Dataset Information

Identifying informative subsets of the Gene Ontology with information bottleneck methods.

ABSTRACT:

Motivation

The Gene Ontology (GO) is a controlled vocabulary designed to represent the biological concepts pertaining to gene products. This study investigates the methods for identifying informative subsets of GO terms in an automatic and objective fashion. This task in turn requires addressing the following issues: how to represent the semantic context of GO terms, what metrics are suitable for measuring the semantic differences between terms, how to identify an informative subset that retains as much as possible of the original semantic information of GO.

Results

We represented the semantic context of a GO term using the word-usage-profile associated with the term, which enables one to measure the semantic differences between terms based on the differences in their semantic contexts. We further employed the information bottleneck methods to automatically identify subsets of GO terms that retain as much as possible of the semantic information in an annotation database. The automatically retrieved informative subsets align well with an expert-picked GO slim subset, cover important concepts and proteins, and enhance literature-based GO annotation.

Availability

http://carcweb.musc.edu/TextminingProjects/.

SUBMITTER: Jin B

PROVIDER: S-EPMC2944202 | biostudies-literature | 2010 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Identifying informative subsets of the Gene Ontology with information bottleneck methods.

Jin Bo B Lu Xinghua X

Bioinformatics (Oxford, England) 20100811 19

<h4>Motivation</h4>The Gene Ontology (GO) is a controlled vocabulary designed to represent the biological concepts pertaining to gene products. This study investigates the methods for identifying informative subsets of GO terms in an automatic and objective fashion. This task in turn requires addressing the following issues: how to represent the semantic context of GO terms, what metrics are suitable for measuring the semantic differences between terms, how to identify an informative subset that ...[more]

PMID: 20702400

Similar Datasets

Project description:BACKGROUND: Gene Ontology (GO) annotation, which describes the function of genes and gene products across species, has recently been used to predict protein subcellular and subnuclear localization. Existing GO-based prediction methods for protein subcellular localization use the known accession numbers of query proteins to obtain their annotated GO terms. An accurate prediction method for predicting subcellular localization of novel proteins without known accession numbers, using only the input sequence, is worth developing. RESULTS: This study proposes an efficient sequence-based method (named ProLoc-GO) by mining informative GO terms for predicting protein subcellular localization. For each protein, BLAST is used to obtain a homology with a known accession number to the protein for retrieving the GO annotation. A large number n of all annotated GO terms that have ever appeared are then obtained from a large set of training proteins. A novel genetic algorithm based method (named GOmining) combined with a classifier of support vector machine (SVM) is proposed to simultaneously identify a small number m out of the n GO terms as input features to SVM, where m <<n. The m informative GO terms contain the essential GO terms annotating subcellular compartments such as GO:0005634 (Nucleus), GO:0005737 (Cytoplasm) and GO:0005856 (Cytoskeleton). Two existing data sets SCL12 (human protein with 12 locations) and SCL16 (Eukaryotic proteins with 16 locations) with <25% sequence identity are used to evaluate ProLoc-GO which has been implemented by using a single SVM classifier with the m = 44 and m = 60 informative GO terms, respectively. ProLoc-GO using input sequences yields test accuracies of 88.1% and 83.3% for SCL12 and SCL16, respectively, which are significantly better than the SVM-based methods, which achieve < 35% test accuracies using amino acid composition (AAC) with acid pairs and AAC with dipedtide composition. For comparison, ProLoc-GO using known accession numbers of query proteins yields test accuracies of 90.6% and 85.7%, which is also better than Hum-PLoc (85.0%) and Euk-OET-PLoc (83.7%) using ensemble classifiers with hybridization of GO terms and amphiphilic pseudo amino acid composition for SCL12 and SCL16, respectively. CONCLUSION: The growth of Gene Ontology in size and popularity has increased the effectiveness of GO-based features. GOmining can serve as a tool for selecting informative GO terms in solving sequence-based prediction problems. The prediction system using ProLoc-GO with input sequences of query proteins for protein subcellular localization has been implemented (see Availability).

Project description:The Gene Ontology (GO) vocabulary has been extensively explored to analyze the functions of coexpressed genes. However, despite its extended use in Biology and Medical Sciences, there are still high levels of uncertainty about which ontology (i.e. Molecular Process, Cellular Component or Molecular Function) should be used, and at which level of specificity. Moreover, the GO database can contain incomplete information resulting from human annotations, or highly influenced by the available knowledge about a specific branch in an ontology. In spite of these drawbacks, there is a trend to ignore these problems and even use GO terms to conduct searches of gene expression profiles (i.e. expression + GO) instead of more cautious approaches that just consider them as an independent source of validation (i.e. expression versus GO). Consequently, propagating the uncertainty and producing biased analysis of the required gene grouping hypotheses. We proposed a web tool, Onto-CC, as an automatic method specially suited for independent explanation/validation of gene grouping hypotheses (e.g. coexpressed genes) based on GO clusters (i.e. expression versus GO). Onto-CC approach reduces the uncertainty of the queries by identifying optimal conceptual clusters that combine terms from different ontologies simultaneously, as well as terms defined at different levels of specificity in the GO hierarchy. To do so, we implemented the EMO-CC methodology to find clusters in structural databases [GO Directed acyclic Graph (DAG) tree], inspired on Conceptual Clustering algorithms. This approach allows the management of optimal cluster sets as potential parallel hypotheses, guided by multiobjective/multimodal optimization techniques. Therefore, we can generate alternative and, still, optimal explanations of queries that can provide new insights for a given problem. Onto-CC has been successfully used to test different medical and biological hypotheses including the explanation and prediction of gene expression profiles resulting from the host response to injuries in the inflammatory problem. Onto-CC provides two versions: Ready2GO, a precalculated EMO-CC for several genomes and an Advanced Onto-CC for custom annotation files (http://gps-tools2.wustl.edu/onto-cc/index.html).

Dataset Information

Identifying informative subsets of the Gene Ontology with information bottleneck methods.

Motivation

Results

Availability

Publications

Identifying informative subsets of the Gene Ontology with information bottleneck methods.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets