Support Vector Machines for Biomarkers Detection in in vitro and in vivo Experiments of Organochlorines Exposure
Abstract
Metabolomic studies generate large amounts of data, whose complexity increases if they are derived from in vivo experiments. As a result, analysis methods highly used in metabolomics, such as Partial Least Squares Discriminant Analysis (PLS-DA), can have particular difficulties with this type of data. However, there is evidence that indicates that Support Vector Machines (SVMs) can better deal with complex data. On the other hand, chronic exposure to organochlorines is a public health problem. It has been associated with diseases such as cancer. Therefore, its identification is relevant to reduce their impact on human health. This study explores the performance of SVMs in classifying metabolic profiles and identifying relevant metabolites in studies of exposure to organochlorines. For this purpose, two experiments were conducted: in the first one, organochlorine exposure was evaluated in HepG2 cells; and, in the second one, it was evaluated in serum samples of agricultural workers exposed to pesticides. The performance of SVMs was compared with that of PLS-DA. Four kernel functions were assessed in SVMs, and the accuracy of both methods was evaluated using a k-fold cross-validation test. In order to identify the most relevant metabolites, Recursive Feature Elimination (RFE) was used in SVMs and Variable Importance in Projection (VIP) in PLS-DA. The results show that SVMs exhibit a higher percentage of accuracy with fewer training samples and better performance in classifying the samples from the exposed agricultural workers. Finally, a workflow based on SVMs for the identification of biomarkers in samples with high biological complexity is proposed.
References
J. C. Lindon; J. K. Nicholson: E. Holmes, The Handbook of Metabonomics and Metabolomics. Elsevier, 2007.
E. C. Horning; M. G. Horning, “Human Metabolic Profiles Obtained by GC and GC/MS,” J. Chromatogr. Sci., vol. 9, no. 3, pp. 129–140, Mar. 1971. https://doi.org/10.1093/chromsci/9.3.129
S. Mahadevan; S. L. Shah; T. J. Marrie; C. M. Slupsky, “Analysis of Metabolomic Data Using Support Vector Machines,” Anal. Chem., vol. 80, no. 19, pp. 7562–7570, Sep. 2008. https://doi.org/10.1021/ac800954c
C. Cortes; V. Vapnik, “Support-vector networks,” Mach. Learn., vol. 20, no. 3, pp. 273–297, Sep. 1995. https://doi.org/10.1007/BF00994018
A. Alonso; S. Marsal; A. JuliÃ, “Analytical Methods in Untargeted Metabolomics: State of the Art in 2015,” Front. Bioeng. Biotechnol., vol. 3, p. 23, Mar. 2015. https://doi.org/10.3389/fbioe.2015.00023
J. Heinemann; A. Mazurie; M. Tokmina-Lukaszewska; G. J. Beilman; B. Bothner, “Application of support vector machines to metabolomics experiments with limited replicates,” Metabolomics, vol. 10, no. 6, pp. 1121–1128, Dec. 2014, https://doi.org/10.1007/s11306-014-0651-0
K. M. Mendez; S. N. Reinke; D. I. Broadhurst, “A comparative evaluation of the generalised predictive ability of eight machine learning algorithms across ten clinical metabolomics data sets for binary classification,” Metabolomics, vol. 15, no. 12, p. 150, Nov. 2019. https://doi.org/10.1007/s11306-019-1612-4
P. S. Gromski et al., “A tutorial review: Metabolomics and partial least squares-discriminant analysis – a marriage of convenience or a shotgun wedding,” Anal. Chim. Acta, vol. 879, pp. 10–23, Jun. 2015. https://doi.org/10.1016/j.aca.2015.02.012
I. Guyon; J. Weston; S. Barnhill; V. Vapnik, “Gene selection for cancer classification using support vector machines,” Mach. Learn., vol. 46, no. 1, pp. 389–422, Jan. 2002. https://doi.org/10.1023/A:1012487302797
W. Guan et al., “Ovarian cancer detection from metabolomic liquid chromatography/mass spectrometry data by support vector machines,” BMC Bioinformatics, vol. 10, no. 259, Aug. 2009. https://doi.org/10.1186/1471-2105-10-259
X. Lin et al., “A support vector machine-recursive feature elimination feature selection method based on artificial contrast variables and mutual information,” J. Chromatogr. B, vol. 910, pp. 149–155, Dec. 2012. https://doi.org/10.1016/j.jchromb.2012.05.020
M. Abdollahi; A. Ranjbar; S. Shadnia; S. Nikfar; A. Rezaiee, “Pesticides and oxidative stress: a review,” Med. Sci. Monit., vol. 10, no. 6, Jun. 2004.https://pubmed.ncbi.nlm.nih.gov/15173684/
V. Moses; J. V. Peter, “Acute intentional toxicity: endosulfan and other organochlorines,” Clin. Toxicol., vol. 48, no. 6, pp. 539–544, Jul. 2010. https://doi.org/10.3109/15563650.2010.494610
R. Jayaraj; P. Megha; P. Sreedev, “Organochlorine pesticides, their toxic effects on living organisms and their fate in the environment,” Interdiscip. Toxicol., vol. 9, no. 3–4, p. 90- 100, Dec. 2016. https://doi.org/10.1515/intox-2016-0012
M. Zuluaga; J. J. Melchor; F. A. Tabares-Villa; G. Taborda; J. C. Sepúlveda-Arias, “Metabolite Profiling to Monitor Organochlorine Pesticide Exposure in HepG2 Cell Culture,” Chromatographia, vol. 79, no. 17–18, pp. 1061–1068, Sep. 2016. https://doi.org/10.1007/s10337-016-3031-2
O. Fiehn; T. Kind, “Metabolite Profiling in Blood Plasma,” in Metabolomics, Springer, 2007, pp. 3–17. https://doi.org/10.1007/978-1-59745-244-1_1
O. Fiehn et al., “Quality control for plant metabolomics: reporting MSI-compliant studies,” Plant J., vol. 53, no. 4, pp. 691–704, Feb. 2008. https://doi.org/10.1111/j.1365-313X.2007.03387.x
J. Chong; D. S. Wishart; J. Xia, “Using MetaboAnalyst 4.0 for Comprehensive and Integrative Metabolomics Data Analysis,” Curr. Protoc. Bioinforma., vol. 68, no. 1, p. e86, Sep. 2019. https://doi.org/10.1002/cpbi.86
L. Eriksson, Introduction to multi-and megavariate data analysis using projection methods (PCA & PLS). Umetrics AB, 1999.
R. C. Team, “R: A language and environment for statistical computing,” 2013. https://www.yumpu.com/en/document/read/6853895/r-a-language-and-environment-for-statistical-computing
M. Campbell, “RStudio Projects,” in Learn RStudio IDE, Berkeley, CA: Apress, 2019, pp. 39–48. https://doi.org/10.1007/978-1-4842-4511-8_4
D. Meyer et al., “Package ‘e1071, Misc Functions of the Department of Statistics, Probability Theory Group (Formerly: E1071), TU Wien’”, versió 1.7-9, R J., 2019. http://sunsite2.icm.edu.pl/pub/unix/math/cran/web/packages/e1071/e1071.pdf
H. Zheng et al., “Predictive diagnosis of major depression using NMR-based metabolomics and least-squares support vector machine,” Clin. Chim. Acta, vol. 464, pp. 223–227, Jan. 2017. https://doi.org/10.1016/j.cca.2016.11.039
B. Feizizadeh; M. S. Roodposhti; T. Blaschke; J. Aryal, “Comparing GIS-based support vector machine kernel functions for landslide susceptibility mapping,” Arab. J. Geosci., vol. 10, no. 122, Mar. 2017. https://doi.org/10.1007/s12517-017-2918-z
M. A. Horaira; M. S. Ahmed; M. H. Kabir; M. N. H. Mollah; M. A. Rahman Shah, “Colon Cancer Prediction from Gene Expression Profiles Using Kernel Based Support Vector Machine,” in 2018 International Conference on Computer, Communication, Chemical, Material and Electronic Engineering (IC4ME2), Feb. 2018, pp. 1–4. https://ieeexplore.ieee.org/document/8465636
V. Wan; W. M. Campbell, “Support vector machines for speaker verification and identification,” in Neural Networks for Signal Processing X. Proceedings of the 2000 IEEE Signal Processing Society Workshop (Cat. No.00TH8501), vol. 2, pp. 775–784. https://doi.org/10.1109/NNSP.2000.890157
V. Hooshmand Moghaddam; J. Hamidzadeh, “New Hermite orthogonal polynomial kernel and combined kernels in Support Vector Machine classifier,” Pattern Recognit., vol. 60, pp. 921–935, Dec. 2016. https://doi.org/10.1016/j.patcog.2016.07.004
X. Huang; Q.-S. Xu; Y.-H. Yun; J.-H. Huang; Y.-Z. Liang, “Weighted variable kernel support vector machine classifier for metabolomics data analysis,” Chemom. Intell. Lab. Syst., vol. 146, pp. 365–370, Aug. 2015. https://doi.org/10.1016/j.chemolab.2015.06.009
D. A. López-Sarmiento; H. C. Manta-Caro; N. E. Vera-Parra, “Clasificador basado en una máquina de vectores de soporte de mínimos cuadrados frente a un clasificador por regresión logística ante el reconocimiento de dígitos numéricos,” TecnoLógicas, no. 31, pp. 37-51, Nov. 2011. https://doi.org/10.22430/22565337.99
L. A. Muñoz-Bedoya; L. E. Mendoza; H. J. Velandia-Villamizar, “Segmentación de Imágenes de Resonancia Magnética IRM utilizando LS-SVM y Análisis Multiresolución Wavelet,” TecnoLógicas, pp. 681-693, Nov. 2013. https://doi.org/10.22430/22565337.381
M. Moon; K. Nakai, “Stable feature selection based on the ensemble L 1 -norm support vector machine for biomarker discovery,” BMC Genomics, vol. 17, no. s13, Dec. 2016. https://doi.org/10.1186/s12864-016-3320-z
Downloads
Altmetric
