Accelerating organism engineering through the application of AI

生物系统工程需要在生物设计和实施的不同层次上整合实验输入和输出数据。这些因素可以很容易地归类为与生物学有关的内在因素，或与介质和温度等物理条件有关的外部因素。在考虑非微生物生物合成途径的设计和实现时，它们并不遵循一套已知的规则，但我们可以将其分解为3类：第一，该途径本身的遗传设计可以由酶的同一性调节，其实例化所使用的遗传元件包括启动子、5‘非编码区、RBS、基因顺序、拷贝数。第二，宿主代谢网络，它通常为生物合成过程提供输入前体和能量，并通过新的途径施加在系统上的代谢负荷。最后，外部因素，如细胞菌株，培养基成分，时间和温度。这个项目将专注于将机器人合成生物学家扩展到更雄心勃勃的生物合成途径，在大肠杆菌中生产高价值化学物质。第一种方法是开发基于CRISPR的工具来调节宿主代谢网络，从而为系统提供交互节点，从而学习如何针对特定的生物生产任务优化宿主。第二种方法是集成人工代谢网络(AMN)，这是代谢反应大肠杆菌通量平衡分析(FBA)模型的白盒神经网络实现。第三，这些将在生物合成途径中实施：首先是紫罗兰素，这是一种具有色素输出的模型5-基因生物合成途径，随后是乙酸丁酯，这是一种自然积累在细胞外部的挥发性风味化合物，可以很容易地使用溶剂覆盖法捕获。

The engineering of biological systems requires the integration of experimental inputs and outputdata across different levels of biodesign and implementation. These can readily be classed intoeither intrinsic factors, which relate to the biology, or external factors that relate to physicalconditions such as media and temperature. When considering the design and implementation of amicrobial biosynthetic pathway, they do not follow a set of prior-known rules, but we can breakthem down into 3 classes: firstly, the genetic design of the pathway itself can be modulated byenzyme identity, and genetic elements used for its instantiation, including promoter, 5'UTR, RBS,gene order, copy number. Secondly, the host metabolic network, which usually provides the inputprecursor and energy for the biosynthetic process and the metabolic load that is exerted on thesystem by the new pathway. Finally, the external factors such as cell strain, media composition, timeand temperature.This project will focus on extending the Robot Synthetic Biologist to more ambitious biosyntheticpathways for the production of high value chemicals in E. coli. The first approach will be to developCRISPR based tools that can modulate the host metabolic network, thus providing the system withinteractive nodes that can thus learn how to optimise the host for the specific bioproduction task.Secondly, it will integrate Artificial Metabolic Networks (AMN), which are a white box neural netimplementation of the E. coli Flux Balance Analysis (FBA) model of metabolic reactions. Thirdly,these will be implemented in biosynthetic pathways: initially for Violacein, a model 5-genebiosynthetic pathway with a pigment output and subsequently for butyl acetate, a volatile flavourcompound that naturally accumulates external to the cell and can easily be captured using a solventoverlay.