An integrative multiomics random forest framework for robust biomarker discovery
GigaScience · 21.01.2026 · 15
DOI: 10.1093/gigascience/giaf148 ↗Kurz gefasst
Fachartikel in der Zeitschrift GigaScience, online erschienen am 09.12.2025. Verfasst von Wei Zhang und 4 weiteren Autor:innen. Beteiligte Einrichtung: Division of Biostatistics and Bioinformatics, Department of Public Health Sciences, University of Miami Miller School of Medicine, Miami, FL 33136, U…. Hauptthemen laut MEDLINE: Genomics, Biomarkers, Biomarkers, Tumor, Computational Biology. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIH HHS, NIA NIH HHS, NINDS NIH HHS.
Abstract (Originalsprache)
Background
High-throughput technologies now produce a wide array of omics data, from genomic and transcriptomic profiles to epigenomic and proteomic measurements. Integrating multiple omics layers measured on the same samples can reveal cross-layer molecular hubs that single-layer analyses miss. However, many existing integrative methods rely on linear assumptions or univariate feature importance, limiting their ability to capture nonlinear and interaction-driven dependencies across data modalities.
Results
We present an unsupervised, multivariate random forest (MRF) framework with an inverse minimal depth (IMD) importance to prioritize shared biomarkers across omics. In each forest, one layer serves as a multivariate response and the other as predictors; IMD summarizes how early a predictor (or response maximal splitting response variable) appears across trees, yielding interpretable, cross-layer feature rankings. We provide two IMD-based selection strategies and introduce an optional IMD power transform to enhance sensitivity to interaction signals. In extensive simulations spanning linear, nonlinear, and interaction regimes, our method matches sparse partial least squares/canonical correlation analysis under linear settings and outperforms them as nonlinearity increases, while adapted univariate ensemble learners (random forest, gradient boosting machine, XGBoost) underperform in the multivariate, unsupervised context. Applied to breast invasive carcinoma and colon adenocarcinoma in The Cancer Genome Atlas (TCGA), MRF-IMD identifies genes, CpGs, and microRNAs enriched for cancer-relevant pathways and yields more robust survival stratification than linear integrators with matched model sizes. In a TCGA pan-cancer analysis, MRF-IMD features achieve a higher Adjusted Rand Index than alternatives and recover coherent tumor-type clusters; in the Alzheimer’s Disease Neuroimaging Initiative (ADNI), the integrative signature improves dementia progression stratification over a published methylation risk score.
Conclusions
MRF-IMD provides a scalable and interpretable framework for multiomics integration that reliably identifies cross-layer biomarkers when nonlinear and interaction-driven dependencies are present. This approach advances robust biomarker discovery beyond the limits of linear integrative methods.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Division of Biostatistics and Bioinformatics, Department of Public Health Sciences, University of Miami Miller School of Medicine, Miami, FL 33136, USA.
- Sylvester Comprehensive Cancer Center, University of Miami Miller School of Medicine, Miami, FL 33136, USA.
- Dr. John T. Macdonald Foundation Department of Human Genetics, University of Miami Miller School of Medicine, Miami, FL 33136, USA.
- John P. Hussman Institute for Human Genomics, University of Miami Miller School of Medicine, Miami, FL 33136, USA.
- Division of Hematology and Oncology, Department of Medicine, Vanderbilt University Medical Center, Nashville, TN 37232, USA.
ORCID-Profile: Wei Zhang, X Steven Chen
Förderung
- NIH HHS
- NIA NIH HHS
- NINDS NIH HHS
- NCI NIH HHS
- Department of Defense Breast Cancer Research
- National Institutes of Health
Zitieren
APA
Zhang, W., Huang, H., Wang, L., Lehmann, B. D., & Chen, X. S. (2026). An integrative multiomics random forest framework for robust biomarker discovery. GigaScience, 15. https://doi.org/10.1093/gigascience/giaf148
Vancouver
Zhang W, Huang H, Wang L, Lehmann BD, Chen XS. An integrative multiomics random forest framework for robust biomarker discovery. GigaScience. 2026;15. doi:10.1093/gigascience/giaf148
BibTeX
@article{Zhang2026,
author = {Zhang, Wei and Huang, Hanchen and Wang, Lily and Lehmann, Brian D and Chen, X Steven},
title = {An integrative multiomics random forest framework for robust biomarker discovery},
journal = {GigaScience},
year = {2026},
volume = {15},
doi = {10.1093/gigascience/giaf148}
}
EUVIMED