Laplacian Eigenmaps for dimensionality reduction and data representation
Neural Computation
Clustering of gene expression data based on shape similarity
EURASIP Journal on Bioinformatics and Systems Biology - Special issue on applications of signal procesing techniques to bioinformatics, genomics, and proteomics
Proceedings of the ACM Conference on Bioinformatics, Computational Biology and Biomedicine
Hi-index | 0.00 |
The gene networks underlying closure of the optic fissure during vertebrate eye development are poorly understood. We used a novel clustering method based on Laplacian Eigenmaps, a nonlinear dimension reduction method, to analyze microarray data from laser capture microdissected (LCM) cells at the site and developmental stages (days 10.5 to 12.5) of optic fissure closure. Our new method provided greater biological specificity than classical clustering algorithms in terms of identifying more biological processes and functions related to eye development as defined by Gene Ontology at lower false discovery rates. This new methodology builds on the advantages of LCM to isolate pure phenotypic populations within complex tissues and allows improved ability to identify critical gene products expressed at lower copy number. The combination of LCM of embryonic organs, gene expression microarrays, and extracting spatial and temporal co-variations appear to be a powerful approach to understanding the gene regulatory networks that specify mammalian organogenesis.