MICALIS Institute, INRAE, University of Paris-Saclay, Jouy-en-Josas, France.
MICALIS Institute, INRAE, University of Paris-Saclay, Jouy-en-Josas, France.
Curr Opin Chem Biol. 2021 Dec;65:85-92. doi: 10.1016/j.cbpa.2021.06.002. Epub 2021 Jul 16.
Among the main learning methods reviewed in this study and used in synthetic biology and metabolic engineering are supervised learning, reinforcement and active learning, and in vitro or in vivo learning. In the context of biosynthesis, supervised machine learning is being exploited to predict biological sequence activities, predict structures and engineer sequences, and optimize culture conditions. Active and reinforcement learning methods use training sets acquired through an iterative process generally involving experimental measurements. They are applied to design, engineer, and optimize metabolic pathways and bioprocesses. The nascent but promising developments with in vitro and in vivo learning comprise molecular circuits performing simple tasks such as pattern recognition and classification.
在本研究中回顾的主要学习方法中，有监督学习、强化学习和主动学习，以及体外或体内学习。在生物合成方面，正在利用监督机器学习来预测生物序列的活性，预测结构和设计序列，并优化培养条件。主动学习和强化学习方法使用通过迭代过程获得的训练集，该过程通常涉及实验测量。它们应用于设计、工程和优化代谢途径和生物工艺。处于起步阶段但很有前途的体外和体内学习的发展包括执行简单任务（如模式识别和分类）的分子电路。
