The overall performance of different methods in identifying FNs (a) and FPs (b) in the rank-based test and the screen-specific performance of different methods in identifying FNs (c) and FPs (d) in the rank-based test. The error bars represent the estimated standard deviations for the corresponding quantities. The DN, SP, DK and AT represent the four different network similarity measurements, i.e., direct neighbor, shortest path, diffusion kernel and association analysis-based transformation, respectively. Index 1, 2 and 3 represent the three different summarizing formulas, respectively (see Additional file 1 – Table S2 for details). GR represents the GeneRank algorithm.