[Gene clustering analysis of DNA microarray data].

Area of Science:

• Statistics
• Bioinformatics
• Computational Biology

Context:

• Microarray experiments generate large, complex, multivariate datasets.
• Analyzing gene expression data requires robust statistical methods.
• Existing clustering methods present limitations for high-dimensional biological data.

Purpose:

• To review and evaluate clustering methods for DNA microarray gene expression data.
• To discuss the advantages and disadvantages of supervised, unsupervised, and model-based clustering approaches.
• To identify the need for novel, specialized clustering techniques for microarray analysis.

Summary:

• This paper reviews various clustering techniques, including supervised, unsupervised, and model-based methods.
• The merits and defects of each method are discussed in the context of gene expression data from DNA microarrays.
• The review highlights the methodological and computational challenges posed by large-scale biological datasets.

Impact:

• Provides a comprehensive overview of clustering methods applicable to gene expression data analysis.
• Informs the development of more effective and realistic clustering algorithms for bioinformatics.
• Aims to advance the statistical analysis of complex biological data from high-throughput experiments.