From: Large-scale comparison of machine learning methods for profiling prediction of kinase inhibitors
Molecular feature | Method | AUCg | F1 scoreh | BAi |
---|---|---|---|---|
Molecular graphs | GCNa | 0.729 ± 0.206 | 0.658 ± 0.271 | 0.604 ± 0.127 |
GATb | 0.675 ± 0.225 | 0.636 ± 0.272 | 0.582 ± 0.145 | |
MPNNc | 0.658 ± 0.202 | 0.621 ± 0.298 | 0.557 ± 0.128 | |
Attentive FPd | 0.674 ± 0.207 | 0.661 ± 0.295 | 0.581 ± 0.116 | |
Chemprope | 0.717 ± 0.173 | 0.640 ± 0.291 | 0.573 ± 0.108 | |
FP-GNNf | 0.704 ± 0.223 | 0.627 ± 0.367 | 0.604 ± 0.142 | |
Mean | 0.693 ± 0.028 | 0.641 ± 0.016 | 0.584 ± 0.018 |