Table 3 Comparisons of average accuracies (%) against two different strategies for retrosynthesis on the USPTO-50k dataset
From: CNN-based two-branch multi-scale feature extraction network for retrosynthesis prediction
Model | Top-k accuracy % | |||
|---|---|---|---|---|
1 | 3 | 5 | 10 | |
NeuralSym (Plain) | 38.5 | 55.7 | 61.3 | 66.6 |
NeuralSym (Aug) | 45.4 | 67.7 | 73.5 | 81.1 |
CNN-TMN (Plain) | 49.1 | 64.4 | 67.6 | 72.6 |
CNN-TMN (Aug) | 61.1 | 79.1 | 83.9 | 87.7 |