MultiOmicsAgent: Guided Extreme Gradient-Boosted Decision Trees-Based Approaches for Biomarker-Candidate Discovery in Multiomics Data
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.
Authors
- Jianbo Fu (ORCID: https://orcid.org/0000-0003-3358-8106)
- Patrick G. A. Pedrioli (ORCID: https://orcid.org/0000-0001-6719-9139)
- Sebastian N. Steiner (ORCID: https://orcid.org/0000-0002-1281-8403)
- Peter J. Schüffler
- Sandra Goetze (ORCID: https://orcid.org/0000-0001-6880-8020)
- Martin Gesell (ORCID: https://orcid.org/0000-0002-5855-4028)
- Jens Settelmeier (ORCID: https://orcid.org/0000-0001-5885-9465)
- Amanda Khoo (ORCID: https://orcid.org/0000-0001-8917-918X)
- Bernd Wollscheid (ORCID: https://orcid.org/0000-0002-3923-1610)
- Diyora Salimova (ORCID: https://orcid.org/0000-0002-0111-5462)
- Jacqueline Hammer (ORCID: https://orcid.org/0000-0002-8155-128X)
- Julia Boshart
Institutions
- SIB Swiss Institute of Bioinformatics (CH)
- University of Freiburg (DE)
- ETH Zurich (CH)
- Institute of Translational Health Sciences (US)
- Department of Medical Sciences (BY)
- Technical University of Munich (DE)
Publication Details
- Journal
- Journal of Proteome Research
- Published
- 2025-05-26
- DOI
- https://doi.org/10.1021/acs.jproteome.4c01066
- Citations
- 1
- Primary Topic
- Gene expression and cancer classification
- Type
- article
- Field-Weighted Citation Impact
- 0.81