Title : Hyperconic Machine Learning to Predict Microbial Growth
Abstract:
The design and control of biological reactors depends upon the correct calibration and selection of kinetic parameters from the exponential phase in the microbial growth. Nowadays, kinetic microbial parameters reported in the literature of biochemical engineering are obtained based on specific growth conditions, thus limiting their possible application in a wide variety of dynamic models. In this paper, we propose an adaptive machine learning approach to predict microbial growth and provide information on the effect that variations of pH (5, 7, 9) and concentration of the culture media (10, 20, 40, 60, 80, 100%v/v) have on the growth rate. We study biological reactions and obtain a set of experimental exploratory data using the Pseudomonas aeruginosa. The versatile and robust metabolism of P. aeruginosa is responsible of its ability of growth in different environment conditions even at low nutrient and oxygen levels, in an sample range of temperatures (4°- 42° C) and polluted sites. As first contribution, we propose a technique to gather experimental data via measurements of optical density, microbial growth, from the MultiskanTM FC Microplate Photometer, Thermo Scientific. Our second contribution consist in integrating the Hyperconic Multilayer Perceptron (HCMLP) as computational and mathematical approach to predict microbial growth across all the set of conditions of the experimental design. HCMLP is a state-of-the-art method to define complex nonlinear decision boundaries, in the parameters? space, using a mix of ideas from conformal geometry and neural networks, and focusing on quadratic hyper-surfaces through multiple hidden layers. As a consequence, we generate precise hyper-surface responses which predicts microbial growth even in values not evaluated during the experimental stage. Finally, our statistical testing and comparisons validate that the proposed experimental, mathematical and computational framework is robust and capable of predicting the dynamic growth of bacteria P. aeruginosa using two main operation conditions: pH and concentration culture media. In the future, we plan to apply our proposed methodology to other bacterial strains and advance HCMLP for forecasting dynamics of other multiple microbial measurements under a wide variety of conditions. The design and control of biological reactors depends upon the correct calibration and selection of kinetic parameters from the exponential phase in the microbial growth. Nowadays, kinetic microbial parameters reported in the literature of biochemical engineering are obtained based on specific growth conditions, thus limiting their possible application in a wide variety of dynamic models. In this paper, we propose an adaptive machine learning approach to predict microbial growth and provide information on the effect that variations of pH (5, 7, 9) and concentration of the culture media (10, 20, 40, 60, 80, 100%v/v) have on the growth rate. We study biological reactions and obtain a set of experimental exploratory data using the Pseudomonas aeruginosa. The versatile and robust metabolism of P. aeruginosa is responsible of its ability of growth in different environment conditions even at low nutrient and oxygen levels, in an sample range of temperatures (4°- 42° C) and polluted sites. As first contribution, we propose a technique to gather experimental data via measurements of optical density, microbial growth, from the MultiskanTM FC Microplate Photometer, Thermo Scientific. Our second contribution consist in integrating the Hyperconic Multilayer Perceptron (HCMLP) as computational and mathematical approach to predict microbial growth across all the set of conditions of the experimental design. HCMLP is a state-of-the-art method to define complex nonlinear decision boundaries, in the parameters? space, using a mix of ideas from conformal geometry and neural networks, and focusing on quadratic hyper-surfaces through multiple hidden layers. As a consequence, we generate precise hyper-surface responses which predicts microbial growth even in values not evaluated during the experimental stage. Finally, our statistical testing and comparisons validate that the proposed experimental, mathematical and computational framework is robust and capable of predicting the dynamic growth of bacteria P. aeruginosa using two main operation conditions: pH and concentration culture media. In the future, we plan to apply our proposed methodology to other bacterial strains and advance HCMLP for forecasting dynamics of other multiple microbial measurements under a wide variety of conditions.
