Microsoft Research· Felix Pultar, John Gardner, Guoqing Liu, Marwin Segler·· 10 d ago
Improving synthesis prediction of small molecules at scale with RetroChimera
Improving synthesis prediction of small molecules at scale with RetroChimera
AI summary
Microsoft published RetroChimera, a retrosynthesis prediction framework, in Nature and open-sourced its implementation and weights. It combines the Transformer model R-SMILES 2 with GNN-based NeuralLoc, using a learned ensemble to rerank predictions. Chemists preferred its single-step reaction predictions in blind testing.
Selection record
Threshold 60Official, first-handFirst 42Second 38
Not admittedSum of both 80 < twice the threshold 120
- Source tier
- Official, first-hand; this tier's threshold is 60
- Pre-filter
- passed：AI模型RetroChimera用于逆合成预测
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: Microsoft Research · microsoft.com