Figure 5From: The BioDICE Taverna plugin for clustering and visualization of biological data: a workflow for molecular compounds explorationTrained map and cluster detection. The map (left) shows the input data objects within regions of similarity (light areas). Dark boundaries divide regions with dissimilar data objects. The map is interactive: an area selection operation generates the list of compounds in the area. The boundaries of the clusters (right) are obtained with a Canny filter and an image segmentation algorithm. The Canny filter can be tuned in order to adjust the clusters detection interactively.Back to article page