Reinforcement Learning for Bioretrosynthesis
Year: 2019
Type: article
Abstract: Metabolic engineering aims to produce chemicals of interest from living organisms, to advance toward 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 bioretrosynthesis 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 data set of 20 manually curated experimental pathways as well as on a larger data set of 152 successful metabolic engineering projects. Moreover, we provide a novel feature that suggests potential media supplements to complement the enzymatic synthesis plan.
Source: ACS Synthetic Biology
Authors: Mathilde Koch, Thomas Duigou, Jean-Loup Faulon
Institutions: AgroParisTech, Université Paris-Saclay, Microbiologie de l’alimentation au service de la santé, Centre National de la Recherche Scientifique, Commissariat à l'Énergie Atomique et aux Énergies Alternatives, University of Manchester, Génomique Métabolique du Genoscope, Institut de Biologie systémique et synthétique, Genoscope
Language: English
Subfield: Molecular Biology
Domain: Life Sciences
Open Access status: green
Awards: CENTRE FOR SYNTHETIC BIOLOGY OF FINE AND SPECIALITY CHEMICALS, G2558356852, (Bio)synthesis and study of physico-chemical/biological properties of sinapoyl malate analogues: non-toxic and biobased anti-UV compounds for cosmetics industry, G4855065492, G579361868, G5802621812, Institut français de bioinformatique, G6803667113, G8312094183, Metabolic Engineering Machine, G995922834
OpenAlex ID: W2995188634