The monitoring of oil production process by deep learning based on morphology in oleaginous yeasts.

BACKGROUND: Monitoring jar fermenter-cultured microorganisms in real time is important for controlling productivity of bioproducts in large-scale cultivation settings. Morphological data is used to understand the growth and fermentation states of these microorganisms during monitoring. Oleaginous yeasts are used for their high productivity of single-cell oils but the relationship between lipid productivity and morphology has not been elucidated in these organisms. RESULTS: In this study, we investigated the relationship between the morphology of oleaginous yeasts (Lipomyces starkeyi and Rhodosporidium toruloides were used) and their cultivation state in a large-scale cultivation setting using a real-time monitoring system. We combined this with deep learning by feeding a large amount of high-definition cell images obtained from the monitoring system to a deep learning algorithm. Our results showed that the cell images could be grouped into 7 distinct groups and that a strong correlation existed between each group and its biochemical activity (growth and oil-productivity). CONCLUSIONS: This is the first report describing the morphological variations of oleaginous yeasts in a large-scale cultivation, and describes a promising new avenue for improving productivity of microorganisms in large-scale cultivation through the use of a real-time monitoring system combined with deep learning. KEY POINTS: • A real-time monitoring system followed the morphological change of oleaginous yeasts. • Deep learning grouped them into 7 distinct groups based on their morphology. • A correlation between the cultivation state and the shape of the yeast was observed.

A real-time monitoring system for automatic morphology analysis of yeast cultivation in a jar fermenter.

The monitoring of microbial cultivation in real time and controlling their cultivation aid in increasing the production yield of useful material in a jar fermenter. Common sensors such as dissolved oxygen (DO) and pH can easily provide general-purpose indexes but do not reveal the physiological states of microbes because of the complexity of measuring them in culture conditions. It is well known from microscopic observations that the microbial morphology changes in response to the intracellular state or extracellular environment. Recently, studies have focused on rapid and quantitative image analysis techniques using machine learning or deep learning for gleaning insights into the morphological, physiological or gene expression information in microbes. During image analysis, it is necessary to retrieve high-definition images to analyze the microbial morphology in detail. In this study, we have developed a microfluidic device with a high-speed camera for the microscopic observation of yeast, and have constructed a system capable of generating their morphological information in real-time and at high definition. This system was connected to a jar fermenter, which enabled the automatic sampling for monitoring the cultivation. We successfully acquired high-definition images of over 10,000 yeast cells in about 2.2 s during ethanol fermentation automatically for over 168 h. We recorded 33,600 captures containing over 1,680,000 cell images. By analyzing these images, the morphological changes of yeast cells through ethanol fermentation could be captured, suggesting the expansion of the application of this system in controlling microbial fermentation using the morphological information generated. KEY POINTS: • Enables real-time visualization of microbes in a jar fermenter using microscopy. • Microfluidic device for acquiring high-definition images. • Generates a large amount of image data by using a high-speed camera.