Skip to main content

Advertisement

Table 20 Win/loss counts for all random folds for extended similarites on DuD set ( α (0.0, 0.1); approach B2)

From: Improving structural similarity based virtual screening using background knowledge

       ECFP ext      MCS ext
       c1%      5%      10%      1%      5%      10%
  Win Loss Win Loss Win Loss Win Loss Win Loss Win Loss
HMGR 102 8 88 22 98 12 48 7 49 6 55 0
ER 70 40 74 36 74 36 87 23 89 21 67 43
PPAR γ 93 17 86 24 88 22 69 41 95 15 72 38
P38 MAP 93 17 96 14 103 7 93 17 100 10 110 0
TK 75 35 95 15 94 16 96 14 85 25 82 28
FXa 101 9 67 43 80 30 99 11 84 26 83 27
ADA 86 24 79 31 98 12 60 39 88 11 76 23
DHFR 75 35 107 3 110 0 100 10 110 0 110 0
ACHE 86 24 95 15 96 14 87 23 98 12 94 16
COX-2 69 41 76 34 78 32 65 45 86 24 90 20
Sum 850 250 863 237 919 181 804 230 884 150 839 195
  1. Win/loss counts for all 110 random folds (10 repetitions * 11 αs) for extended similarites MCS ext and ECFP ext versus their base similarities MCS and ECFP for the receptor specific decoy sets DuD set at 1%, 5% and 10% of the database. The extension fingerprint is calculated from 10% (20% for HMGR, TK and ADA) of the ligands (approach B2).