CS Forum: Using Machine Learning in Synthetic Biology: the Design-Build-Test and Learn cycle
Synthetic biology and metabolic engineering have succeeded in the biosynthesis of numerous commodity or high value compounds.
Prof. Jean-Loup Faulon, Institut of Systems & Synthetic Bioogy, Université d'Evry-Val d'Essonne, France
Abstract:
Synthetic biology and metabolic engineering have succeeded in the biosynthesis of numerous commodity or high value compounds. Yet, the choice of pathways and enzymes used for such successful applications was many times made ad hoc, or required expert knowledge of the specific biochemical reactions. In order to rationalize this process we have developed the computer-aided design (CAD) tool RetroPath [1] that explores and enumerates metabolic pathways connecting the endogenous metabolites of a chassis cell to a target compound. Namely, our tool queries for target activities the list of enzymes found in metabolic databases based on their annotated and predicted activities based on a tensor product kernel [2]. Next, it ranks pathways based on the predicted efficiency of the available enzymes, the toxicity of the intermediate metabolites and the calculated maximum product flux.
As an illustration of the power of rational design, RetroPath compiled the top-ranking pathways producing the flavonoid pinocembrin (a antibacterials targeting Staphylococcus aureus), narrowing down a list of nine million possible enzyme combinations to a number that could be easily assembled and tested. We next constructed the top-ranked enzyme combinations, four of which displayed significant yields. One round of metabolic network optimization based on RetroPath output further increased pinocembrin titers 17-fold [3]. In total, 12 out of the 13 enzymes tested in this work displayed a performance that was in accordance with its predicted score. These results validate the ranking function of our CAD tool, and open the way to its utilization in the biosynthesis of novel compounds.
1. Carbonell P, Parutto P, Herisson J, Pandit S.B, Faulon J.L. XTMS: pathway design in an eXTended metabolic space. Nucleic Acids Res. in press 2014, [PMID: 24792156].
2. Faulon J.L., Misra M., Martin S., Sale, K., Sapra R.. Genome Scale Enzyme-metabolites and Drug-Target interaction predictions using the signature molecular descriptor, Bioinformatics, 24, 225-233, 2008.
3. Fernández-Castané A, Fehér T, Carbonell P, Pauthenier C, Faulon J.L. Computer-aided design for metabolic engineering. J Biotechnol. in press 2014, [PMID: 24704607].
About the speaker:
Prof. Jean-Loup Faulon is the director of the institute of Systems and Synthetic Biology (a CNRS research unit in Evry, France) and the course director of a master program in Systems and Synthetic Biology and the University of Paris Saclay. Since 2014 he holds a Chair in Synthetic Biology in the Chemistry School at the University of Manchester. Jean-Loup Faulon obtained his PhD in 1991 in computational chemistry at Ecole des Mines, Paris and a Habilitation in 2007 in theoretical chemistry from the University of Strasbourg. From 1991 to 2008, Jean-Loup Faulon was a research associate at Penn Sate University and then a distinguished scientist at Sandia a US national laboratory. While in the US, he was the PI or co-PI of a dozen of projects funded by the US National Institute of Health, Chevron, Exxon, and the US DOE Genome To Life and Math Information programs. He has also been a research director at the Joint Bioenergy Institute. Jean-Loup Faulon main research interest is the application of Computer-Aided-Design for chemical and biological structures and networks. He is the author of more than 80 peer reviewed publications and book chapters in metabolic engineering, systems biology and synthetic biology. Jean-Loup Faulon research is currently being funded by the ANR, the CNRS, Genopole, and the SYNBIOCHEM BBSRC center grant.
Host: Juho Rousu