TY - JOUR TI - Machine learning-assisted discovery of growth decision elements by relating bacterial population dynamics to environmental diversity AU - Aida, Honoka AU - Hashizume, Takamasa AU - Ashino, Kazuha AU - Ying, Bei-Wen A2 - Altan-Bonnet, Grégoire A2 - Barkai, Naama A2 - Thessen, Anne VL - 11 PY - 2022 DA - 2022/08/26 SP - e76846 C1 - eLife 2022;11:e76846 DO - 10.7554/eLife.76846 UR - https://doi.org/10.7554/eLife.76846 AB - Microorganisms growing in their habitat constitute a complex system. How the individual constituents of the environment contribute to microbial growth remains largely unknown. The present study focused on the contribution of environmental constituents to population dynamics via a high-throughput assay and data-driven analysis of a wild-type Escherichia coli strain. A large dataset constituting a total of 12,828 bacterial growth curves with 966 medium combinations, which were composed of 44 pure chemical compounds, was acquired. Machine learning analysis of the big data relating the growth parameters to the medium combinations revealed that the decision-making components for bacterial growth were distinct among various growth phases, e.g., glucose, sulfate, and serine for maximum growth, growth rate, and growth delay, respectively. Further analyses and simulations indicated that branched-chain amino acids functioned as global coordinators for population dynamics, as well as a survival strategy of risk diversification to prevent the bacterial population from undergoing extinction. KW - bacterial growth KW - machine learning KW - culture medium KW - decision-making chemicals KW - population dynamics KW - survival strategy KW - data mining JF - eLife SN - 2050-084X PB - eLife Sciences Publications, Ltd ER -