Table 3. EF at FPF of 0.001 Determined on Training and Test Sets of Best Performing Ensembles Selected To Maximize EF at FPF of 0.001a.
androgen
receptor |
CDK2 |
PPAR-δ |
|||||||
---|---|---|---|---|---|---|---|---|---|
method | size | training | test | size | training | test | size | training | test |
exhaustive | 4 | 232.1 ± 87.2 | 151.8 ± 73.9 | 2 | 211.9 ± 57.9 | 148.3 ± 50.3 | 3 | 183.3 ± 83.0 | 116.7 ± 64.04 |
slow heuristic | 4 | 232.1 ± 87.2 | 151.8 ± 73.9 | 2 | 211.9 ± 57.9 | 148.3 ± 50.3 | 3 | 183.3 ± 83.0 | 116.7 ± 64.04 |
fast heuristic | 3 | 232.1 ± 87.2 | 133.9 ± 70.1 | 1 | 207.63 ± 57.5 | 152.5 ± 50.9 | 2 | 175.0 ± 76.6 | 125.0 ± 62.2 |
The column labeled “size” gives the number of target conformations in the optimally performing ensemble identified by each method; 95% confidence intervals are given. Androgen receptor ensembles were constructed from 10 MD conformations identified using pocket volume clustering and a crystal structure. CDK2 ensembles were constructed from five MD conformations identified using RMSD-based pocket clustering and a crystal structure. PPAR δ ensembles were constructed from 12 crystal structures.