cluML: A markup language for clustering and cluster validity assessment of microarray data.

Area of Science:

• Bioinformatics
• Computational Biology
• Data Science

Background:

• Traditional data formats for microarray analysis have limitations in storing diverse clustering and validation results.
• Existing methods struggle to represent multiple clustering outcomes, including biclustering, within a single dataset.

Purpose of the Study:

• Introduce cluML (clustering Markup Language), a new XML-based format for microarray data clustering and validation.
• Address limitations of traditional formats by enabling storage of multiple clustering and validation results.
• Facilitate biomedical knowledge representation in gene expression data analysis.

Main Methods:

• Developed cluML as an XML-based markup language.
• Designed cluML to accommodate multiple clustering results (including biclustering).
• Incorporated cluster validity assessment within the cluML framework.

Main Results:

• cluML effectively stores multiple clustering and validation results for gene expression data.
• The format overcomes limitations of traditional microarray data representations.
• Demonstrated cluML's utility in supporting biomedical knowledge representation.

Conclusions:

• cluML is an effective tool for microarray data clustering and validation.
• The language supports comprehensive representation of clustering and validation results.
• cluML's applicability extends beyond DNA microarrays to other biomedical and physical data.