Biclustering Method for Data Analysis in Systems Biology
Author Information
Author(s): DiMaggio Peter A Jr, McAllister Scott R, Floudas Christodoulos A, Feng Xiao-Jiang, Rabinowitz Joshua D, Rabitz Herschel A
Primary Institution: Princeton University
Hypothesis
Can optimal re-ordering of data matrices improve the effectiveness of biclustering algorithms in systems biology?
Conclusion
The OREO method produces more insightful clusters than existing algorithms, effectively revealing underlying patterns in biological data.
Supporting Evidence
- OREO was tested on metabolite concentration data, image reconstruction, synthetic data, and gene expression data.
- Clusters produced by OREO showed better grouping of related metabolites and genes compared to other methods.
- OREO effectively separated normal and tumor tissues in colon cancer data.
Takeaway
This study shows a new way to group data that helps scientists see patterns better, especially in biological research.
Methodology
The study introduces OREO, a biclustering algorithm that optimally re-orders rows and columns of data matrices using network flow or traveling salesman problem models.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website