Skip to main content

Table 9 Mean Δ EF and standard deviation for the ECFP and ECFP ext similarity methods (approach B1)

From: Improving structural similarity based virtual screening using background knowledge

DuD set

ECFP

ECFP ext

 

1%

5%

10%

1%

5%

10%

HMGR

8.7 ± 9.4

6.8 ± 8.5

4.2 ± 5.6

0.0 ± 0.0

2.8 ± 2.2

0.9 ± 0.5

ER

8.0 ± 4.0

7.4 ± 3.9

6.7 ± 4.6

6.3 ± 4.8

9.2 ± 1.6

3.3 ± 1.2

PPAR γ

1.3 ± 0.7

7.1 ± 11.2

1.0 ± 0.7

4.2 ± 11.1

3.6 ± 5.7

1.8 ± 2.8

P38 MAP

7.0 ± 5.9

5.9 ± 3.0

3.4 ± 2.0

2.8 ± 5.7

5.0 ± 4.1

2.4 ± 2.1

TK

9.8 ± 6.0

12.1 ± 8.9

10.9 ± 6.4

16.5 ± 8.4

11.4 ± 3.6

4.3 ± 2.0

FXa

7.4 ± 11.3

2.4 ± 2.0

1.7 ± 1.5

3.5 ± 11.0

4.3 ± 5.3

2.0 ± 2.7

ADA

6.3 ± 3.3

6.4 ± 4.5

8.9 ± 6.0

8.3 ± 7.1

7.7 ± 2.0

2.4 ± 1.0

DHFR

2.5 ± 2.0

1.8 ± 1.5

1.8 ± 1.5

1.9 ± 0.9

0.1 ± 0.1

0.0 ± 0.0

AChE

15.0 ± 11.2

5.2 ± 2.3

6.8 ± 3.8

11.0 ± 12.0

9.4 ± 5.6

4.0 ± 2.8

COX-2

8.7 ± 10.6

3.4 ± 1.9

3.4 ± 2.5

6.7 ± 10.0

5.5 ± 5.0

2.1 ± 2.6

w/d/l

 

7 / 0 / 3

5 / 0 / 5

8 / 0 / 2

  1. Mean Δ EF and standard deviation for the ECFP and ECFP ext similarity methods at 1%, 5% and 10% of the database (receptor specific decoy set DuD set ). The extension fingerprint is calculated from all ligands (approach B1). Improvements of ECFP ext compared to ECFP are marked with bold print. w/d/l = wins/draws/losses.