Molecule-Edit Templates for Efficient and Accurate Retrosynthesis Prediction

TL;DR

This paper introduces METRO, a machine learning model that uses minimal molecule-edit templates to improve the efficiency and accuracy of retrosynthesis prediction, addressing limitations of existing template-based and template-free methods.

Contribution

The paper presents a novel minimal-template approach for retrosynthesis prediction that reduces computational complexity while maintaining high accuracy.

Findings

METRO achieves state-of-the-art results on standard benchmarks.

Minimal templates effectively capture essential reaction patterns.

The approach improves computational efficiency over traditional methods.

Abstract

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.