by Xiang Guo, Rongxiang Liu, Craig D Shriver, Hai Hu, Michael N Liebman
Abstract:
MOTIVATION: Pathway modeling requires the integration of multiple data including prior knowledge. In this study, we quantitatively assess the application of Gene Ontology (GO)-derived similarity measures for the characterization of direct and indirect interactions within human regulatory pathways. The characterization would help the integration of prior pathway knowledge for the modeling. RESULTS: Our analysis indicates information content-based measures outperform graph structure-based measures for stratifying protein interactions. Measures in terms of GO biological process and molecular function annotations can be used alone or together for the validation of protein interactions involved in the pathways. However, GO cellular component-derived measures may not have the ability to separate true positives from noise. Furthermore, we demonstrate that the functional similarity of proteins within known regulatory pathways decays rapidly as the path length between two proteins increases. Several logistic regression models are built to estimate the confidence of both direct and indirect interactions within a pathway, which may be used to score putative pathways inferred from a scaffold of molecular interactions.
Reference:
Assessing semantic similarity measures for the characterization of human regulatory pathways. (Xiang Guo, Rongxiang Liu, Craig D Shriver, Hai Hu, Michael N Liebman), In Bioinformatics (Oxford, England), volume 22, 2006.
Bibtex Entry:
@article{Guo2006,
abstract = {MOTIVATION: Pathway modeling requires the integration of multiple data including prior knowledge. In this study, we quantitatively assess the application of Gene Ontology (GO)-derived similarity measures for the characterization of direct and indirect interactions within human regulatory pathways. The characterization would help the integration of prior pathway knowledge for the modeling. RESULTS: Our analysis indicates information content-based measures outperform graph structure-based measures for stratifying protein interactions. Measures in terms of GO biological process and molecular function annotations can be used alone or together for the validation of protein interactions involved in the pathways. However, GO cellular component-derived measures may not have the ability to separate true positives from noise. Furthermore, we demonstrate that the functional similarity of proteins within known regulatory pathways decays rapidly as the path length between two proteins increases. Several logistic regression models are built to estimate the confidence of both direct and indirect interactions within a pathway, which may be used to score putative pathways inferred from a scaffold of molecular interactions.},
author = {Guo, Xiang and Liu, Rongxiang and Shriver, Craig D and Hu, Hai and Liebman, Michael N},
doi = {10.1093/bioinformatics/btl042},
issn = {1367-4803},
journal = {Bioinformatics (Oxford, England)},
keywords = {Databases, Protein,Gene Expression Regulation,Gene Expression Regulation: physiology,Humans,Information Storage and Retrieval,Information Storage and Retrieval: methods,Natural Language Processing,Protein Interaction Mapping,Protein Interaction Mapping: methods,Proteins,Proteins: classification,Proteins: metabolism,SML-LIB-BIBLIO,Semantics,Signal Transduction,Signal Transduction: physiology,lang:ENG},
mendeley-tags = {SML-LIB-BIBLIO,lang:ENG},
month = apr,
number = {8},
pages = {967--73},
pmid = {16492685},
title = {{Assessing semantic similarity measures for the characterization of human regulatory pathways.}},
url = {http://www.ncbi.nlm.nih.gov/pubmed/16492685},
volume = {22},
year = {2006}
}