MiMiR: a comprehensive solution for storage, annotation and exchange of microarray data

Abstract

Background: The generation of large amounts of microarray data presents challenges for data collection, annotation, exchange and analysis. Although there are now widely accepted formats, minimum standards for data content and ontologies for microarray data, only a few groups are using them together to build and populate large-scale databases. Structured environments for data management are crucial for making full use of these data.

Description: The MiMiR database provides a comprehensive infrastructure for microarray data annotation, storage and exchange and is based on the MAGE format. MiMiR is MIAME-supportive, customised for use with data generated on the Affymetrix platform and includes a tool for data annotation using ontologies. Detailed information on the experiment, methods, reagents and signal intensity data can be captured in a systematic format. Reports screens permit the user to query the database, to view annotation on individual experiments and provide summary statistics. MiMiR has tools for automatic upload of the data from the microarray scanner and export to databases using MAGE-ML.

Conclusion: MiMiR facilitates microarray data management, annotation and exchange, in line with international guidelines. The database is valuable for underpinning research activities and promotes a systematic approach to data handling. Copies of MiMiR are freely available to academic groups under licence.

Figure 1

Two views of MiMiR. Figure 1a shows information flow in and out of the database. Information about the experimental design, spots on the array (the sequence of each reporter), signal intensities for each coordinate on the scanned array and the derived spot level data are uploaded into the database. The same interface is also used for queries and to update the data. Information about the data in MiMiR is available via web-based reports. Data on individual experiments may be exported as MAGE-ML to databases such as ArrayExpress. Figure 1b shows the architecture of the database and the underlying applications. The BC4J framework drives interactions between the user interface and the data model. JClient mediates navigation of the database. XDK permits the creation of XML directly from MiMiR. Tomcat offers potential for remote access of the database by users on different sites.

Figure 2

Data captured in MiMiR. Diagram showing the information captured from the details of the experiment through to the information gained from the scanned array and how they are linked. Although arrows indicate the logical flow of information capture as the experiment proceeds, data entry can be initiated at any of the boxes containing bold text and connected to other information about the experiment at a later stage.

Figure 3

A snapshot of the user interface showing how experimental factors are captured. A snapshot of the data entry screen showing how the 'factors' (the variables) in an experiment are captured within MiMiR. The experiment involved treatment of cells in culture with 0, 0.04, 0.1 or 0.2 mM hydrogen peroxide and harvesting at 0, 2, 4 or 8 hours. The lower part of the screen shows the MiMiR Ontology Viewer (MOV) with the MGED Ontology displayed as a tree in the pane on the left. Definitions of terms highlighted in the tree are displayed on the right. The Factor Category and Value columns at the top of the screen were populated using MGED Ontology terms selected from MOV. The measurement kind, measurement unit type and measurement unit were selected from drop-down menus and the Factor Name and the Measurement Value were entered manually.