RespectM revealed metabolic heterogeneity powers deep learning for reshaping the DBTL cycle

Synthetic biology, relying on Design-Build-Test-Learn (DBTL) cycle, aims to solve medicine, manufacturing, and agriculture problems. However, the DBTL cycle’s Learn (L) step lacks predictive power for the behavior of biological systems, resulting from the incompatibility between sparse testing data and chaotic metabolic networks. Herein, we develop a method, “RespectM,” based on mass spectrometry imaging, which is able to detect metabolites at a rate of 500 cells per hour with high efficiency. In this study, 4,321 single cell level metabolomics data were acquired, representing metabolic heterogeneity. An optimizable deep neural network was applied to learn from metabolic heterogeneity and a “heterogeneity-powered learning (HPL)” based model was trained as well. By testing the HPL based model, we suggest minimal operations to achieve high triglyceride production for engineering. The HPL strategy could revolutionize rational design and reshape the DBTL cycle. [Display omitted] •A strategy “RespectM” is proposed for microbial single-cell level metabolomics (MSCLM)•Over 4,321 MSCLM data are acquired by using the RespectM strategy•Heterogeneity-powered learning (HPL) is established with MSCLM data•The HPL-based model could reshape traditional DBTL cycle of synthetic biology Machine learning; Metabolic Engineering; Synthetic biology