Laboratory of Systems and Synthetic Biology, Wageningen University & Research, 6708 WE Wageningen, The Netherlands.
Department of Science and Research, dsm-firmenich, Science & Research, 2600 MA Delft, The Netherlands.
ACS Synth Biol. 2024 Apr 19;13(4):1312-1322. doi: 10.1021/acssynbio.4c00035. Epub 2024 Mar 28.
Industrial biotechnology uses Design-Build-Test-Learn (DBTL) cycles to accelerate the development of microbial cell factories, required for the transition to a biobased economy. To use them effectively, appropriate connections between the phases of the cycle are crucial. Using -coumaric acid (pCA) production in as a case study, we propose the use of one-pot library generation, random screening, targeted sequencing, and machine learning (ML) as links during DBTL cycles. We showed that the robustness and flexibility of the ML models strongly enable pathway optimization and propose feature importance and Shapley additive explanation values as a guide to expand the design space of original libraries. This approach allowed a 68% increased production of pCA within two DBTL cycles, leading to a 0.52 g/L titer and a 0.03 g/g yield on glucose.
工业生物技术利用设计-构建-测试-学习（DBTL）循环来加速微生物细胞工厂的开发，这是向生物基经济转型所必需的。为了有效地利用它们，循环各阶段之间的适当连接至关重要。本文以对香豆酸（pCA）生产为例，提出在 DBTL 循环中使用一锅文库生成、随机筛选、靶向测序和机器学习（ML）作为连接。我们表明，ML 模型的稳健性和灵活性可以强有力地促进途径优化，并提出特征重要性和 Shapley 可加性解释值作为扩展原始文库设计空间的指南。该方法使 pCA 的产量在两个 DBTL 循环内增加了 68%，达到 0.52 g/L 的滴度和 0.03 g/g 的葡萄糖产率。
