Abstract. DNA microarrays are a high-throughput technology useful for functional genomics and gene expression analysis. While many microarray data are generated in sequence, most expression analysis tools are not utilizing the temporal information. Temporal expression profiling is important in many applications, including developmental studies, pathway analysis, and disease prognosis. In this paper, we develop a learning method designed for temporal gene expression profiling from massive DNA-microarray data. It attempts to learn probabilistic lattice maps of the gene expressions, which are then used for profiling the trajectories of temporal expressions of co-regulated genes. This self-organizing latent lattice (SOLL) model combines the topographic mapping capability of self-organizing maps and the generative property of probabilistic latent-variable models. We empirically evaluate the SOLL model on a set of cell-cycle regulation data, demonstrating its effectiveness in discovering the temporal patterns of correlated genes and its usefulness as a tool for generating and visualizing interesting hypotheses. Keywords: DNA-microarray data, correlated genes, temporal expression profiling, learning latent-variable models, visualization 1.
|
4344
|
Maximum likelihood from incomplete data via the EM algorithm
– Dempster, Laird, et al.
- 1977
|
|
2961
|
Pattern Classification and Scene Analysis
– Duda, Hart
- 1973
|
|
2062
|
The Self-Organizing Map
– Kohonen
- 1990
|
|
1357
|
R.C.: Algorithms for clustering data
– Jain, Dubes
- 1988
|
|
798
|
Cluster analysis and display of genome-wide expression patterns
– Eisen, Spellman, et al.
- 1998
|
|
397
|
An Introduction to Multivariate Statistical Analysis
– Anderson
- 1971
|
|
336
|
Comprehensive identification of cell cycle-regulated genes of the yeast saccharomyces cerevisiae by microarray hybridization. Molecular Biology of the Cell
– SPELLMAN, SHERLOCK, et al.
- 1998
|
|
316
|
Broad patterns of gene expression revealed by clustering of tumor and normal colon tissues probed by oligonucleotide arrays
– Alon, Barkai, et al.
- 1999
|
|
295
|
Exploring the metabolic and genetic control of gene expression on a genomic scale, Science
– DeRisi, Iver, et al.
- 1997
|
|
270
|
Interpreting patterns of gene expression with self-organizing maps: methods and application to hematopoietic differentiation
– Tamayo, Slonim, et al.
- 1999
|
|
203
|
GTM: The generative topographic mapping
– Bishop, Svensén, et al.
- 1998
|
|
182
|
Operations for learning with graphical models
– Buntine
- 1994
|
|
175
|
Biclustering of expression data
– Cheng, Church
- 2000
|
|
154
|
A genome-wide transcriptional analysis of the mitotic cell cycle
– Cho, Campbell, et al.
- 1998
|
|
89
|
Feature Selection for Classification
– Dash, Liu
- 1997
|
|
71
|
CLICK: A Clustering Algorithm with Applications to Gene Expression Analysis
– Sharan, Shamir
- 2000
|
|
70
|
A hierarchical unsupervised growing neural network for clustering gene expression patters
– Herrero, Valencia, et al.
|
|
63
|
A Dendrite Method for Cluster Analysis
– Calinski, Harabasz
- 1974
|
|
61
|
Principal components analysis to summarize microarray experiments: application to sporulation time series
– Raychaudhuri, JM, et al.
|
|
56
|
Aligning gene expression time series with time warping algorithms
– Aach, Church
|
|
38
|
Cluster analysis of gene expression dynamics
– MF, Sebastiani, et al.
- 2002
|
|
28
|
Analysis of temporal gene expression profiles: Clustering by simulated annealing and determining the optimal number of clusters. Bioinformatics
– AV, Fuchs
|
|
23
|
Evolutionary induction of sparse neural trees
– Zhang, Ohm, et al.
- 1997
|
|
21
|
Discovering functional relationships between RNA expression and chemotherapeutic susceptibility using relevance networks
– Butte, Tamayo, et al.
- 2000
|
|
14
|
DNA expression monitoring by hybridization of high density oligonucleotide arrays. Nature Biotechnology
– Lockhart, Dong, et al.
- 1996
|
|
13
|
Visualizing associations between genome sequences and gene expression data using genome-mean expression profiles
– Chiang, Brown, et al.
- 2001
|
|
10
|
Biomedical discovery with DNA arrays
– Young
- 2000
|
|
5
|
Microarrays and cell cycle transcription in yeast
– Futcher
- 2000
|
|
5
|
Cell cycle regulated transcription in yeast
– Koch, Nasmyth
- 1994
|
|
4
|
The role of phosphorylation and the CDC28 protein kinase in cell cycle-regulated nuclear import of S. cerevisiae transcription factor SWI5. Cell66
– Moll, Tebb, et al.
- 1991
|
|
4
|
Extracting transcriptional events from temporal gene expression patterns during Dictyostelium development
– Sasik, Iranfar, et al.
- 2002
|
|
4
|
Analyzing auditory representations for sound classification with self-organizing neural networks
– Spevak, Polfreman
- 2000
|
|
3
|
Latent variable models. Learning in Graphical Models
– Bishop
- 1998
|
|
3
|
A general approach to the isolation of cell cycle regulated genes in the budding yeast, Saccharomyces cerevisiae
– Price, Nasmyth, et al.
- 1991
|
|
2
|
Regulation of transcription by proteins that control the cell cycle
– Brian
- 1997
|
|
2
|
Binding of human minichromosome maintenance proteins with histone H3
– Ishimi, Ichinose, et al.
- 1996
|
|
2
|
The identification of a second cell cycle control on the HO promoter in yeast; cell cycle regulation of SWI5 neclear entry
– Nasmyth, Adolf, et al.
- 1990
|
|
2
|
The regulation of histone synthesis in the cell cycle
– Osley
- 1991
|
|
2
|
Identification of assymetrically localized determinant, Ash1p, required for lineage-specific trascription of the yeast HO gene
– Sil, Herskowitz
- 1996
|
|
2
|
Regulation of histone gene expression
– Stein, Stein, et al.
- 1992
|
|
2
|
SWI5 instablilty may be neccesarry but is not sufficient for asymmetric HO expression in yeast. Genes Dev
– Tebb, Moll, et al.
- 1993
|
