MultiOmicsAgent: Guided Extreme Gradient-Boosted Decision Trees-Based Approaches for Biomarker-Candidate Discovery in Multiomics Data.

Journal: Journal of proteome research
Published Date: May 25, 2025

Abstract

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

  • Jens Settelmeier
    Institute of Translational Medicine at the Department of Health Sciences and Technology, ETH, Zurich 8093, Switzerland.
  • Sandra Goetze
    Institute of Translational Medicine at the Department of Health Sciences and Technology, ETH, Zurich 8093, Switzerland.
  • Julia Boshart
    Institute of Translational Medicine at the Department of Health Sciences and Technology, ETH, Zurich 8093, Switzerland.
  • Jianbo Fu
    College of Pharmaceutical Sciences, Zhejiang University, Hangzhou 310058, China.
  • Amanda Khoo
    Institute of Translational Medicine at the Department of Health Sciences and Technology, ETH, Zurich 8093, Switzerland.
  • Sebastian N Steiner
    Institute of Translational Medicine at the Department of Health Sciences and Technology, ETH, Zurich 8093, Switzerland.
  • Martin Gesell
    Institute of Translational Medicine at the Department of Health Sciences and Technology, ETH, Zurich 8093, Switzerland.
  • Jacqueline Hammer
    Institute of Translational Medicine at the Department of Health Sciences and Technology, ETH, Zurich 8093, Switzerland.
  • Peter J Schüffler
    Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, USA.
  • Diyora Salimova
    Department for Applied Mathematics, Albert-Ludwigs-University of Freiburg, Freiburg 79104, Germany.
  • Patrick G A Pedrioli
    Institute of Translational Medicine at the Department of Health Sciences and Technology, ETH, Zurich 8093, Switzerland.
  • Bernd Wollscheid
    Department of Health Sciences and Technology, Institute of Translational Medicine, ETH Zürich, Zürich, Switzerland.

Keywords

External Resources

Popular Topics
Recent Journals