Atul J. Butte and Isaac S. Kohane. Mutual information relevance networks: Functional genomic clustering using pairwise entropy measurements. In Pacific Symposium on Biocomputing, volume 5, pages 415--426, 2000.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....New York, NY 10027, USA. and Department of Pathology, University of Texas M.D. Anderson Cancer Center, USA. Email: edward ee.tamu.edu) and then choosing a threshold of the mutual information to create clusters of genes encompassing those with mutual information higher than the threshold [3]. These works are based on pair wise mutual information, and thus essentially only explore the marginal distributions of the multi dimensional data. Here our clustering strategy is based on minimizing the mutual information of the variables among clusters, and hence it fully explores the ....

A.J. Butte and I.S. Hohane, "Mutual information relevance networks: functional genomic clustering using pairwise entropy measurements," Pacific Symposium on Biocomputing, Vol. 4, 2000.

....context of prior world knowledge. The difficulty is in specifying the prior world knowledge. Also, many well known clustering algorithms can be used to compute domains, highly correlated, on type of machines. Examples of applying such schemes have appeared in literature; such as, mutual information[3]. There are many other techniques available for building these models; we are currently examining the viability of the alternatives. A common mechanism used to build these models is to setup a weighted graph G = V; E) and set the weight on the edge connecting two nodes to be a measure of H(X) ....

....5 Mutual Information as a Graph Edge Weight We use mutual information to perform comprehensive pairwise comparisons to produce an edge weight connecting two nodes. The medical field has used mutual information in the genomic project to find functional genomic clusters in RNA expression data [3]. The mutual information is a measure of the additional information known about one type of machine when given another, as shown in equation 1. Entropy H is the measure of uncertainty in a random variable. Mutual Information is the reduction of that uncertainty given another random variable. I(X; ....

A. Butte and I. Kohane. Mutual information relevance networks: functional genomic cluster ing using pairwise entropy measurements. In Proc. of the Pacific Symposium on Biocomputing, 2000.

....using genomic expression data to elucidate and visualize the effect of different stimuli on these genetic networks. Typical automatic analysis of microarray expression data is performed by clustering the expression profiles: using pair wise measures such as correlation[1,7] and mutual information[2]; using more multivariate methods like principal components[18] and Fourier analysis[20] Clustering methods are based on the microarray expression data and subsequent efforts are made to correlate clusters with pathways[22] Several authors have suggested methods for synthesizing pathways using ....

A.J. Butte et al, "Mutual information relevance networks: Functional genomic clustering using pairwise entropy measurements" PSB (2000)

.... Among the analytical tools applied to mine microarray data, are visual discovery and interpretation procedures [10, 13] singular value decomposition and projection on principal component planes [2, 20, 28] supervised machine learning techniques [6, 15] Fourier analysis [31] relevance networks [7 8], self organizing maps [17, 34 35] procedures based on network inference [11] and Shannon entropy calculations [14] Among all, the most widely used technique is hierarchical agglomerative clustering. As reported in many publications, clustering techniques have been applied to identify groups ....

Butte, A.J., and Kohane, I.S. (2000) Mutual information relevance networks: functional genomics clustering using pairwise entropy measurements. Proc. Pacific Symposium on Biocomputing, 5, 415-426.

....genomics. These devices are enabling the genome wide study of expression in Escherichia coli K 12, for example [4] Others are using DNA microarrays in the study of B cell lymphomas [5] growth control genes [6] and aging [7] Some researchers are focusing on developing new [8] or using existing [9] clustering techniques to facilitate the analysis of all the data made available by this relatively new technology. Few, however, have focused specifically on studying the properties of these array data to better understand how to distinguish significant from insignificant findings. One way we ....

A.J. Butte and I.S. Kohane, "Mutual information relevance networks: functional genomic clustering using pairwise entropy measurements" Proceedings of the Pacific Symposium on Biocomputing (2000)

No context found.

Atul J. Butte and Isaac S. Kohane. Mutual information relevance networks: Functional genomic clustering using pairwise entropy measurements. In Pacific Symposium on Biocomputing, volume 5, pages 415--426, 2000.

No context found.

A.J. Butte and I.S. Kohane. Mutual information relevance networks: Functional genomic clustering using pairwise entropy measurements. In R.B. Altman, A.K. Dunker, L. Hunter, K. Lauderdale, and T.E. Klein, editors, Pacific Symposium on Biocomputing 2000.

No context found.

Butte, A. J. & Kohane, I. S. Mutual information relevance networks: functional genomic clustering using pairwise entropy measurements. In Pac Symp Biocomput (2000).

No context found.

Butte A.J., Kohane I.S., (2000) \Mutual information relevance networks: Functional genomic clustering using pairwise entropy measurements. " Pacic Symposium Biocomputating. pp. 418-429.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC