Improving Route Development Using Convergent Retrosynthesis Planning

Abstract

Computer-aided synthesis planning approaches have allowed a greater exploration of potential synthesis routes, however, these methods are generally developed to produce linear routes from a singular product to a set of proposed building blocks and are not designed to leverage potential shared paths between targets. These convergent routes allow the simultaneous synthesis of compounds, reducing the time and cost of synthesis across compound libraries. We introduce a novel planning approach to develop convergent synthesis routes, which can search multiple products and intermediates simultaneously, enhancing the overall efficiency and practical applicability of retrosynthetic planning. We evaluate the multi-step synthesis planning approach using extracted convergent routes from Johnson \& Johnson Electronic Laboratory Notebooks (J\&J ELN) and publicly available datasets and observe that solvability is generally very high across those routes, being able to identify a convergent route for over 90\% of the test routes and showing an individual compound solvability of over 98\%.