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 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% |