Related Experiment Video
Updated: Jun 25, 2026
09:53
Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography
Published on: August 16, 2020
Master regulators used as breast cancer metastasis classifier
Wei Keat Lim1, Eugenia Lyashenko, Andrea Califano
1Center for Computational Biology and Bioinformatics, Department of Biomedical Informatics, Columbia University, 1130 Saint Nicholas Avenue, New York, NY 10032, USA.
Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing
|February 13, 2009
Summary
Identifying reliable cancer prognostic biomarkers is challenging. This study introduces a systems biology approach to find upstream Master Regulators, outperforming traditional gene signatures for better cancer prognosis prediction.
Area of Science:
- Computational biology
- Cancer research
- Systems biology
Background:
- Identifying prognostic biomarkers for cancer is difficult.
- Existing gene expression signature methods lack robustness and generalizability.
- Signatures from different studies often show poor overlap and performance on new data.
Purpose of the Study:
- To develop a computational systems biology approach for inferring robust prognostic markers.
- To identify upstream Master Regulators causally linked to cancer phenotypes.
- To improve upon existing methods for cancer sub-phenotype classification.
Main Methods:
- Utilized a computational systems biology strategy.
- Focused on identifying upstream Master Regulators.
- Applied the method to infer prognostic markers causally related to phenotypes.
Main Results:
- Inferred Master Regulators demonstrated superior performance compared to canonical gene signatures.
- The approach showed robustness on both original and distinct datasets.
- The method offers a complementary strategy to existing biomarker discovery techniques.
Conclusions:
- The proposed systems biology approach effectively identifies robust prognostic markers.
- Master Regulators are promising biomarkers for cancer prognosis.
- This method aids in elucidating molecular mechanisms underlying cancer phenotypes.
