Related Experiment Videos
Clustering gene expression pattern and extracting relationship in gene network based on artificial neural networks
Jihua Huang1, Hiroshi Shimizu, Suteaki Shioya
1Department of Biotechnology, Graduate School of Engineering, Osaka University, Suita, Osaka 565-0871, Japan.
Journal of Bioscience and Bioengineering
|October 20, 2005
Summary
This study uses self-organizing maps (SOM) and artificial neural networks (ANN) to analyze gene expression data, revealing key patterns and network interconnections in yeast cell cycles.
Area of Science:
- Bioinformatics
- Computational Biology
- Systems Biology
Background:
- DNA microarray technologies generate massive gene expression datasets.
- Extracting biological insights like expression patterns and gene networks from this data is crucial.
Purpose of the Study:
- To mine biological information, specifically typical gene expression patterns and gene network interconnections, from large datasets.
- To develop and validate a computational approach for analyzing gene expression data.
Main Methods:
- Clustering of gene expression data using a self-organizing map (SOM) algorithm.
- Extraction of relationships between expression patterns using a three-layer artificial neural network (ANN) model.
- Evaluation of SOM clustering using biological and statistical indices.
- Validation of the ANN model using a created test dataset.
Main Results:
- Successful clustering of gene expression data using SOM.
- Identification and extraction of relationships between typical expression patterns via ANN.
- Visualization of interconnections within yeast cell cycle phases (early G1, late G1, S, G2, M).
Conclusions:
- The combined SOM and ANN approach effectively extracts biological information from massive gene expression datasets.
- This method enables the discovery of gene network interconnections and typical expression patterns, exemplified by the yeast cell cycle analysis.