-
IEEE International Geoscience & Remote Sensing Symposium, IGARSS 2010, July 25-30, 2010, Honolulu, Hawaii, USA, Proceedings; 01/2010
-
[show abstract]
[hide abstract]
ABSTRACT: Abstract
Background
Chow and Liu showed that the maximum likelihood tree for multivariate discrete distributions may be found using a maximum weight spanning tree algorithm, for example Kruskal's algorithm. The efficiency of the algorithm makes it tractable for high-dimensional problems.
Results
We extend Chow and Liu's approach in two ways: first, to find the forest optimizing a penalized likelihood criterion, for example AIC or BIC, and second, to handle data with both discrete and Gaussian variables. We apply the approach to three datasets: two from gene expression studies and the third from a genetics of gene expression study. The minimal BIC forest supplements a conventional analysis of differential expression by providing a tentative network for the differentially expressed genes. In the genetics of gene expression context the method identifies a network approximating the joint distribution of the DNA markers and the gene expression levels.
Conclusions
The approach is generally useful as a preliminary step towards understanding the overall dependence structure of high-dimensional discrete and/or continuous data. Trees and forests are unrealistically simple models for biological systems, but can provide useful insights. Uses include the following: identification of distinct connected components, which can be analysed separately (dimension reduction); identification of neighbourhoods for more detailed analyses; as initial models for search algorithms with a larger search space, for example decomposable models or Bayesian networks; and identification of interesting features, such as hub nodes.
BMC Bioinformatics. 01/2010;
-
[show abstract]
[hide abstract]
ABSTRACT: Chow and Liu showed that the maximum likelihood tree for multivariate discrete distributions may be found using a maximum weight spanning tree algorithm, for example Kruskal's algorithm. The efficiency of the algorithm makes it tractable for high-dimensional problems.
We extend Chow and Liu's approach in two ways: first, to find the forest optimizing a penalized likelihood criterion, for example AIC or BIC, and second, to handle data with both discrete and Gaussian variables. We apply the approach to three datasets: two from gene expression studies and the third from a genetics of gene expression study. The minimal BIC forest supplements a conventional analysis of differential expression by providing a tentative network for the differentially expressed genes. In the genetics of gene expression context the method identifies a network approximating the joint distribution of the DNA markers and the gene expression levels.
The approach is generally useful as a preliminary step towards understanding the overall dependence structure of high-dimensional discrete and/or continuous data. Trees and forests are unrealistically simple models for biological systems, but can provide useful insights. Uses include the following: identification of distinct connected components, which can be analysed separately (dimension reduction); identification of neighbourhoods for more detailed analyses; as initial models for search algorithms with a larger search space, for example decomposable models or Bayesian networks; and identification of interesting features, such as hub nodes.
BMC Bioinformatics 01/2010; 11:18. · 2.75 Impact Factor
-
Nucleic Acids Research. 01/2009; 37:951-953.
-
Proceedings of the Graphics Interface 2007 Conference, May 28-30, 2007, Montreal, Canada; 01/2007
-
ACM Trans. Graph. 01/2006; 25:1-18.
-
Nucleic Acids Research. 01/2006; 34:656-659.
-
J. Graphics Tools. 01/2006; 11:1-12.
-
Proceedings of the Graphics Interface 2006 Conference, June 7-9, 2006, Quebec, Canada; 01/2006
-
Nucleic Acids Research. 01/2005; 33:656-659.
-
Eighth International Conference on Information Quality (IQ 2003), November 7-9. 2003; 01/2003
