Table 4 Comparison of model accuracy on single reactant reaction dataset using ECFP and MACCS keys
From: Substructure-based neural machine translation for retrosynthetic prediction
| Â | MACCS | ECFP (Radius, nBits) | |||
|---|---|---|---|---|---|
1,1024 | 1,2048 | 2,1024 | 2,2048 | ||
Encoder | 126 | 1024 | 2016 | 1024 | 2048 |
Decoder | 126 | 1024 | 2027 | 1024 | 2048 |
Ave. length | 74 | 56 | 56 | 74 | 74 |
| Â | Accuracy | ||||
\(T_{c} = 1.0\) | 29.0% | 35.6% | 37.6% | 9.1% | 10.1% |
\(T_{c} \ge 0.85\) | 57.7% | 50.7% | 52.0% | 28.4% | 30.0% |
\(\overline{T_{c}}\) | 0.84 | 0.80 | 0.80 | 0.66 | 0.66 |