Skip to main content

Table 1 Improvement of prediction quality due to atom specific weighting

From: Combination of scoring schemes for protein docking

 

unopt

amino acid specific

atom specific

amino acid × atom specific

unopt

amino acid specific

atom specific

amino acid × atom specific

unopt

amino acid specific

atom specific

amino acid × atom specific

Optimisation (Benchmark 2.0, 15°)

 

Enzyme-Inhibitor (22)

Antibody-Antigen (18)

Others (30)

No on 1

0

1

3

3

0

1

1

1

0

0

0

0

No = 10

2

5

6

9

1

1

3

3

0

2

1

1

No = 50

4

12

13

14

1

3

6

5

1

4

5

5

No = 100

6

15

16

16

2

9

8

8

2

6

8

7

Average

1222

370

242

283

3119

462

267

295

3088

1560

1303

1323

Validation (Literature-data, 12°)

 

Enzyme-Inhibitor (21)

Antibody-Antigen (4)

Others (4)

No on 1

1

1

1

4

0

0

0

0

1

0

0

0

No = 10

2

5

7

7

0

0

0

0

1

0

0

0

No = 50

6

10

14

12

1

0

0

0

1

0

0

0

No = 100

8

12

14

13

1

0

0

0

1

0

0

0

Average

918

720

669

606

9887

568

499

442

3493

5761

3513

4188

  1. Number of complexes for which a near-native structure can be predicted on the first and within the top10, top50 and top100 ranks. Furthermore the average rank of the first near-native structure is given. These quality measurements are shown for a non-optimised ranking, based on the geometric correlation (unopt), a ranking based on the amino-acid specific weighting factors (amino acid specific), a ranking based on the atom specific weighting factors (atom specific), and for the combination of amino acid and atom specific ranking.