Table 2. Summary of Performance of State-of-the-Art Models for DTBA Predictiona.
| authors | name | method type | data set | data set size/interactions | target variable | R2 | rm2 | RMSE | SCC | PCC | CI |
|---|---|---|---|---|---|---|---|---|---|---|---|
| (116) | KronRLS | ML | Davis | 30 056 (68 ligands and 442 targets) | Kd | 0.580 | 0.407d | 0.573 | 0.883 | ||
| 0.0482, 4 | 0.8402,4 | 0.748e | |||||||||
| 0.4393,4 | 0.6603,4 | 0.861f | |||||||||
| KIBA | 118 254 (2116 drugs and 229 proteins) | KIBA score | 0.413 | 0.3421 | 0.657 | 0.7921 | |||||
| 0.3272, 4 | 0.7022,4 | ||||||||||
| 0.3633,4 | 0.6813,4 | ||||||||||
| Metz | 35 259 (1.421 compounds and 156 kinases) | Ki | 0.335 | 0.781 | 0.793 | ||||||
| 0.3282, 4 | 0.7842,4 | 0.7362 | |||||||||
| 0.1133,4 | 0.8993,4 | 0.6663 | |||||||||
| (90) | SimBoost | ML | Davis | 30 056 (68 ligands and 442 targets) | Kd | 0.703g | 0.6441 | 0.247 | 0.884 | ||
| KIBA | 118 254 (2116 drugs and 229 proteins) | KIBA score | 0.7014 | 0.6291 | 0.204 | 0.847 | |||||
| Metz | 35 259 (1421 compounds and 156 kinases) | Ki | 0.6324 | 0.116 | 0.851 | ||||||
| (96) | PADME | Graph-based | Davis | 30 056 (68 ligands and 442 targets) | Kd | 0.765 | 0.429 | 0.903 | |||
| 0.1442 | 0.8052 | 0.7122 | |||||||||
| 0.5913 | 0.5643 | 0.8543 | |||||||||
| KIBA | 118 254 (2116 drugs and 229 proteins) | KIBA score | 0.745 | 0.433 | 0.858 | ||||||
| 0.5092 | 0.6012 | 0.7742 | |||||||||
| 0.4713 | 0.6233 | 0.7683 | |||||||||
| Metz | 35 259 (1,421 compounds and 156 kinases) | Ki | 0.665 | 0.556 | 0.806 | ||||||
| 0.4482 | 0.7122 | 0.7432 | |||||||||
| 0.3183 | 0.7903 | 0.6963 | |||||||||
| (77) | DeepDTA | DL | Davis | 30 056 (68 ligands and 442 targets) | Kd | 0.630 | 0.511 | 0.878 | |||
| KIBA | 118 254 (2116 drugs and 229 proteins) | KIBA score | 0.673 | 0.440 | 0.863 | ||||||
| BindingDB | 263 534 training samples and 113 142 test samples | Ki | 0.686h | 0.8865 | |||||||
| (117) | WideDTA | DL | Davis | 30 056 (68 ligands and 442 targets) | Kd | 0.512 | 0.820 | 0.886 | |||
| KIBA | 118 254 (2116 drugs and 229 proteins) | KIBA score | 0.423 | 0.856 | 0.875 | ||||||
| (119) | IVPGAN | DL | Davis | 30 056 (68 ligands and 442 targets) | Kd | 0.945 | 0.201 | 0.973 | |||
| 0.8632 | 0.2892 | 0.9492 | |||||||||
| 0.9063 | 0.2203 | 0.9633 | |||||||||
| KIBA | 118 254 (2116 drugs and 229 proteins) | KIBA score | 0.766 | 0.400 | 0.843 | ||||||
| 0.6472 | 0.4702 | 0.8072 | |||||||||
| 0.7063 | 0.4493 | 0.8233 | |||||||||
| Metz | 35 259 (1421 compounds and 156 kinases) | Ki | 0.628 | 0.553 | 0.791 | ||||||
| 0.6172 | 0.5482 | 0.7892 | |||||||||
| 0.5933 | 0.5743 | 0.7783 | |||||||||
| (92) | GANsDTA | DL | Davis | 30 056 (68 ligands and 442 targets) | Kd | 0.653 | 0.525 | 0.881 | |||
| KIBA | 118 254 (2116 drugs and 229 proteins) | KIBA score | 0.675 | 0.473 | 0.866 | ||||||
| (118) | MT-DTI | DL | Davis | 30,056 (68 ligands and 442 targets) | Kd | 0.665 | 0.495 | 0.887 | |||
| KIBA | 118 254 (2,116 drugs and 229 proteins) | KIBA score | 0.738 | 0.390 | 0.882 | ||||||
| (93) | DGraphDTA | Graph-based | Davis | 30 056 (68 ligands and 442 targets) | Kd | 0.700 | 0.450 | 0.867 | 0.904 | ||
| KIBA | 118 254 (2116 drugs and 229 proteins) | KIBA score | 0.786 | 0.355 | 0.903 | 0.904 | |||||
| (120) | MONN | DL | BindingDB | 263 534 training samples and 113 142 test samples | Ki | 0.658 | 0.895 | ||||
| (94) | GraphDTA | Graph-based | Davis | 30 056 (68 ligands and 442 targets) | Kd | 0.478 | 0.893 | ||||
| KIBA | 118 254 (2116 drugs and 229 proteins) | KIBA score | 0.373 | 0.891 | |||||||
| (81) | Affinity2Vec | Graph-based | Davis | 30 056 (68 ligands and 442 targets) | Kd | 0.693 | 0.490 | 0.887 | |||
| KIBA | 118 254 (2116 drugs and 229 proteins) | KIBA score | 0.765 | 0.352 | 0.910 | ||||||
| (115) | DeepMHADTA | DL | Davis | 30 056 (68 ligands and 442 targets) | Kd | 0.701 | 0.494 | 0.895 | |||
| KIBA | 118 254 (2116 drugs and 229 proteins) | KIBA score | 0.719 | 0.431 | 0.876 | ||||||
| (121) | WGNN-DTA | Graph-based | Davis | 30 056 (68 ligands and 442 targets) | Kd | 0.456 | 0.863 | 0.898 | |||
| KIBA | 118 254 (2116 drugs and 229 proteins) | KIBA score | 0.360 | 0.900 | 0.884 |
Abbreviations: R2: Coefficient of Determination, rm2: Modified r2 ;b RMSE: Root Mean Square Error, SCC: Spearman Correlation Coefficient, PCC: Pearson Correlation Coefficient, CI: Concordance Indexc, ML: Machine Learning, Kd: Dissociation Constant, KIBA: Kinase Inhibitor BioActivity, Ki: Inhibition Constant, DL: Deep Learning.
rm2 considers the actual difference between the observed and predicted response data without considering the training set mean.130
The CI is a generalization of the AUC and measures the ability of a model to correctly rank the survival times of individuals. It ranges from 0 to 1, where a higher value indicates better predictive performance.131
Results retrieved from DeepDTA.77
These were obtained under the S2 or cold drug condition; that is, only the drug was not encountered in the training set.
These were obtained under the S3 or cold target condition; that is, only the target was not encountered in the training set.
Results retrieved from PADME.96
Result obtained from Li et al.120