No abstract

No abstract

In microbial manufacturing, yeast extract is an important component of the growth media. The production of heterologous proteins often varies because of the yeast extract composition. To identify why this reduces protein production, the effects of yeast extract composition on the growth and green fluorescent protein (GFP) production of engineered Escherichia coli were investigated using a deep neural network (DNN)‐mediated metabolomics approach. We observed 205 peaks from the various yeast extracts using gas chromatography‐mass spectrometry. Principal component analyses of the peaks identified at least three different clusters. Using 20 different compositions of yeast extract in M9 media, the yields of cells and GFP in the yeast extract‐containing media were higher than those in the control without yeast extract by approximately 3.0‐ to 5.0‐fold and 1.5‐ to 2.0‐fold, respectively. We compared machine learning models and found that DNN best fit the data. To estimate the importance of each variable, we performed DNN with a mean increase error calculation based on a permutation algorithm. This method identified the significant components of yeast extract. DNN learning with varying numbers of input variables provided the number of significant components. The influence of specific components on cell growth and GFP production was confirmed with a validation cultivation.

This a preprint and has not been peer reviewed. Data may be preliminary.

Natural media are often used for various commercial bioprocesses by manufacturers to cut raw material cost. However, the components of the raw materials varies between lot-to-lots and brand-to-brands. The varieties of raw materials influence to the cell growths and materials productivities, and results in unstable production across batches in manufacturing processes. To ensure the quality of raw materials among batches, it is necessary to perform a laboratory screening to purchasing the optimal one, and ensure a desirable performance in industrial process. To solve the serious problems in bioprocesses, it is developing that a modelling methodology using composition of raw materials, named us “substratome”, obtained by non-targeted metabolomicslike methods can estimate the cell growth and bio-productions. Here, we will present that two model studies: [1] Escherichia coli growths have been estimated from hydrophilic components in yeast extract obtained by gas chromatography-mass spectrometry (GC-MS), and [2] bioethanol production have been estimated by the volatile components in corncob and corn stover hydrolysates obtained by GC-MS; by partial least square regression (PLS-R). Additionally, we will present preliminary results to solve the same issues by using artificial intelligence.