Generalized regression neural network for converting fluorescence emission ratio to ATP concentration

Problems associated with cell biochemistry are nowadays of general concern. In particular, much attention is being paid to the problem of changes in cytosolic ATP Levels. ATeam, a genetically encoded fluorescence resonance energy transfer (FRET)-based biological indicator, can monitor the fluorescence emission ratio against ATP concentration. Up to now, change curve has always acted as a bridge between fluorescence emission ratio and ATP concentration due to that generating a precise change curve allows for the optimized possibility to convert ATP concentrations from sampled fluorescence emission ratios. Before that, an existing problem is how to incorporate an effective mechanism into the generation of change curve. As before, logistic equation as a classical but powerful model has universally been used to detect the quantitative relationship between fluorescence emission ratio and ATP concentration by modelling data points with a curve. However, the prediction by logistic model is still not satisfactory observed from experiments. To address the question, we combine the working mechanism of ATeam and machine learning by introducing generalized regression neural network (GRNN) model to capture minor changes appearing in the process of changes of fluorescence emission ratio, by which any ATP concentration can be calculated. Experiments designed in this paper is carried out to certify the accuracy of GRNN model compared to logistic model, suggesting that GRNN model is superior to logistic model in accuracy and effectiveness as a solution to convert fluorescence emission ratio to ATP concentration.

[1]  B. M. Mar'yanov,et al.  Use of Linear Regression for the Processing of Curves of Differential Potentiometric Titration of a Binary Mixture of Heterovalent Ions Using Precipitation Reactions , 2003 .

[2]  P. Righetti,et al.  Affinity titration curves: determination of dissociation constants of lectin-sugar complexes and of their pH-dependence by isoelectric focusing electrophoresis. , 1980, Biochimica et biophysica acta.

[3]  D. Fell,et al.  A method for accounting for maintenance costs in flux balance analysis improves the prediction of plant cell metabolic phenotypes under stress conditions. , 2013, The Plant Journal.

[4]  T. Uemura,et al.  In vivo fluorescent adenosine 5'-triphosphate (ATP) imaging of Drosophila melanogaster and Caenorhabditis elegans by using a genetically encoded fluorescent ATP biosensor optimized for low temperatures. , 2013, Analytical chemistry.

[5]  Sargur N. Srihari,et al.  On multiple classifier systems for pattern recognition , 1992, Proceedings., 11th IAPR International Conference on Pattern Recognition. Vol.II. Conference B: Pattern Recognition Methodology and Systems.

[6]  Takeharu Nagai,et al.  Visualization of ATP levels inside single living cells with fluorescence resonance energy transfer-based genetically encoded indicators , 2009, Proceedings of the National Academy of Sciences.

[7]  E. Hiraki,et al.  A Dual Voltage Power System by Battery/Supercapacitors Hybrid Configuration , 2005, 2005 IEEE 36th Power Electronics Specialists Conference.

[8]  Maria Papadopouli,et al.  On User-Centric Modular QoE Prediction for VoIP Based on Machine-Learning Algorithms , 2016, IEEE Transactions on Mobile Computing.

[9]  David W. Hosmer,et al.  Goodness-of-fit tests for logistic regression models when data are collected using a complex sampling design , 2007, Comput. Stat. Data Anal..

[10]  Y. Koucheryavy,et al.  The internet of Bio-Nano things , 2015, IEEE Communications Magazine.

[11]  S. H. Darwish,et al.  Micro-Doppler detection and target identification using Artificial Neural Network , 2012, 2012 IEEE Aerospace Conference.

[12]  J. Kokorian,et al.  An optical in-plane displacement measurement technique with sub-nanometer accuracy based on curve-fitting , 2014, 2014 IEEE 27th International Conference on Micro Electro Mechanical Systems (MEMS).

[13]  H. Noji,et al.  Changes in cytosolic ATP levels and intracellular morphology during bacteria-induced hypersensitive cell death as revealed by real-time fluorescence microscopy imaging. , 2012, Plant & cell physiology.

[14]  P. Rich,et al.  The mitochondrial respiratory chain. , 2010, Essays in biochemistry.

[15]  J E Wilson,et al.  Chelation of divalent cations by ATP, studied by titration calorimetry. , 1991, Analytical biochemistry.

[16]  Xin Cheng,et al.  Application of the generalized regression neural network in short-term load forecasting , 2011, 2011 IEEE 3rd International Conference on Communication Software and Networks.