Skip to main content

Table 5 What is the effect on FunFOLD performance if the native structures are used for each target?

From: FunFOLD: an improved automated method for the prediction of ligand binding residues using 3D models of proteins

Group

ID

N

Mean score for

group

Mean score for

FunFOLD

Increase in mean

score

Mean Z-score for

group

Mean Z-score for

FunFOLD

P-value

(raw score)

P-value

(Z-score)

1 - p-value

(raw score)

1 - p-value

(Z-score)

  

MCC

BDT

MCC

BDT

MCC

BDT

MCC

BDT

MCC

BDT

MCC

BDT

MCC

BDT

MCC

BDT

MCC

BDT

FN407

23

0.793

0.735

0.853

0.774

0.060

0.039

1.160

1.238

1.343

1.388

0.112

0.255

0.119

0.277

0.888

0.746

0.881

0.723

FN293

18

0.786

0.721

0.891

0.828

0.106

0.107

1.086

1.091

1.413

1.483

0.009

0.330

0.008

0.033

0.991

0.967

0.991

0.967

FN202

21

0.691

0.593

0.863

0.790

0.172

0.196

0.841

0.789

1.334

1.414

0.001

0.001

0.001

0.001

0.999

0.999

0.999

0.999

  1. A repeat comparison of FunFOLD performance versus the top 3 groups at CASP8.