BiNA: a visual analytics tool for biological network data

Abstract

Interactive visual analysis of biological high-throughput data in the context of the underlying networks is an essential task in modern biomedicine with applications ranging from metabolic engineering to personalized medicine. The complexity and heterogeneity of data sets require flexible software architectures for data analysis. Concise and easily readable graphical representation of data and interactive navigation of large data sets are essential in this context. We present BiNA--the Biological Network Analyzer--a flexible open-source software for analyzing and visualizing biological networks. Highly configurable visualization styles for regulatory and metabolic network data offer sophisticated drawings and intuitive navigation and exploration techniques using hierarchical graph concepts. The generic projection and analysis framework provides powerful functionalities for visual analyses of high-throughput omics data in the context of networks, in particular for the differential analysis and the analysis of time series data. A direct interface to an underlying data warehouse provides fast access to a wide range of semantically integrated biological network databases. A plugin system allows simple customization and integration of new analysis algorithms or visual representations. BiNA is available under the 3-clause BSD license at http://bina.unipax.info/.

Figure 1. Metabolic pathway representation in BiNA. The KEGG Glycerolipid metabolism of human (on the top) in comparison to the corresponding metabolic representation of BiNA using the KEGG visual style (below).

BiNA's KEGG visual style provides layouts of the pathways which are very similar to the KEGG maps. Additionally, BiNA supports filtering of organism-unspecific parts of a pathway, which improves the readability. In this figure, we manually removed disconnected reactions from BiNA's pathway. Furthermore, neighbored pathways can be directly explored and shown in the same visualization, which clearly supports the biological understanding of relationships across borders of canonical pathways (not shown).

Figure 2. Sub-cellular compartment visualization.

The visualization of the KEGG Apoptosis pathway in a layered sub-cellular compartment model demonstrates BiNA possibilities for integrating cellular location information. For this, information, e.g., from SwissProt , can be used to assign the proteins to the layout layers, which correspond to an abstract cell model. This representation is meaningful for highlighting signaling cascades into the nucleus. Since, proteins can have multiple cellular locations, it is also possible to validate the compartment assignment by projecting the ambiguity level of the cellular locations to the node colors: From unambiguous (red) via ambiguous (rose) to white (no information available).

Figure 3. High-throughput data projection in BiNA.

High-throughput datasets can be projected onto a network by simple drag and drop operations. The upper right hand side of the view shows available datasets. When one of these datasets is dragged onto the main network visualization, possible network attributes for projection arise (green boxes). Afterwards, a dialog opens and permits a more detailed configuration of the projection (not shown).

Figure 4. Access R from BiNA.

The editor for connecting R expressions with functions in BiNA. The new normalize_vsn(x) function calls the underlying R statement normalizeVSN(x).

Figure 5. Derive new data sets using R. Creation of a new sample (dataset) using the callback function defined in Figure 4.

Figure 6. NetworkTrail Application.

The results of NetworkTrail can be visualized using BiNA Webstart. The NetworkTrail plug-in of BiNA provides interactive navigation through the found subnetworks using the toolbox in the top-left corner of the visualization, which supports the evaluation of the results. It is easily possible to switch to a certain subnetwork of size k, or to hide the consensus network, which is the union of all found subnetworks. It is also possible to show or hide the score and the number of relations an edge represents. On the right-hand side, the user can adjust some basic visual mapping properties.

Figure 7. Architecture sketch of BiNA and BN++.

BiNA acts as a visualizer for the BN++ data warehouse system, which semantically integrates several biological databases and stores them into BNDB. BiNA is able to access BNDB directly via SQL, either the MySQL or the Apache Derby version. BiNA consists of a number of plug-ins (OSGi bundles), which are packed together for distribution. Using these plug-ins BiNA can import various file formats, use an R server for processing experimental data, and visualize and analyze networks in different contexts. The user is able to extend the functionality of BiNA using the public API of the OSGi bundles.