HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Journal articles

Reinforcement learning for bioretrosynthesis

Abstract : Metabolic engineering aims to produce chemicals of interest from living organisms, to advance towards greener chemistry. Despite efforts, the research and development process is still long and costly and efficient computational design tools are required to explore the chemical biosynthetic space. Here, we propose to explore the bio-retrosynthesis space using an Artificial Intelligence based approach relying on the Monte Carlo Tree Search reinforcement learning method, guided by chemical similarity. We implement this method in RetroPath RL, an open-source and modular command line tool. We validate it on a golden dataset of 20 manually curated experimental pathways as well as on a larger dataset of 152 successful metabolic engineering projects. Moreover, we provide a novel feature, that suggests potential media supplements to complement the enzymatic synthesis plan.
Document type :
Journal articles
Complete list of metadata

https://hal.inrae.fr/hal-02905157
Contributor : Jean-Loup Faulon Connect in order to contact the contributor
Submitted on : Thursday, July 23, 2020 - 11:02:14 AM
Last modification on : Saturday, April 30, 2022 - 3:39:58 AM

Links full text

Identifiers

Citation

Mathilde Koch, Thomas Duigou, Jean-Loup Faulon. Reinforcement learning for bioretrosynthesis. ACS Synthetic Biology, American Chemical Society, 2019, 9 (1), pp.157-168. ⟨10.1021/acssynbio.9b00447⟩. ⟨hal-02905157⟩

Share

Metrics

Record views

25