FlyMine: an integrated database for Drosophila and Anopheles genomics

Abstract

FlyMine is a data warehouse that addresses one of the important challenges of modern biology: how to integrate and make use of the diversity and volume of current biological data. Its main focus is genomic and proteomics data for Drosophila and other insects. It provides web access to integrated data at a number of different levels, from simple browsing to construction of complex queries, which can be executed on either single items or lists.

Figure 1

Aspects. FlyMine groups data into 'aspects', each of which provide a 'homepage' for a different category of data. (a) The aspects available in FlyMine release 6.0. Each aspect page can be accessed by clicking on its icon or title. (b) Example aspect page: Genomics Aspect. Each aspect provides background information on the origin of each of its source datasets through a short description, and references if available. Likewise, links are provided to any source databases. Convenient bulk datasets are made available for browsing, or export in standard format. In addition, relevant template queries and classes for use as starting points in the query builder are provided.

Figure 2

Map of the user interface. The icons at the four corners represent entry points allowing (clockwise from top left): the construction of new queries; search for/running of pre-made 'template' queries; uploading of lists of objects (which can be used in queries); or a quick search for objects based on their identifiers or synonyms. Running a query produces a results page, allowing browsing and paging through results and selection of items for inclusion in lists or export in a variety of formats. Lists can be saved between sessions, set operations can be carried out on multiple lists and the list details page summarizes list contents and provides other tools that operate on lists.

Figure 3

The object details page for the D. melanogaster Notch gene. (a) The left-hand side of the top pane provides a summary for the object being viewed, including the main describing attributes. To the right of the summary, a 'further information' section provides link-outs to relevant databases and access to relevant graphical tools, in this case GBrowse and a graph showing expression of the Notch gene during the D. melanogaster life cycle. (b) For easy navigation, further information for the object being viewed is divided into different sections according to the different 'aspects'. For each aspect, related objects (for example, proteins, for a gene page) from referenced classes and the results of relevant template queries (run using the object being viewed as the variable) are available in-line. From each related object a link is provided to the object details page for that object via the [details...] links. In this example, the objects referenced in the overlappingFeatures class are shown and the results of one template query have been expanded.

Figure 4

Example of a template query. The template 'All pairs of interacting proteins in organism1 → Orthologues in organism2' is shown. All template queries have a 'short name' and a longer description. The short name aids visual scanning of available templates. Template queries consist of a form, in which the user is able to adjust the default constraints on classes and attributes. Each box, or variable, can be constrained to either a single value or, if appropriate, to a list of objects (if the user has lists of the appropriate type stored in their history). The buttons 'Show Results' and 'Edit Query' provide the user with the choice of either viewing the results page, or viewing the query in the query builder, where it may be modified.

Figure 5

The model browser: part of the FlyMine query builder. The model browser initially displays a user-selected class, from where it is possible to browse to other classes via the references between them. This figure shows the Gene class with some of its attributes and referenced classes. These referenced classes (for example, Organism, Proteins) also appear as attributes of the Gene class.

Figure 6

Browsing the data model. Expanding a referenced class in the model browser, in this case the Protein class, shows its attributes and referenced classes, which in turn can also be expanded.

Figure 7

The FlyMine query builder. The query builder consists of three sections that show the data model, constraints and output columns. The model browser in the top left displays the starting class and its attributes (in this case the Gene class and its attributes, including references to other classes). Next to each attribute in the model browser are 'show' and 'constrain' buttons. Clicking on the constrain button brings up a box on the right hand side where a constraint can be specified. The screenshot shows the constraint box that appears after clicking on 'constrain' next to the organism name attribute. Any constraints added are listed in the constraints list on the top right. In the example shown, constraints have already been added to the organism name, attributes for microarray results and assay and for GO annotation name. The query therefore combines four different types of data. Clicking on a 'show' button adds that attribute to the 'Fields selected for output' pane at the bottom of the query builder. In this example the attributes for gene name, microarray assay, mRNA fold-enrichment, mRNA signal and GO annotation name have been added. Any attributes selected in this way will appear in the query results. The 'Show results' button runs the query.

Figure 8

An overview of the InterMine architecture. FlyMine is built using InterMine, which provides the core query system, data integration and web application. The IMStore forms the core of the system; this is accessed from the web application and sends queries to a PostgreSQL relational database. Before execution, the QueryOptimiser re-writes SQL queries to make use of pre-computed tables.