The following is translated from the original:
Understanding how cells process nutrients and produce energy (collectively called metabolism) is crucial to biology. Modern biology generates large data sets about various cellular activities, but integrating and analyzing large amounts of data about cellular processes to determine metabolic states is a complex task.
Kinetic models provide a way to decode this complexity by providing a mathematical representation of cellular metabolism. They serve as detailed maps describing how molecules interact and transform within cells, and how matter is transformed into energy and other products over time. This helps scientists understand the biochemical processes that support cellular metabolism. Despite its potential, developing kinetic models remains challenging due to the difficulty of determining the parameters that control cellular processes.
A research team led by Ljubisa Miskovic and Vassily Hatzimanikatis of the École Polytechnique Fédérale de Lausanne (EPFL) has now created RENISSANCE, an artificial intelligence-based tool that simplifies the creation of dynamic models. RENISSANCE combines data from various types of cells to accurately describe metabolic states, making it easier to understand cell functions. RENAISSANCE is a major advancement in computational biology, opening up new avenues for research and innovation in the fields of health and biotechnology.
In research published in the journal Nature Catalysis, researchers used RENISSANCE to create a kinetic model that accurately reflects the metabolic behavior of E. coli. The tool successfully generated a model that matched experimentally observed metabolic behavior, simulating how bacteria adjust their metabolism over time in a bioreactor.
Dynamic models have also proven to be robust, maintaining stability even when disturbed by genetic and environmental conditions. This shows that the model can reliably predict cell responses to different scenarios, enhancing its practicality in research and industrial applications.
“Despite advances in omics technology, insufficient data coverage remains a continuing challenge,” Miskovic said. “For example, metabolomics and proteomics can only detect and quantify a limited number of metabolites and proteins. Modeling techniques that integrate and coordinate genomic data from different sources can address this limitation and enhance system understanding.
“By combining genomic data with other relevant information, such as extracellular medium content, physicochemical data and professional knowledge, RENISSANCE allows us to accurately quantify unknown intracellular metabolic states, including metabolic fluxes and metabolite concentrations.”
RENAISSANCE’s ability to accurately simulate cellular metabolism is important, providing a powerful tool for studying metabolic changes, whether or not caused by disease, and assisting in the development of new therapies and biotechnology. Its ease of use and efficiency will enable a wider range of researchers in academia and industry to effectively utilize dynamic models and promote collaboration.
If you want to learn more, you can click on the link below the video.
Thank you for watching this video. If you like it, please subscribe and like it. thank
Original text:https://phys.org/news/2024-08-ai-tool-cell-metabolism-precision.html
More information: Subham Choudhury et al., Generative machine learning generates kinetic models that accurately characterize metabolic states in cells, Natural Catalysis (2024). DOI：10.1038/s41929-024-01220-6
Journal Information: Natural Catalysis
Oil tubing: