Retro-fallback: retrosynthetic planning in an uncertain world

Published: 28 Oct 2023, Last Modified: 06 Dec 2023NeurIPS2023-AI4Science PosterEveryoneRevisionsBibTeX
Keywords: Retrosynthesis, planning, chemistry, search
TL;DR: We propose an algorithm to produce multiple retrosynthesis plans whose real-life outcomes are uncorrelated
Abstract: Retrosynthesis is the task of proposing a series of chemical reactions to create a desired molecule from simpler, buyable molecules. While previous works have proposed algorithms to find optimal solutions for a range of metrics (e.g. shortest, lowest-cost), these works generally overlook the fact that we have imperfect knowledge of the space of possible reactions, meaning plans created by the algorithm may not work in a laboratory. In this paper we propose a novel formulation of retrosynthesis in terms of stochastic processes to account for this uncertainty. We then propose a novel greedy algorithm called retro-fallback which maximizes the probability that at least one synthesis plan can be executed in the lab. Using in-silico benchmarks we demonstrate that retro-fallback generally produces better sets of synthesis plans than the popular MCTS and retro* algorithms. We encourage the reader to view the full version of this paper at
Submission Track: Original Research
Submission Number: 73