Entropy Reduction Method ERM

EMC provides a more accurate representation of the relationship between two variables because nonlinearities are better described if higher moments of the pair distribution are considered. There is, of course, a price to be paid for this higher accuracy and that is the requirement for large amounts of data. However, even with well-estimated pair distribution functions one can, theoretically, make better, less ambiguous predictions of network structure from these measurements. 

Acknowledgment This chapter is based on selections from the article On the deduction of chemical reaction pathways from measurements of time series of concentrations by Michael Samoilov, Adam Arkin, and John Ross [1]. 

Michaels, G. S. Carr, D. Askenazi, B. M. Wen, X. Fuhrman, S. Somogyi, R. Cluster analysis and data visualization of large scale gene expression data. Pacific Symposium on Biocomputing 1998, 5, 42-53. 

Fuhrman, S. Cunningham, M. L Wen, X. Zweiger, G. J. Seilhamer, J. Somogyi, R. The application of Shannon entropy in the identification of putative drug targets. BioSystems 2000, 55, 5-14. 

---