Optimizing artificial neural network models for metabolomics and systems biology: An example using HPLC retention index data

Bioanalysis

Volumn 7, Issue 8, 2015, Pages 939-955

  Hall, L Mark ^a   Hill, Dennis W ^b   Menikarachchi, Lochana C ^b   Chen, Ming Hui ^b   Hall, Lowell H ^c   Grant, David F ^b  

^a Hall Associates Consulting ^*  (United States)

^b UNIVERSITY OF CONNECTICUT   (United States)

^c EASTERN NAZARENE COLLEGE   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ANALYTICAL ERROR; ANALYTICAL PARAMETERS; ARTICLE; ARTIFICIAL NEURAL NETWORK; CONTROLLED STUDY; DATA SPLIT METHOD; HIGH PERFORMANCE LIQUID CHROMATOGRAPHY; LEARNING RATE ANNEALING; MASS SPECTROMETRY; METABOLOMICS; NETWORK ARCHITECTURE; NONLINEAR SYSTEM; PROCESS OPTIMIZATION; RETENTION INDEX; STOPPING CRITERIA; SYSTEMS BIOLOGY; VALIDATION PROCESS; ARTIFICIAL INTELLIGENCE; CLUSTER ANALYSIS; FACTUAL DATABASE; PROCEDURES; STANDARDS; TANDEM MASS SPECTROMETRY;

ARTIFICIAL INTELLIGENCE; CHROMATOGRAPHY, HIGH PRESSURE LIQUID; CLUSTER ANALYSIS; DATABASES, FACTUAL; METABOLOMICS; NEURAL NETWORKS (COMPUTER); SYSTEMS BIOLOGY; TANDEM MASS SPECTROMETRY;

EID: 84929335742     PISSN: 17576180     EISSN: 17576199     Source Type: Journal    
DOI: 10.4155/bio.15.1     Document Type: Article

References (31)

1. Nicholson JK, Lindon JC, Holmes E. 'Metabonomics': understanding the metabolic responses of living systems to pathophysiological stimuli via multivariate statistical analysis of biological NMR spectroscopic data. Xenobiotica 29(11), 1181-1189 (1999).
2. Kertesz TM, Hill DW, Albaugh DR, Hall LH, Hall LM, Grant DF. Database searching for structural identification of metabolites in complex biofluids for mass spectrometry-based metabonomics. Bioanalysis 1(9), 1627-1643 (2009).
3. Hall LM, Hall LH, Kertesz TM et al. Development of Ecom50 and Retention Index Models for Nontargeted Metabolomics: Identification of 1,3-Dicyclohexylurea in Human Serum by HPLC/Mass Spectrometry. J. Chem. Inf. Model. 52, 1222-1237 (2012).
4. Hill DW, Kertesz TM, Fontaine D, Friedman R, Grant DF. Mass spectral metabonomics beyond elemental formula: Chemical database querying by matching experimental with computational fragmentation spectra. Anal. Chem. 80, 5574-5582 (2008).
5. Menikarachchi LC, Cawley S, Hill DW et al. MolFind: A Software Package Enabling HPLC/MS-Based Identification of Unknown Chemical Structures. Anal. Chem. 84, 9388-9394 (2012).
6. Hall LM, Hill DW, Hall LH, Kormos TM, Grant DF. Development of HPLC retention index QSAR models for non-targeted metabolomics. In: Advances in Chromatrography (Volume 51). Nelu Grinberg, Eli Grushka (Eds.), CRC Press, Boca Raton, USA, 241-279 (2013).
7. Albaugh DR, Hall LM, Hill DW et al. Prediction of HPLC Retention Index Using Artificial Neural Networks and IGroup E-State Indices. J. Chem. Inf. Model. 49, 788-799 (2009).
8. Hamdalla MA, Mandoiu II, Hill DW, Rajasekaran S, Grant DF. BioSM: A metabolomics tool for identifying endogenous mammalian biochemical structures in chemical structure space. J. Chem. Inf. Model. 53, 601-612 (2013).
9. Hill DW, Baveghems CL, Albaugh DR et al. Correlation of Ecom50 values between mass spectrometers: effect of collision cell radiofrequency voltage on calculated survival yield. Rapid Commun. Mass Spectrom. 26, 2303-2310 (2012).
10. Guo W, Lu Y, Zheng XM. The predicting study for chromatographic retention index of saturated alcohols by MLR and ANN. Talanta 51(3), 479-488 (2000).
11. Jalali-Heravi M, Kyani A. Use of computer-assisted methods for the modeling of the retention time of a variety of volatile organic compounds: a PCA-MLR-ANN approach. J. Chem. Inf. Comput. Sci. 44(4), 1328-1335 (2004).
12. Acevedo-Martinez JJ, Escalona-Arranz C, Villar-Rojas A et al. Quantitative study of the structure-retention index relationship in the imine family. J. Chromatogr. A. 1102, 238-244 (2006).
13. Hadjmohammadi MR, Fatemi MH, Kamel K. Quantitative structure-property relationship study of retention time of some pesticides in gas chromatography. J. Chromatogr. Sci. 45(7), 400-404. (2007)
14. Rouhollahi A, Shafieyan H, Ghasemi JB. A QSPR study on the GC retention times of a series of fatty, dicarboxylic and amino acids by MLR and ANN. Ann. Chim. 97(9) 925-933 (2007).
15. Konoz E, Fatemi MH, Faraji R. Prediction of Kovats retention indices of some aliphatic aldehydes and ketones on some stationary phases at different temperatures using artificial neural network. J. Chromatogr. Sci. 46(5), 406-412 (2008).
16. Quiming NS, Denola NL, Saito Y, Jinno K. Multiple linear regression and artificial neural network retention prediction models for ginsenosides on a polyamine-bonded stationary phase in hydrophilic interaction chromatography. J. Sep. Sci. 31(9), 1550-1563 (2008).
17. Hall LH, Kier LB, Hall LM. ADME-Tox approaches, electrotopological state indices to assess molecular absorption, distribution, metabolism, excretion, and toxicity. In: Comprehensive Medicinal Chemistry II (Volume 5). Taylor JB Triggle DJ (Ed.), Elsevier, Oxford, UK, 555-576 (2007).
18. Computer assisted drug design, topological quantitative structure-activity relationship applications: structure information in drug discovery. In: Comprehensive Medicinal Chemistry II. Taylor JB, Triggle DJ (Eds.), Elsevier, Oxford, UK, 555-576 (2007).
19. Hall LH, Kier LB. Molecular Structure Description: The Electrotopological State. Academic Press, San Diego, USA (1999).
20. Kier LB, Hall LH. The kappa indices for modeling molecular shape and flexibility. In: Topological Indices and Related Descriptors in QSAR and QSPR. Balaban AT, Devillers J (Eds.), Gordon and Breach, Reading, UK, 455-489 (1999).
21. Hall LH. Structure-Information, an approach to prediction of biological activities and properties. Chem. Biodiversity 1, 183-201 (2004).
22. Hall LH, Hall LM, Kier LB, Parham ME, Votano JR. Interpretation of the role of the Electrotopological State and Molecular Connectivity Indices in the prediction of physical properties and ADME-Tox behavior. Case study: Human Plasma Protein Binding. In: Proceedings of the Solvay Conference, Virtual ADMET Assessment in Target Selection and Maturation. Turski L, Testa B (Eds.), IOS Press, 67-100 (2006).
23. Smith GE, Ragsdale CT. A deterministic approach to small data set partitioning for neural networks. In: Advances in Business and Management Forecasting (Volume 7). Ronald KK, Lawrence KD (Eds.), Emerald Group Publishing Limited, 157-170 (2010).
24. Zupon J, Gasteiger J. Neural Networks for Chemists. VCH publishers, New York, USA (1993).
25. Rumelhart DE, Hinton GE, Williams RJ. Learning representations by back-propigating errors. In: Cognitive Modeling (Volume 8). Seifert CM, Polk TA (Eds.), MIT Press, Cambridge, USA, 213-220 (2002).
26. Wilson DR, Martinez TR. The general inefficiency of batch training for gradient descent learning. Neural Networks 16, 1429-1451 (2003).
27. Magoulas GD, Vrahatis MN, Androulakis GS. Improving the convergence of the backpropagation algorithm using learning rate adaptation methods. Neural Computation 11, 1769-1796 (1999).
28. Magoulas GD, Vrahatis MN, Androulakis GS. Effective back propagation with variable stepsize. Neural Networks. 10, 69-82 (1997).
29. Ward JH. Hierarchical grouping to optimize and objective function. Journal of the Americal Statistical Association. 58, 236-244 (1963).
30. Brindle JT, Antti H, Holmes E et al. Rapid and noninvasive diagnosis of the presence and severity of coronary heart disease using 1H-NMR-based metabolomics. Nat. Med. 8(12), 1439-1444 (2002).
31. Tsang TM, Huang JT, Holmes E, Bahn S. Metabolic profiling of plasma from discordant schizophrenia twins: correlation between lipid signals and global functioning in female schizophrenia patients. J. Proteome Res. 5(4), 756-760 (2006).