Retrosynthetic Analysis
A computational chemistry method that works backward from a target molecule to derive feasible synthetic routes. It traditionally relied on chemists' experience, and is now often performed using machine learning models combined with tree search.
Timeline (last 90 days)
The core task of retrosynthesis analysis is, given a target molecule, to work backward to feasible synthetic routes; PostEra's approach is to model reaction prediction as a sequence-to-sequence or graph-to-graph problem, training models on large-scale reaction datasets (such as USPTO patent reaction data).
The combinatorial explosion of chemical reaction space is a difficulty for retrosynthesis models: a route often has a dozen or more steps, each with multiple candidates, and errors accumulate step by step.
All Facts (2)
The core task of retrosynthesis analysis is, given a target molecule, to work backward to feasible synthetic routes; PostEra's approach is to model reaction prediction as a sequence-to-sequence or graph-to-graph problem, training models on large-scale reaction datasets (such as USPTO patent reaction data).
50%UnverifiedThe combinatorial explosion of chemical reaction space is a difficulty for retrosynthesis models: a route often has a dozen or more steps, each with multiple candidates, and errors accumulate step by step.
50%