenges like normalization, data incompleteness, class imbalances and data leakage between disjoint data splits. MOAgent's guided data analysis strategy opens up data-driven insights from digitized clinical biospecimen cohorts, making advanced data analysis accessible and reliable for a wide audience.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Institute of Translational Medicine at the Department of Health Sciences and Technology, ETH, Zurich 8093, Switzerland.
- Swiss Institute of Bioinformatics, Lausanne 1015, Switzerland.
- ETH PHRT Swiss Multi-Omics Center (SMOC), Zurich 8093, Switzerland.
- Institute of Pathology, TUM School of Medicine and Health, Technical University of Munich, Munich 81675, Germany.
- Department for Applied Mathematics, Albert-Ludwigs-University of Freiburg, Freiburg 79104, Germany.
- Department of Biology, ETH, Zurich 8093, Switzerland.
ORCID-Profile: Jens Settelmeier, Peter J Schüffler
Förderung
- Personalized Health and Related Technologies from ETH Domain
Zitieren
APA
Settelmeier, J., Goetze, S., Boshart, J., Fu, J., Khoo, A., Steiner, S. N., Gesell, M., Hammer, J., Schüffler, P. J., Salimova, D., Pedrioli, P. G. A., & Wollscheid, B. (2025). MultiOmicsAgent: Guided Extreme Gradient-Boosted Decision Trees-Based Approaches for Biomarker-Candidate Discovery in Multiomics Data. Journal of Proteome Research. https://doi.org/10.1021/acs.jproteome.4c01066
Vancouver
Settelmeier J, Goetze S, Boshart J, Fu J, Khoo A, Steiner SN, et al. MultiOmicsAgent: Guided Extreme Gradient-Boosted Decision Trees-Based Approaches for Biomarker-Candidate Discovery in Multiomics Data. Journal of Proteome Research. 2025. doi:10.1021/acs.jproteome.4c01066
BibTeX
@article{Settelmeier2025,
author = {Settelmeier, Jens and Goetze, Sandra and Boshart, Julia and Fu, Jianbo and Khoo, Amanda and Steiner, Sebastian N and Gesell, Martin and Hammer, Jacqueline and Schüffler, Peter J and Salimova, Diyora and Pedrioli, Patrick G A and Wollscheid, Bernd},
title = {MultiOmicsAgent: Guided Extreme Gradient-Boosted Decision Trees-Based Approaches for Biomarker-Candidate Discovery in Multiomics Data},
journal = {Journal of Proteome Research},
year = {2025},
doi = {10.1021/acs.jproteome.4c01066}
}
EUVIMED