Skip to main content
. 2012 Apr 13;7(4):e35254. doi: 10.1371/journal.pone.0035254

Table 3. A comparison between the similarity-based method (Eq.10) and the interaction-based method (Eq.6) in identifying the 2,138 drugs in the Inline graphic dataset (cf. Supporting Information S2).

Prediction order Similarity-based Interaction-based Difference
1 40.36% 67.40% 27.04%
2 13.89% 21.09% 7.20%
3 9.17% 13.47% 4.30%
4 5.99% 7.16% 1.17%
5 3.32% 4.91% 1.59%
6 2.76% 3.46% 0.70%
7 0.65% 1.54% 0.89%
8 0.23% 0.75% 0.52%
9 0.09% 0.75% 0.66%
10 0.05% 0.56% 0.51%
11 0.05% 0.09% 0.04%
12 0.00% 0.33% 0.33%
13 0.09% 0.09% 0.00%
14 0.05% 0.05% 0.05%