Evaluating Molecule Synthesizability via Retrosynthetic Planning and Reaction Prediction
This addresses the problem of synthesizability assessment for drug discovery researchers, offering a more reliable metric than existing synthetic accessibility scores, though it is incremental in building on recent advances in synthetic route generation.
The paper tackles the challenge of evaluating molecule synthesizability in drug design by proposing a new data-driven metric that leverages retrosynthetic planners and reaction predictors, demonstrating its efficacy through comprehensive evaluations of generative models.
A significant challenge in wet lab experiments with current drug design generative models is the trade-off between pharmacological properties and synthesizability. Molecules predicted to have highly desirable properties are often difficult to synthesize, while those that are easily synthesizable tend to exhibit less favorable properties. As a result, evaluating the synthesizability of molecules in general drug design scenarios remains a significant challenge in the field of drug discovery. The commonly used synthetic accessibility (SA) score aims to evaluate the ease of synthesizing generated molecules, but it falls short of guaranteeing that synthetic routes can actually be found. Inspired by recent advances in top-down synthetic route generation and forward reaction prediction, we propose a new, data-driven metric to evaluate molecule synthesizability. This novel metric leverages the synergistic duality between retrosynthetic planners and reaction predictors, both of which are trained on extensive reaction datasets. To demonstrate the efficacy of our metric, we conduct a comprehensive evaluation of round-trip scores across a range of representative molecule generative models.