Skip to main content

Table 4 Performance of Sfcnn, DeepBindRG, AutoDockVina, and Pafnucy on CASF-2013, CSAR_HiQ_NRC_set, and Astex_diverse_set datasets

From: Sfcnn: a novel scoring function based on 3D convolutional neural network for accurate and stable protein–ligand affinity prediction

Dataset

R

RMSE

MAE

Size

Sfcnn performance

 CASF-2013

0.7946

1.4518

1.1139

107

 CSAR_HiQ_NRC_set

0.824

1.277

0.8375

343

 CSAR_HiQ_NRC_set*

0.6758

1.8079

1.3680

149

 Astex_diverse_set

0.6474

1.3627

1.0518

74

DeepBindRG performance

 CASF-2103

0.6394

1.817

1.4829

195

 CSAR_HiQ_NRC_set

0.6585

1.7239

1.3607

343

 Astex_diverse_set

0.4657

1.6209

1.3355

74

AutoDockVina performance

 CASF-2103

0.5725

2.401

1.9462

195

 CSAR_HiQ_NRC_set

0.5707

2.2884

1.7268

343

 Astex_diverse_set

0.422

2.2027

1.7068

74

Pafnucy performance

 CASF-2103

0.5855

1.8491

1.5131

195

 CSAR_HiQ_NRC_set

0.6693

1.6805

1.3336

343

 CSAR_HiQ_NRC_set*

0.7040

1.8868

1.5230

136

 Astex_diverse_set

0.5146

1.4654

1.1732

74

  1. Results (excluding all the Sfcnn performance and the Pafnucy performance on CSAR_HiQ_NRC_set* dataset) cited from Zhang et al. [36]
  2. *indicates the dataset after removal of the overlaps
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us