Retrosynthesis is a fundamental but challenging task in organic chemistry, with broad applications in fields such as drug design and synthesis. Given a target molecule, the goal of retrosynthesis is to find out a series of reactions which could be assembled into a synthetic route which starts from purchasable molecules and ends at the target molecule. The uncertainty of reactions used in retrosynthetic planning, which is caused by hallucinations of backward models, has recently been noticed. In this paper we propose a succinct probabilistic model to describe such uncertainty. Based on the model, we propose a new retrosynthesis planning algorithm called retro-prob to maximize the successful synthesis probability of target molecules, which acquires high efficiency by utilizing the chain rule of derivatives. Experiments on the Paroutes benchmark show that retro-prob outperforms previous algorithms, retro* and retro-fallback, both in speed and in the quality of synthesis plans.

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.

Image created using DALL-E with the prompt "Games, Chemistry, Artificial Intelligence". In modern pharmaceutical research, active ingredients are designed using a computer. Only in a second step, one determines, still away from the wet lab, whether these complex molecules can actually be synthesized. This is considered a true art among chemists as it is highly complex and requires a broad knowledge of chemical reactions. At the pharmaceutical company Bayer, one uses a time-intensive Artificial Neural Network (ANN) to predict which reactions could immediately produce the candidate at hand.

The problem of retrosynthetic planning can be framed as one player game, in which the chemist (or a computer program) works backwards from a molecular target to simpler starting materials though a series of choices regarding which reactions to perform. This game is challenging as the combinatorial space of possible choices is astronomical, and the value of each choice remains uncertain until the synthesis plan is completed and its cost evaluated. Here, we address this problem using deep reinforcement learning to identify policies that make (near) optimal reaction choices during each step of retrosynthetic planning. Using simulated experience or self-play, we train neural networks to estimate the expected synthesis cost or value of any given molecule based on a representation of its molecular structure. We show that learned policies based on this value network outperform heuristic approaches in synthesizing unfamiliar molecules from available starting materials using the fewest number of reactions. We discuss how the learned policies described here can be incorporated into existing synthesis planning tools and how they can be adapted to changes in the synthesis cost objective or material availability.