All living things require metabolism. Metabolism is the process by which the body changes food and drink into energy. During this process, calories in food and drinks mix with oxygen to make the energy the body needs. Even at rest, a body needs energy for all it does.
Metabolism is arguably the best indicator of the cell’s physiological state. Once considered only a passive result of the state of a cell, it is now widely recognized as the main contributor to cellular behavior. It can provide valuable data for disease diagnostics, toxicological studies, and treatment follow-up or optimization in a variety of applications from clinical to environmental or agricultural sciences. More specifically, it is a key player in a number of diseases, including diabetes, neurodegenerative diseases, and cancer, where altered metabolism is now accepted as a hallmark
How an organism metabolizes nutrients is a complex process, and simulating the chemical processes that keep life going is a difficult challenge.
With the advent of bioinformatics and computational biology, computational and mathematical techniques can provide an accurate simulation of biological processes.
Model of metabolism
Any biological process, including metabolic processes, can be represented as a pathway with
interconnected nodes, and thus, mathematical models such as graph theory, ordinary differential
equations, Petri nets, etc., have an obvious role in the simulation of biological systems. For a structural view, a metabolic network can be perceived as a bipartite graph that consists of two sets of nodes representing metabolites and biochemical processes.
Cell metabolism is a network of biochemical reactions transforming metabolites to fulfill biological functions. At the core of this biochemical network there are catabolic pathways that break down molecules to generate energy, which is then used to fuel biosynthetic processes and to do mechanical work.
Cell metabolism is characterized by three fundamental energy demands: to sustain cell maintenance, to trigger aerobic fermentation and to achieve maximum metabolic rate. The basal metabolic state of a cell is characterized by a maintenance energy demand. It is currently assumed that the maintenance energy represents the energy cost incurred to maintain ions balance between the cell and the extracellular medium.
When cells grow, move or perform other functions the energy requirements increase beyond the basal maintenance demand. Cells utilize glycolysis and oxidative phosphorylation to satisfy these energetic demands. Finally, there is the energy demand necessary to sustain the maximum growth rate, or maximum metabolic rate in general. The energy demand at maximum growth rate can only be sustained by glycolysis and therefore we can estimate the maximum energy requirements of cells from their maximum reported rates of fermentation.
There are different methods to model a metabolic system: steady-state analysis (e.g., FBA) involves a set of linear equations, while kinetic simulations involve ordinary differential equations (ODEs). Each variable represents the variation of a metabolite concentration, in a dynamic or steady state, where the concentration depends on the rates of the reactions that produce and consume that metabolite. They are highly effective at predicting the behavior of small systems where sufficient experimental data can be collected for model calibration and parameter estimation .
For large systems, however, the use of kinetic modeling remains challenging. The increasing demand for systems-level genome-scale analyses has recently led to the widespread use of constraint-based steady-state models and their unsteady-state extensions.
Constraint-based modelling is the most widely used approach to model the behavior of metabolism, often assuming that cells have to fulfill a given task (e.g., ATP production, growth, or proliferation) or to optimize the production of a given compound. Such models have two main advantages: first, they do not need dynamic or kinetic data as they are based on mass balance across the metabolic network; second, they are suitable for integration of different omic layers at genome scale to improve their predictive performance.
In addition, accurate modeling of metabolism, made possible with improved computer technology and the availability of a large amount of biological data, is becoming increasingly important for a number of highly diverse areas from bioreactor growth, drug target determination and optimization and testing to environmental bioremediation, for example.
Many of these applications produce large amounts of data requiring different aspects of analysis and allowing the derivation of different knowledge including sample or biomolecule clustering or classification, the selection of major features and components, as well as the optimization of model parameters. Machine learning has been used for all of these tasks. Machine learning has been defined as a field of study that gives computers the ability to learn without being explicitly programmed.”
Although machine learning is an old area of computer sciences, the availability of sufficiently large datasets providing learning material, as well as computer power providing learning ability resulted in machine learning applications flourishing in biological applications only recently.
Using AI to understand cellular metabolism
Theoretically, the procedure can be represented by mathematical equations with parameters specific to each organism. But practically determining those parameters is a complicated matter due to the lack of experimental data.
Scientists generally need large experimental data and processing power to find these parameters. EPFL scientists proposed a deep-learning-based computational framework reproducing the dynamic metabolic properties observed in cells. The framework called REKINDLE could pave the way for more efficient and accurate modeling of metabolic processes.
Ljubisa Miskovic of EPFL’s Laboratory of Computational Systems Biotechnology and co-PI of the study said, “REKINDLE will allow the research community to reduce computational efforts in generating kinetic models by several orders of magnitude. It will also help postulate new hypotheses by integrating biochemical data in these models, elucidating experimental observations, and steering new therapeutic discoveries and biotechnology designs.”
Subham Choudhury, the first author of the study, said, “The overarching aim of metabolic modeling is to describe the cellular metabolic behavior to such a degree that understanding and predicting the eﬀects of variations in cellular states and environmental conditions can reliably be tested for a wide gamut of studies in health, biotechnology, and systems and synthetic biology. We hope that REKINDLE facilitates building metabolic models for the broader community.”
The technique has direct biotechnological applications because kinetic models are crucial for numerous investigations, including those on bioproduction, drug targeting, interactions between microbes, and bioremediation.