Table 1 Overall comparison on retrosynthesis prediction in top-k accuracy (%).
From: G2Retro as a two-step graph generative models for retrosynthesis prediction
Method type | Method | Coverage(%) | Reaction type known | Reaction type unknown | ||||||
|---|---|---|---|---|---|---|---|---|---|---|
1 | 3 | 5 | 10 | 1 | 3 | 5 | 10 | |||
TB | Retrosim12 | 100.0 | 52.9 | 73.8 | 81.2 | 88.1 | 37.3 | 54.7 | 63.3 | 74.1 |
Neuralsym13 | 100.0 | 55.3 | 76.0 | 81.4 | 85.1 | 44.4 | 65.3 | 72.4 | 78.9 | |
GLN14 | 93.3 | 64.2 | 79.1 | 85.2 | 90.0 | 52.5 | 69.0 | 75.6 | 83.7 | |
MHNreact15 | 100.0 | - | - | - | - | 50.5 | 73.9 | 81.0 | 87.9 | |
LocalRetro16 | 98.1 | 63.9 | 86.8 | 92.4 | 96.3 | 53.4 | 77.5 | 85.9 | 92.4 | |
TF | SCROP17 | 100.0 | 59.0 | 74.8 | 78.1 | 81.1 | 43.7 | 60.0 | 65.2 | 68.7 |
LV-Trans18 | 100.0 | - | - | - | - | 40.5 | 65.1 | 72.8 | 79.4 | |
GET19 | 100.0 | 57.4 | 71.3 | 74.8 | 77.4 | 44.9 | 58.8 | 62.4 | 65.9 | |
Chemformer20 | 100.0 | - | - | - | - | 54.3 | - | 62.3 | 63.0 | |
Graph2SMILES21 | 100.0 | - | - | - | - | 51.2 | 66.3 | 70.4 | 73.9 | |
TiedTransformer22 | 100.0 | - | - | - | - | 47.1 | 67.1 | 73.1 | 76.3 | |
GTA23 | 100.0 | - | - | - | - | 51.1 | 67.6 | 74.8 | 81.6 | |
Dual24 | 100.0 | 65.7 | 81.9 | 84.7 | 85.9 | 53.6 | 70.7 | 74.6 | 77.0 | |
Retroformer25 | 100.0 | 64.0 | 82.5 | 86.7 | 90.2 | 53.2 | 71.1 | 76.6 | 82.1 | |
MEGAN26 | 100.0 | 60.7 | 82.0 | 87.5 | 91.6 | 48.1 | 70.7 | 78.4 | 86.1 | |
Semi-TB | RetroXpert27 | 100.0 | 62.1 | 75.8 | 78.5 | 80.9 | 50.4 | 61.1 | 62.3 | 63.4 |
G2G28 | 97.9 | 61.0 | 81.3 | 86.0 | 88.7 | 48.9 | 67.6 | 72.5 | 75.5 | |
GraphRetro29 | 95.0 | 63.9 | 81.5 | 85.2 | 88.1 | 53.7 | 68.3 | 72.2 | 75.5 | |
RetroPrime30 | 100.0 | 64.8 | 81.6 | 85.0 | 86.9 | 51.4 | 70.8 | 74.0 | 76.1 | |
G2Retro | 97.5 | 63.1 | 84.2 | 88.5 | 91.7 | 53.9 | 74.6 | 80.7 | 86.6 | |
G2Retro-B | 97.5 | 63.6 | 83.6 | 88.4 | 91.5 | 54.1 | 74.1 | 81.2 | 86.7 | |
