Discovery of Prokaryotic Relationships Through Latent Structure of Correlated Nucleotide Sequences
Abstract
This paper describes an application of statistical techniques that have yielded fruitful results in many fields including artificial intelligence and information retrieval to the problem of establishing relationships among organisms. A combination of these techniques constitutes a new method of comparing organisms based on their whole genomic sequences. The method represents genomes as sets of short overlapping nucleotide subsequences and employs latent structure modeling to capture correlations in the observed patterns of their distribution. Factor scores computed to measure the correlations serve as the input to a Ward's hierarchical cluster analysis method, which produces a tree of their relationships. The runtime results indicate that this method allows for the fast and efficient comparison that scales well as the number of organisms increases.
Cite
Text
Muzinich. "Discovery of Prokaryotic Relationships Through Latent Structure of Correlated Nucleotide Sequences." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2005. doi:10.1109/CVPR.2005.443Markdown
[Muzinich. "Discovery of Prokaryotic Relationships Through Latent Structure of Correlated Nucleotide Sequences." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2005.](https://mlanthology.org/cvpr/2005/muzinich2005cvpr-discovery/) doi:10.1109/CVPR.2005.443BibTeX
@inproceedings{muzinich2005cvpr-discovery,
title = {{Discovery of Prokaryotic Relationships Through Latent Structure of Correlated Nucleotide Sequences}},
author = {Muzinich, Natalya},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2005},
pages = {143},
doi = {10.1109/CVPR.2005.443},
url = {https://mlanthology.org/cvpr/2005/muzinich2005cvpr-discovery/}
}