Self-organizing latent lattice models for temporal gene expression profiling

Byoung Tak Zhang, Jinsan Yang, Sung Wook Chi

Research output: Contribution to journalArticle

10 Citations (Scopus)

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.

Original languageEnglish
Pages (from-to)67-89
Number of pages23
JournalMachine Learning
Volume52
Issue number1-2
DOIs
Publication statusPublished - 2003 Jul 1
Externally publishedYes

Fingerprint

Microarrays
Gene expression
DNA
Genes
Self organizing maps
Cells
Trajectories
Throughput

Keywords

  • Correlated genes
  • DNA-microarray data
  • Learning latent-variable models
  • Temporal expression profiling
  • Visualization

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Cite this

Self-organizing latent lattice models for temporal gene expression profiling. / Zhang, Byoung Tak; Yang, Jinsan; Chi, Sung Wook.

In: Machine Learning, Vol. 52, No. 1-2, 01.07.2003, p. 67-89.

Research output: Contribution to journalArticle

Zhang, Byoung Tak ; Yang, Jinsan ; Chi, Sung Wook. / Self-organizing latent lattice models for temporal gene expression profiling. In: Machine Learning. 2003 ; Vol. 52, No. 1-2. pp. 67-89.
@article{dd3d4c76e3654c5491667a5730c39af8,
title = "Self-organizing latent lattice models for temporal gene expression profiling",
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 = "Correlated genes, DNA-microarray data, Learning latent-variable models, Temporal expression profiling, Visualization",
author = "Zhang, {Byoung Tak} and Jinsan Yang and Chi, {Sung Wook}",
year = "2003",
month = "7",
day = "1",
doi = "10.1023/A:1023993325417",
language = "English",
volume = "52",
pages = "67--89",
journal = "Machine Learning",
issn = "0885-6125",
publisher = "Springer Netherlands",
number = "1-2",

}

TY - JOUR

T1 - Self-organizing latent lattice models for temporal gene expression profiling

AU - Zhang, Byoung Tak

AU - Yang, Jinsan

AU - Chi, Sung Wook

PY - 2003/7/1

Y1 - 2003/7/1

N2 - 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.

AB - 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.

KW - Correlated genes

KW - DNA-microarray data

KW - Learning latent-variable models

KW - Temporal expression profiling

KW - Visualization

UR - http://www.scopus.com/inward/record.url?scp=0038724495&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0038724495&partnerID=8YFLogxK

U2 - 10.1023/A:1023993325417

DO - 10.1023/A:1023993325417

M3 - Article

AN - SCOPUS:0038724495

VL - 52

SP - 67

EP - 89

JO - Machine Learning

JF - Machine Learning

SN - 0885-6125

IS - 1-2

ER -