AgBase: a unified resource for functional analysis in agriculture

Abstract

Analysis of functional genomics (transcriptomics and proteomics) datasets is hindered in agricultural species because agricultural genome sequences have relatively poor structural and functional annotation. To facilitate systems biology in these species we have established the curated, web-accessible, public resource 'AgBase' (www.agbase.msstate.edu). We have improved the structural annotation of agriculturally important genomes by experimentally confirming the in vivo expression of electronically predicted proteins and by proteogenomic mapping. Proteogenomic data are available from the AgBase proteogenomics link. We contribute Gene Ontology (GO) annotations and we provide a two tier system of GO annotations for users. The 'GO Consortium' gene association file contains the most rigorous GO annotations based solely on experimental data. The 'Community' gene association file contains GO annotations based on expert community knowledge (annotations based directly from author statements and submitted annotations from the community) and annotations for predicted proteins. We have developed two tools for proteomics analysis and these are freely available on request. A suite of tools for analyzing functional genomics datasets using the GO is available online at the AgBase site. We encourage and publicly acknowledge GO annotations from researchers and provide an online mechanism for agricultural researchers to submit requests for GO annotations.

Figure 1

Analysis of functional datasets using the AgBase GO tools. Together the AgBase GO suite of tools form a pipeline for using GO to analyze microarray and other functional genomics datasets. Square boxes represent the tools, octagonal boxes are points in the pipeline that require human interpretation and ovals represent data files. GORetriever searches a set of annotated databases for existing GO annotations; sequences without annotations from GORetriever are entered into GOanna which BLAST searches a local GO database. GOanna returns up to six proteins that exceed an operator-defined E-value threshold. The user determines if the GO annotations from any of these matches can be used. Users may then choose to add literature-based or expert knowledge GO annotations to produce the final GO Summary file. GOSlimViewer can then be used to generate a high level view of the GO annotation for the proteins in a dataset using GO Slim sets.