A Deep Learning with Expert Augmentation Approach for Route Scoring in Organic Synthesis

The selection of efficient multi-step synthesis routes is a fundamental challenge in organic synthesis. Comparing different routes involves numerous parameters, economic considerations, and the integration of nuanced chemical knowledge. While computer-aided synthesis planning (CASP) tools can generate synthetic routes, evaluating their overall feasibility and quality continues to rely heavily on human expertise, often lacking consistency and reproducibility. To address this, we have developed a data-driven scoring model that incorporates significant human input. Experts selected key synthesis aspects to score and determined the most representative features of chemical knowledge. The model produces target-specific, generalizable scores for synthetic routes, achieving a top-1 ranking accuracy of 60 \% when benchmarked against experimental data. Evaluation bins, defined by human experts, were incorporated into the final score alongside route length, ensuring a comprehensive assessment. We demonstrate that this criterion and the resulting route rankings align with expert judgment and synthesis feasibility, learned from published reaction data.