by Haiyuan Yu, Ronald Jansen, Gustavo Stolovitzky, Mark Gerstein
Abstract:
Many classifications of protein function such as Gene Ontology (GO) are organized in directed acyclic graph (DAG) structures. In these classifications, the proteins are terminal leaf nodes; the categories 'above' them are functional annotations at various levels of specialization and the computation of a numerical measure of relatedness between two arbitrary proteins is an important proteomics problem. Moreover, analogous problems are important in other contexts in large-scale information organization--e.g. the Wikipedia online encyclopedia and the Yahoo and DMOZ web page classification schemes.
Reference:
Total ancestry measure: quantifying the similarity in tree-like classification, with genomic applications. (Haiyuan Yu, Ronald Jansen, Gustavo Stolovitzky, Mark Gerstein), In Bioinformatics (Oxford, England), volume 23, 2007.
Bibtex Entry:
@article{Yu2007,
abstract = {Many classifications of protein function such as Gene Ontology (GO) are organized in directed acyclic graph (DAG) structures. In these classifications, the proteins are terminal leaf nodes; the categories 'above' them are functional annotations at various levels of specialization and the computation of a numerical measure of relatedness between two arbitrary proteins is an important proteomics problem. Moreover, analogous problems are important in other contexts in large-scale information organization--e.g. the Wikipedia online encyclopedia and the Yahoo and DMOZ web page classification schemes.},
author = {Yu, Haiyuan and Jansen, Ronald and Stolovitzky, Gustavo and Gerstein, Mark},
doi = {10.1093/bioinformatics/btm291},
issn = {1367-4811},
journal = {Bioinformatics (Oxford, England)},
keywords = {Chromosome Mapping,Chromosome Mapping: methods,Evolution, Molecular,Genetic Variation,Genetic Variation: genetics,Phylogeny,Proteins,Proteins: classification,Proteins: genetics,Proteins: metabolism,Quantitative Trait Loci,Quantitative Trait Loci: genetics,SML-LIB-BIBLIO,Sequence Analysis, DNA,Sequence Analysis, DNA: methods,lang:ENG},
mendeley-tags = {SML-LIB-BIBLIO,lang:ENG},
month = aug,
number = {16},
pages = {2163--73},
pmid = {17540677},
title = {{Total ancestry measure: quantifying the similarity in tree-like classification, with genomic applications.}},
url = {http://www.ncbi.nlm.nih.gov/pubmed/17540677},
volume = {23},
year = {2007}
}