From the source

Improving synthesis prediction of small molecules at scale with RetroChimera

Open-weight retrosynthesis model for molecular synthesis planning

Microsoft Research published RetroChimera, an open-weight retrosynthesis model that predicts synthesis routes for small molecules by combining two complementary neural models—R-SMILES 2 and NeuralLoc—using a learned ensembling strategy.

In blind tests, expert chemists preferred RetroChimera's reaction predictions over preceding models and literature reactions.

The implementation and weights are available on GitHub and via Microsoft Foundry.

From the source
In blind tests, expert chemists preferred disconnections of complex molecules suggested by RetroChimera over those obtained from its constituent sub-models, as well as those from more established approaches, and even from the test set itself.
microsoft.com

Other stories

Other stories

Improving synthesis prediction of small molecules at scale with RetroChimera

From the source

Other stories