Machine Learning and Synthetic Biology
Event details
| Date | 11.02.2020 |
| Hour | 16:00 |
| Speaker | Prof. Jean-Loup Faulon, National Research Institute for Agriculture, Food and Environment INRAE, Jouy-en-Josas (F) and University of Manchester (UK) |
| Location | |
| Category | Conferences - Seminars |
BIOENGINEERING SEMINAR
Abstract:
We have seen the past few years a growing interest in using machine learning in biology and synthetic biology makes no exception to this trend. The three main learning methods found in the synthetic biology literature are supervised learning, reinforcement and active learning, and in vivo/in vitro learning.
Supervised machine learning is being exploited to predict sequence activities, engineer sequences, associate biological signals with phenotypes, and optimize culture conditions. An example of promiscuous enzyme activity prediction with Gaussian processes will be shown in the context of underground metabolism and metabolome completion.
Reinforcement and active learning are using training sets acquired through an iterative process. These methods are particularly emendable to the Design-Build-Test-Learn synthetic biology cycle. Reinforcement learning will be exemplified for retrosynthesis and active learning to maximize the productivity of TXTL cell-free systems.
Engineering information processing devices in living systems is a long-standing venture of synthetic biology. Yet, the problem of engineering devices that perform basic operations found in machine learning remains largely unexplored. As a first step toward engineering biological learning devices, a metabolic perceptron will be presented. The performances of the perceptron will be exemplified with biological sample classification based on metabolic composition.
References:
Bio:
Education:
Abstract:
We have seen the past few years a growing interest in using machine learning in biology and synthetic biology makes no exception to this trend. The three main learning methods found in the synthetic biology literature are supervised learning, reinforcement and active learning, and in vivo/in vitro learning.
Supervised machine learning is being exploited to predict sequence activities, engineer sequences, associate biological signals with phenotypes, and optimize culture conditions. An example of promiscuous enzyme activity prediction with Gaussian processes will be shown in the context of underground metabolism and metabolome completion.
Reinforcement and active learning are using training sets acquired through an iterative process. These methods are particularly emendable to the Design-Build-Test-Learn synthetic biology cycle. Reinforcement learning will be exemplified for retrosynthesis and active learning to maximize the productivity of TXTL cell-free systems.
Engineering information processing devices in living systems is a long-standing venture of synthetic biology. Yet, the problem of engineering devices that perform basic operations found in machine learning remains largely unexplored. As a first step toward engineering biological learning devices, a metabolic perceptron will be presented. The performances of the perceptron will be exemplified with biological sample classification based on metabolic composition.
References:
- Mellor J, et al. Semi-supervised Gaussian Process for automated enzyme search. ACS Synthetic Biology, 2016, 5(6): 518-528.
- Koch M, et al. Reinforcement Learning for Bioretrosynthesis. ACS Synthetic Biology, 2020, 9(1): 157-168.
- Borkowski O, et al. Large scale active-learning-guided exploration to maximize cell-free production, bioRxiv 751669, doi: https://doi.org/10.1101/751669
- Pandi A, et al. Metabolic Perceptrons for Neural Computing in Biological Systems. Nature Communications, 2019, 10: 3880.
Bio:
Education:
- Ph.D. Computer Science, Ecole des Mines, Paris, 1991
- Habilitation, Theoretical Chemistry, Strasbourg, 2007
- 2015- Director of Research (DR1) at Micalis, INRA , France
- 2014- Professor Manchester Institute of Biotechnology , University of Manchester, UK
- 2010-2015 Director Institute of Systems and Synthetic Biology , CNRS, Genopole, University of Evry, France
- 2009- Head master program in Systems and Synthetic Biology (at the University of Paris-Saclay since 2015)
- 2008-2014 – Professor, Biology Department, University of Evry, Evry, France
- 1995-2008 – Senior and Distinguished Member (2004), Computational Systems Biology Dept. Sandia National Laboratory, Livermore, CA, USA
- 1993-1994 – Research Associate, Computer-Aided Molecular Design Group. Sandia National Laboratory, Albuquerque, NM, USA
- 1991-1993 – Post-doc Penn State University, State College, PA, USA
Practical information
- Informed public
- Free
Organizer
Contact
- Institute of Bioengineering (IBI), Christina Mattsson