Keywords and Phrases
Adaptive Resonance Theory; Biclustering; Coclustering; Gene expression clustering
”Detection of gene mutations is central for assessing genetic factors affecting disease predisposition, genetic causes of a particular disease, and gene-targeted treatment. DNA microarray methods are widely used to detect mutations by contrasting the expression levels of thousands of genes together under varying experimental conditions. The experimental conditions could be diseased cell states compared with the normal cell states. Biclustering, a robust exploratory data analysis tool, can be applied to microarray data to detect subsets of genes that co-express highly only for a subset of experimental conditions. Such detection is crucial for gaining insights into gene regulatory networks, differential gene expression, and gene-disease associations to identify candidate genes for further study. However, biclustering fails to identify functional associations between genes within a bicluster and group functionally related genes that might not co-express significantly.
This work presents a novel biclustering algorithm, TopoBARTMAP, which combines a biclustering ARTMAP (BARTMAP) with a topological ART (TopoART) to improve the quality of biclustering. Whilst producing a graphical representation of space, topological clustering can identify arbitrarily shaped clusters in space that are difficult to detect otherwise. These methods find application in analyzing disease-specific gene subgroups and disease progression. TopoBARTMAP inherits, from TopoART, the ability to detect arbitrarily shaped biclusters whilst remaining robust to noise. These capabilities of TopoBARTMAP are rigorously demonstrated in the study with 35 benchmark cancer datasets. Further, the benchmarking study underpins the statistically significant performance improvement observed in comparison to other compared methods. Using the breast cancer dataset containing expression levels of 39,326 genes observed over 38 samples, the graphical output of TopoBARTMAP is analyzed to detect intra-bicluster-gene associations within the dataset”--Abstract, page iv.
Wunsch, Donald C.
Dagli, Cihan H., 1949-
Electrical and Computer Engineering
M.S. in Computer Engineering
Intelligent Systems Center
Missouri University of Science and Technology
Journal article titles appearing in thesis/dissertation
- TopoBARTMAP: Biclustering ARTMAP with or without topological methods in a blood cancer case study
- TopoBARTMAP: Topological biclustering ARTMAP
x, 91 pages
© 2021 Raghu Yelugam, All rights reserved.
Thesis - Open Access
Electronic OCLC #
Yelugam, Raghu, "Topological biclustering ARTMAP" (2021). Masters Theses. 8023.