Literature DB >> 25966007

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

L Mark Hall1, Dennis W Hill, Lochana C Menikarachchi, Ming-Hui Chen, Lowell H Hall, David F Grant.   

Abstract

BACKGROUND: Artificial Neural Networks (ANN) are extensively used to model 'omics' data. Different modeling methodologies and combinations of adjustable parameters influence model performance and complicate model optimization.
METHODOLOGY: We evaluated optimization of four ANN modeling parameters (learning rate annealing, stopping criteria, data split method, network architecture) using retention index (RI) data for 390 compounds. Models were assessed by independent validation (I-Val) using newly measured RI values for 1492 compounds.
CONCLUSION: The best model demonstrated an I-Val standard error of 55 RI units and was built using a Ward's clustering data split and a minimally nonlinear network architecture. Use of validation statistics for stopping and final model selection resulted in better independent validation performance than the use of test set statistics.

Entities:  

Mesh:

Year:  2015        PMID: 25966007      PMCID: PMC4462168          DOI: 10.4155/bio.15.1

Source DB:  PubMed          Journal:  Bioanalysis        ISSN: 1757-6180            Impact factor:   2.681


  22 in total

Review 1.  'Metabonomics': understanding the metabolic responses of living systems to pathophysiological stimuli via multivariate statistical analysis of biological NMR spectroscopic data.

Authors:  J K Nicholson; J C Lindon; E Holmes
Journal:  Xenobiotica       Date:  1999-11       Impact factor: 1.908

2.  Effective Backpropagation Training with Variable Stepsize.

Authors:  George S. Androulakis; Michael N. Vrahatis; George D. Magoulas
Journal:  Neural Netw       Date:  1997-01

3.  Rapid and noninvasive diagnosis of the presence and severity of coronary heart disease using 1H-NMR-based metabonomics.

Authors:  Joanne T Brindle; Henrik Antti; Elaine Holmes; George Tranter; Jeremy K Nicholson; Hugh W L Bethell; Sarah Clarke; Peter M Schofield; Elaine McKilligin; David E Mosedale; David J Grainger
Journal:  Nat Med       Date:  2002-11-25       Impact factor: 53.440

4.  Use of computer-assisted methods for the modeling of the retention time of a variety of volatile organic compounds: a PCA-MLR-ANN approach.

Authors:  M Jalali-Heravi; A Kyani
Journal:  J Chem Inf Comput Sci       Date:  2004 Jul-Aug

5.  Quantitative structure-property relationship study of retention time of some pesticides in gas chromatography.

Authors:  M R Hadjmohammadi; M H Fatemi; K Kamel
Journal:  J Chromatogr Sci       Date:  2007-08       Impact factor: 1.618

6.  Prediction of HPLC retention index using artificial neural networks and IGroup E-state indices.

Authors:  Daniel R Albaugh; L Mark Hall; Dennis W Hill; Tzipporah M Kertesz; Marc Parham; Lowell H Hall; David F Grant
Journal:  J Chem Inf Model       Date:  2009-04       Impact factor: 4.956

7.  Prediction of Kovats retention indices of some aliphatic aldehydes and ketones on some stationary phases at different temperatures using artificial neural network.

Authors:  Elaheh Konoz; Mohammad H Fatemi; Razieh Faraji
Journal:  J Chromatogr Sci       Date:  2008 May-Jun       Impact factor: 1.618

8.  Development of Ecom₅₀ and retention index models for nontargeted metabolomics: identification of 1,3-dicyclohexylurea in human serum by HPLC/mass spectrometry.

Authors:  L Mark Hall; Lowell H Hall; Tzipporah M Kertesz; Dennis W Hill; Thomas R Sharp; Edward Z Oblak; Ying W Dong; David S Wishart; Ming-Hui Chen; David F Grant
Journal:  J Chem Inf Model       Date:  2012-04-27       Impact factor: 4.956

9.  MolFind: a software package enabling HPLC/MS-based identification of unknown chemical structures.

Authors:  Lochana C Menikarachchi; Shannon Cawley; Dennis W Hill; L Mark Hall; Lowell Hall; Steven Lai; Janine Wilder; David F Grant
Journal:  Anal Chem       Date:  2012-10-23       Impact factor: 6.986

10.  A QSPR study on the GC retention times of a series of fatty, dicarboxylic and amino acids by MLR and ANN.

Authors:  Ahmad Rouhollahi; Hooshang Shafieyan; Jahan Bakhsh Ghasemi
Journal:  Ann Chim       Date:  2007-09
View more
  4 in total

Review 1.  Challenges in Identifying the Dark Molecules of Life.

Authors:  María Eugenia Monge; James N Dodds; Erin S Baker; Arthur S Edison; Facundo M Fernández
Journal:  Annu Rev Anal Chem (Palo Alto Calif)       Date:  2019-03-18       Impact factor: 10.745

Review 2.  The application of artificial neural networks in metabolomics: a historical perspective.

Authors:  Kevin M Mendez; David I Broadhurst; Stacey N Reinke
Journal:  Metabolomics       Date:  2019-10-18       Impact factor: 4.290

Review 3.  Machine Learning Methods for Analysis of Metabolic Data and Metabolic Pathway Modeling.

Authors:  Miroslava Cuperlovic-Culf
Journal:  Metabolites       Date:  2018-01-11

4.  Using LC Retention Times in Organic Structure Determination: Drug Metabolite Identification.

Authors:  William L Fitch; Cyrus Khojasteh; Ignacio Aliagas; Kevin Johnson
Journal:  Drug Metab Lett       Date:  2018
  4 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.