文献类型：期刊文献

英文题名：Towards a hybrid model-driven platform based on flux balance analysis and a machine learning pipeline for biosystem design

作者：Wu, Debiao[1];Xu, Feng[1];Xu, Yaying[1];Huang, Mingzhi[1];Li, Zhimin[1];Chu, Ju[1]

机构：[1]East China Univ Sci & Technol, State Key Lab Bioreactor Engn, 130 Meilong Rd, Shanghai 200237, Peoples R China

年份：2024

卷号：9

期号：1

起止页码：33

外文期刊名：SYNTHETIC AND SYSTEMS BIOTECHNOLOGY

收录：;WOS:【SCI-EXPANDED(收录号:WOS:001214153700001)】；

基金：This work was financially supported by the National Natural Science Foundation of China (Grant NO. 32071461) and the National Key Research and Development Program of China (Grant NO. 2019YFA0904300) .

语种：英文

外文关键词：Metabolic modeling; Machine learning; Flux balance analysis; Biosystems design; Saccharomyces cerevisiae; Succinate dehydrogenase

摘要：Metabolic modeling and machine learning (ML) are crucial components of the evolving next-generation tools in systems and synthetic biology, aiming to unravel the intricate relationship between genotype, phenotype, and the environment. Nonetheless, the comprehensive exploration of integrating these two frameworks, and fully harnessing the potential of fluxomic data, remains an unexplored territory. In this study, we present, rigorously evaluate, and compare ML-based techniques for data integration. The hybrid model revealed that the over-expression of six target genes and the knockout of seven target genes contribute to enhanced ethanol production. Specifically, we investigated the influence of succinate dehydrogenase (SDH) on ethanol biosynthesis in Saccharomyces cerevisiae through shake flask experiments. The findings indicate a noticeable increase in ethanol yield, ranging from 6 % to 10 %, in SDH subunit gene knockout strains compared to the wild-type strain. Moreover, in pursuit of a high-yielding strain for ethanol production, dual-gene deletion experiments were conducted targeting glycerol-3-phosphate dehydrogenase (GPD) and SDH. The results unequivocally demon-strate significant enhancements in ethanol production for the engineered strains dsdh4dgpd1, dsdh5dgpd1, dsdh6dgpd1, dsdh4dgpd2, dsdh5dgpd2, and dsdh6dgpd2, with improvements of 21.6 %, 27.9 %, and 22.7 %, respectively. Overall, the results highlighted that integrating mechanistic flux features substantially improves the prediction of gene knockout strains not accounted for in metabolic reconstructions. In addition, the finding in this study delivers valuable tools for comprehending and manipulating intricate phenotypes, thereby enhancing prediction accuracy and facilitating deeper insights into mechanistic aspects within the field of synthetic biology.