Molecule-Edit Templates for Efficient and Accurate Retrosynthesis Prediction
This work addresses the problem of efficient and accurate retrosynthesis prediction for chemists, representing an incremental improvement over existing template-based and template-free methods.
The paper tackles the challenge of retrosynthesis prediction in organic chemistry by introducing METRO, a model that uses minimal templates to predict reactions, achieving state-of-the-art results on standard benchmarks with reduced computational overhead.
Retrosynthesis involves determining a sequence of reactions to synthesize complex molecules from simpler precursors. As this poses a challenge in organic chemistry, machine learning has offered solutions, particularly for predicting possible reaction substrates for a given target molecule. These solutions mainly fall into template-based and template-free categories. The former is efficient but relies on a vast set of predefined reaction patterns, while the latter, though more flexible, can be computationally intensive and less interpretable. To address these issues, we introduce METRO (Molecule-Edit Templates for RetrOsynthesis), a machine-learning model that predicts reactions using minimal templates - simplified reaction patterns capturing only essential molecular changes - reducing computational overhead and achieving state-of-the-art results on standard benchmarks.