Retro-fallback: retrosynthetic planning in an uncertain world

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tripp, Austin, Maziarz, Krzysztof, Lewis, Sarah, Segler, Marwin, Hernández-Lobato, José Miguel
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913312908771328
author Tripp, Austin
Maziarz, Krzysztof
Lewis, Sarah
Segler, Marwin
Hernández-Lobato, José Miguel
author_facet Tripp, Austin
Maziarz, Krzysztof
Lewis, Sarah
Segler, Marwin
Hernández-Lobato, José Miguel
contents Retrosynthesis is the task of planning 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 algorithms 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.
format Preprint
id arxiv_https___arxiv_org_abs_2310_09270
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Retro-fallback: retrosynthetic planning in an uncertain world
Tripp, Austin
Maziarz, Krzysztof
Lewis, Sarah
Segler, Marwin
Hernández-Lobato, José Miguel
Artificial Intelligence
Machine Learning
Retrosynthesis is the task of planning 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 algorithms 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.
title Retro-fallback: retrosynthetic planning in an uncertain world
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2310.09270