Table 4.
Recent developments using machine learning (ML) algorithms in molecular docking.
| SF Name | ML Algorithm | Training Database | Best Performance | Generic or Family Specific | Type of Docking Study | Reference |
|---|---|---|---|---|---|---|
| RF-Score | RF a | PDBbind | Rp b = 0.776 | Generic | BAP c | Ballester 2010 [77] |
| B2BScore | RF | PDBbind | Rp = 0.746 | Generic | BAP | Liu 2013 [192] |
| SFCScoreRF | RF | PDBbind | Rp = 0.779 | Generic | BAP | Zilian, 2013 [202] |
| PostDOCK | RF | Constructed from PDB | 92% accuracy | Generic | VS d | Springer, 2005 [181] |
| - | SVM e | DUD | - | Both | VS | Kinnings, 2011 [175] |
| ID-Score | SVR f | PDBbind | Rp = 0.85 | Generic | BAP | Li, 2013 [203] |
| NNScore | NN g | PDB; MOAD; PDBbind-CN | EF = 10.3 | Generic | VS | Durrant, 2010 [79] |
| CScore | NN | PDBbind | Rp = 0.7668 (gen.) Rp = 0.8237 (fam. spec.) | Both | BAP | Ouyang, 2011 [174] |
| - | Deep NN | CSAR, DUD-E | ROCAUC = 0.868 | Generic | VS | Ragoza, 2017 [196] |
| - | Deep NN | DUD-E | ROCAUC = 0.92 | Both | VS | Imrie, 2018 [183] |
| DLScore | Deep NN | PDBbind | Rp = 0.82 | Generic | BAP | Hassan, 2018 [173] |
| DeepVS | Deep NN | DUD | ROCAUC = 0.81 | Generic | VS | Pereira, 2016 [177] |
| Kdeep | Deep NN | PDBbind | Rp = 0.82 | Generic | BAP | Jiménez, 2018 [78] |
a Random Forest; b Pearson’s Correlation Coefficient; c Binding Affinity Prediction; d Virtual Screening; e Support Vector Machine; f Support Vector Regression; g Neural Network.