Skip to main content
Figure 2 | BMC Research Notes

Figure 2

From: Network module detection: Affinity search technique with the multi-node topological overlap measure

Figure 2

Global control and local control of module detection. The black curve shows the observed relative similarity r Between (K, i) (y-axis) between a module K and the i th closest node versus the growth history (x-axis). The red curve shows the lower bound of the prediction intervals from a local linear regression model. The red horizontal line shows the global threshold T global . According to the global control stopping rule, module growth stops when the black curve falls below T global . According to the local control stopping rule, module growth stops when the black curve falls below the red curve. a) Example where module growth stops because of global control with T global = 0.70. The dashed vertical line shows the final module size. b) Example where module growth stops because of a local control prediction interval with T local = 0.9999.

Back to article page