Orange Bioinformatics extends Orange, a data mining software package, with common functionality for bioinformatics. The provided functionality can be accessed as a Python library or through a visual programming interface (Orange Canvas). The latter is also suitable for non-programmers.
In Orange Canvas the analyst connects basic computational units, called widgets, into data flow analytics schemas. Two units-widgets can be connected if they share a data type. Compared to other popular tools like Taverna, Orange widgets are high-level, integrated potentially complex tasks, but are specific enough to be used independently. Even elaborate analyses rarely consist of more than ten widgets; while tasks such as clustering and enrichment analysis could be executed with up to five widgets. While building the schema each widget is independently controlled with settings, the settings do not conceptually burden the analyst.
Orange Bioinformatics provides access to publicly available data, like GEO data sets, Biomart, GO, KEGG, Atlas, ArrayExpress, and PIPAx database. As for the analytics, there is gene selection, quality control, scoring distances between experiments with multiple factors. All features can be combined with powerful visualization, network exploration and data mining techniques from the Orange data mining framework.