Login Register Cart 0
Generic placeholder image

Current Chinese Science

Editor-in-Chief

ISSN (Print): 2210-2981
ISSN (Online): 2210-2914

Back
Journal Home About Journal Editorial Board Current Issue Volumes/Issues
Subscribe
Research Article

Supervised Machine Learning Models and Protein-Protein Interaction Network Analysis of Gene Expression Profiles Induced by Omega-3 Polyunsaturated Fatty Acids

Author(s): Sergey Shityakov*, Jane Pei-Chen Chang, Ching-Fang Sun, David Ta-Wei Guu, Thomas Dandekar and Kuan-Pin Su

Volume 2, Issue 2, 2022

Published on: 14 March, 2022

Page: [118 - 128] Pages: 11

DOI: 10.2174/2210298102666220112114505

Price: $65

Abstract

Background: Omega-3 polyunsaturated fatty acids (PUFAs), such as eicosapentaenoic (EPA) and docosahexaenoic (DHA) acids, have beneficial effects on human health, but their effect on gene expression in elderly individuals (age ≥ 65) is largely unknown. In order to examine this, the gene expression profiles were analyzed in the healthy subjects (n = 96) at baseline and after 26 weeks of supplementation with EPA+DHA to determine up-regulated and down-regulated differentially expressed genes (DEGs) triggered by PUFAs. The Protein-Protein Interaction (PPI) networks were constructed by mapping these DEGs to a human interactome and linking them to the specific pathways.

Objective: This study aimed to implement supervised machine learning models and proteinprotein interaction network analysis of gene expression profiles induced by PUFAs.

Methods: The transcriptional profile of GSE12375 was obtained from the Gene Expression Omnibus database, which is based on the Affymetrix NuGO array. The probe cell intensity data were converted into the gene expression values, and the background correction was performed by the multi-array average algorithm. The LIMMA (Linear Models for Microarray Data) algorithm was implemented to identify relevant DEGs at baseline and after 26 weeks of supplementation with a p-value < 0.05. The DAVID web server was used to identify and construct the enriched KEGG (Kyoto Encyclopedia of Genes and Genomes) pathways. Finally, the construction of Machine Learning (ML) models, including logistic regression, naïve Bayes, and deep neural networks, were implemented for the analyzed DEGs associated with the specific pathways.

Results: The results revealed that up-regulated DEGs were associated with neurotrophin/MAPK signaling, whereas the down-regulated DEGs were linked to cancer, acute myeloid leukemia, and long-term depression pathways. Additionally, ML approaches were able to cluster the EPA/DHAtreated and control groups by the logistic regression performing the best.

Conclusion: Overall, this study highlights the pivotal changes in DEGs induced by PUFAs and provides the rationale for the implementation of ML algorithms as predictive models for this type of biomedical data.

Keywords: Supervised machine learning, gene expression, polyunsaturated fatty acids, protein-protein interaction networks, clustering, Omega-3.

« Previous Next »
Graphical Abstract

[1]
Abete, P.; Testa, G.; Galizia, G.; Della-Morte, D.; Cacciatore, F.; Rengo, F. PUFA for human health: diet or supplementation? Curr. Pharm. Des., 2009, 15(36), 4186-4190.
[http://dx.doi.org/10.2174/138161209789909665] [PMID: 20041820]
[2]
Yang, B.; Ren, X-L.; Li, Z-H.; Shi, M-Q.; Ding, F.; Su, K-P.; Guo, X.J.; Li, D. Lowering effects of fish oil supplementation on proinflammatory markers in hypertension: results from a randomized controlled trial. Food Funct., 2020, 11(2), 1779-1789.
[http://dx.doi.org/10.1039/C9FO03085A] [PMID: 32044905]
[3]
Guu, T-W.; Mischoulon, D.; Sarris, J.; Hibbeln, J.; McNamara, R.K.; Hamazaki, K.; Freeman, M.P.; Maes, M.; Matsuoka, Y.J.; Belmaker, R.H.; Jacka, F.; Pariante, C.; Berk, M.; Marx, W.; Su, K.P. International society for nutritional psychiatry research practice guidelines for omega-3 fatty acids in the treatment of major depressive disorder. Psychother. Psychosom., 2019, 88(5), 263-273.
[http://dx.doi.org/10.1159/000502652] [PMID: 31480057]
[4]
Brown, I.; Lee, J.; Sneddon, A.A.; Cascio, M.G.; Pertwee, R.G.; Wahle, K.W.J.; Rotondo, D.; Heys, S.D. Anticancer effects of n-3 EPA and DHA and their endocannabinoid derivatives on breast cancer cell growth and invasion. Prostaglandins Leukot. Essent. Fatty Acids, 2020, 156, 102024.
[http://dx.doi.org/10.1016/j.plefa.2019.102024] [PMID: 31679810]
[5]
Bouwens, M.; van de Rest, O.; Dellschaft, N.; Bromhaar, M.G.; de Groot, L.C.; Geleijnse, J.M.; Müller, M.; Afman, L.A. Fish-oil supplementation induces antiinflammatory gene expression profiles in human blood mononuclear cells. Am. J. Clin. Nutr., 2009, 90(2), 415-424.
[http://dx.doi.org/10.3945/ajcn.2009.27680] [PMID: 19515734]
[6]
Maktoobian Baharanchi, E.; Moradi Sarabi, M.; Naghibalhossaini, F. Effects of dietary polyunsaturated fatty acids on DNA methylation and the expression of DNMT3b and PPARα genes in rats. Avicenna J. Med. Biotechnol., 2018, 10(4), 214-219.
[PMID: 30555653]
[7]
Piles, M.; Fernandez-Lozano, C.; Velasco-Galilea, M.; González-Rodríguez, O.; Sánchez, J.P.; Torrallardona, D.; Ballester, M.; Quintanilla, R. Machine learning applied to transcriptomic data to identify genes associated with feed efficiency in pigs. Genet. Sel. Evol., 2019, 51(1), 10.
[http://dx.doi.org/10.1186/s12711-019-0453-y] [PMID: 30866799]
[8]
Amminger, G.P.; Mechelli, A.; Rice, S.; Kim, S.W.; Klier, C.M.; McNamara, R.K.; Berk, M.; McGorry, P.D.; Schäfer, M.R. Predictors of treatment response in young people at ultra-high risk for psychosis who received long-chain omega-3 fatty acids. Transl. Psychiatry, 2015, 5, e495.
[http://dx.doi.org/10.1038/tp.2014.134] [PMID: 25585167]
[9]
Karunathilaka, S.R.; Yakes, B.J.; Choi, S.H.; Brückner, L.; Mossoba, M.M. Comparison of the performance of partial least squares and support vector regressions for predicting fatty acids/fatty acid classes in marine oil dietary supplements using vibrational spectroscopic data. J. Food Prot., 2020, 83(5), 881-889.
[http://dx.doi.org/10.4315/JFP-19-563] [PMID: 32028530]
[10]
Fernández-Navarro, T.; Díaz, I.; Gutiérrez-Díaz, I.; Rodríguez-Carrio, J.; Suárez, A.; de Los Reyes-Gavilán, C.G.; Gueimonde, M.; Salazar, N.; González, S. Exploring the interactions between serum free fatty acids and fecal microbiota in obesity through a machine learning algorithm. Food Res. Int., 2019, 121, 533-541.
[http://dx.doi.org/10.1016/j.foodres.2018.12.009] [PMID: 31108778]
[11]
Tsunoda, T.; Koh, Y.; Koizumi, F.; Tsukiyama, S.; Ueda, H.; Taguchi, F.; Yamaue, H.; Saijo, N.; Nishio, K. Differential gene expression profiles and identification of the genes relevant to clinicopathologic factors in colorectal cancer selected by cDNA array method in combination with principal component analysis. Int. J. Oncol., 2003, 23(1), 49-59.
[http://dx.doi.org/10.3892/ijo.23.1.49] [PMID: 12792775]
[12]
Dennis, G., Jr; Sherman, B.T.; Hosack, D.A.; Yang, J.; Gao, W.; Lane, H.C.; Lempicki, R.A. DAVID: Database for annotation, visualization, and integrated discovery. Genome Biol., 2003, 4(5), 3.
[http://dx.doi.org/10.1186/gb-2003-4-5-p3] [PMID: 12734009]
[13]
Rampasek, L.; Goldenberg, A. TensorFlow: Biology’s gateway to deep learning? Cell Syst., 2016, 2(1), 12-14.
[http://dx.doi.org/10.1016/j.cels.2016.01.009] [PMID: 27136685]
[14]
Shityakov, S.; Dandekar, T.; Förster, C. Gene expression profiles and protein-protein interaction network analysis in AIDS patients with HIV-associated encephalitis and dementia. HIV AIDS (Auckl.), 2015, 7, 265-276.
[http://dx.doi.org/10.2147/HIV.S88438] [PMID: 26604827]
[15]
Lenz, M.; Müller, F-J.; Zenke, M.; Schuppert, A. Principal components analysis and the reported low intrinsic dimensionality of gene expression microarray data. Sci. Rep., 2016, 6, 25696.
[http://dx.doi.org/10.1038/srep25696] [PMID: 27254731]
[16]
Huang, W.; Sherman, B.T.; Lempicki, R.A. Systematic and integrative analysis of large gene lists using DAVID bioinformatics resources. Nat. Protoc., 2009, 4(1), 44-57.
[http://dx.doi.org/10.1038/nprot.2008.211] [PMID: 19131956]
[17]
Hii, C.S.; Ferrante, A.; Edwards, Y.S.; Huang, Z.H.; Hartfield, P.J.; Rathjen, D.A.; Poulos, A.; Murray, A.W. Activation of mitogen-activated protein kinase by arachidonic acid in rat liver epithelial WB cells by a protein kinase C-dependent mechanism. J. Biol. Chem., 1995, 270(9), 4201-4204.
[http://dx.doi.org/10.1074/jbc.270.9.4201] [PMID: 7876176]
[18]
Gu, Z.; Shan, K.; Chen, H.; Chen, Y.Q. n-3 polyunsaturated fatty acids and their role in cancer chemoprevention. Curr. Pharmacol. Rep., 2015, 1(5), 283-294.
[http://dx.doi.org/10.1007/s40495-015-0043-9] [PMID: 26457243]
[19]
Vaughan, V.C.; Hassing, M.R.; Lewandowski, P.A. Marine polyunsaturated fatty acids and cancer therapy. Br. J. Cancer, 2013, 108(3), 486-492.
[http://dx.doi.org/10.1038/bjc.2012.586] [PMID: 23299528]
[20]
Mita, T.; Mayanagi, T.; Ichijo, H.; Fukumoto, K.; Otsuka, K.; Sakai, A.; Sobue, K. Docosahexaenoic acid promotes axon outgrowth by translational regulation of tau and collapsin response mediator protein 2 expression. J. Biol. Chem., 2016, 291(10), 4955-4965.
[http://dx.doi.org/10.1074/jbc.M115.693499] [PMID: 26763232]
[21]
Stillwell, W.; Shaikh, S.R.; Zerouga, M.; Siddiqui, R.; Wassall, S.R. Docosahexaenoic acid affects cell signaling by altering lipid rafts. Reprod. Nutr. Dev., 2005, 45(5), 559-579.
[http://dx.doi.org/10.1051/rnd:2005046] [PMID: 16188208]
[22]
Guirland, C.; Zheng, J.Q. Membrane lipid rafts and their role in axon guidance. Adv. Exp. Med. Biol., 2007, 621, 144-155.
[http://dx.doi.org/10.1007/978-0-387-76715-4_11] [PMID: 18269217]
[23]
Su, K.P.; Shen, W.W.; Huang, S.Y. Effects of polyunsaturated fatty acids on psychiatric disorders. Am. J. Clin. Nutr., 2000, 72(5), 1241.
[http://dx.doi.org/10.1093/ajcn/72.5.1241] [PMID: 11063464]
[24]
Akintoye, E.; Sethi, P.; Harris, W.S.; Thompson, P.A.; Marchioli, R.; Tavazzi, L.; Latini, R.; Pretorius, M.; Brown, N.J.; Libby, P.; Mozaffarian, D. Fish oil and perioperative bleeding. Circ. Cardiovasc. Qual. Outcomes, 2018, 11(11), e004584.
[http://dx.doi.org/10.1161/CIRCOUTCOMES.118.004584] [PMID: 30571332]
[25]
Bedi, H.S.; Tewarson, V.; Negi, K. Bleeding risk of dietary supplements: A hidden nightmare for cardiac surgeons. Indian Heart J., 2016, 68(Suppl. 2), S249-S250.
[http://dx.doi.org/10.1016/j.ihj.2016.03.028] [PMID: 27751305]
[26]
Brown, T.J.; Brainard, J.; Song, F.; Wang, X.; Abdelhamid, A.; Hooper, L. Omega-3, omega-6, and total dietary polyunsaturated fat for prevention and treatment of type 2 diabetes mellitus: systematic review and meta-analysis of randomised controlled trials. BMJ, 2019, 366, l4697.
[http://dx.doi.org/10.1136/bmj.l4697] [PMID: 31434641]
[27]
Calder, P.C. Omega-3 polyunsaturated fatty acids and inflammatory processes: nutrition or pharmacology? Br. J. Clin. Pharmacol., 2013, 75(3), 645-662.
[http://dx.doi.org/10.1111/j.1365-2125.2012.04374.x] [PMID: 22765297]
[28]
Balogun, K.A.; Cheema, S.K. The expression of neurotrophins is differentially regulated by ω-3 polyunsaturated fatty acids at weaning and postweaning in C57BL/6 mice cerebral cortex. Neurochem. Int., 2014, 66, 33-42.
[http://dx.doi.org/10.1016/j.neuint.2014.01.007] [PMID: 24462582]
[29]
Yamagami, T.; Porada, C.D.; Pardini, R.S.; Zanjani, E.D.; Almeida-Porada, G. Docosahexaenoic acid induces dose dependent cell death in an early undifferentiated subtype of acute myeloid leukemia cell line. Cancer Biol. Ther., 2009, 8(4), 331-337.
[http://dx.doi.org/10.4161/cbt.8.4.7334] [PMID: 19197149]
[30]
Chiu, L.C.M.; Wong, E.Y.L.; Ooi, V.E.C. Docosahexaenoic acid modulates different genes in cell cycle and apoptosis to control growth of human leukemia HL-60 cells. Int. J. Oncol., 2004, 25(3), 737-744.
[http://dx.doi.org/10.3892/ijo.25.3.737] [PMID: 15289877]
[31]
Parodi, S.; Muselli, M.; Fontana, V.; Bonassi, S. ROC curves are a suitable and flexible tool for the analysis of gene expression profiles. Cytogenet. Genome Res., 2003, 101(1), 90-91.
[http://dx.doi.org/10.1159/000074404] [PMID: 14571143]
[32]
Shityakov, S.; Förster, C. In silico predictive model to determine vector-mediated transport properties for the blood-brain barrier choline transporter. Adv. Appl. Bioinform. Chem., 2014, 7, 23-36.
[http://dx.doi.org/10.2147/AABC.S63749] [PMID: 25214795]
[33]
Shityakov, S.; Förster, C. In silico structure-based screening of versatile P-glycoprotein inhibitors using polynomial empirical scoring functions. Adv. Appl. Bioinform. Chem., 2014, 7, 1-9.
[http://dx.doi.org/10.2147/AABC.S56046] [PMID: 24711707]
[34]
Bujang, M.A.; Adnan, T.H. Requirements for minimum sample size for sensitivity and specificity analysis. J. Clin. Diagn. Res., 2016, 10(10), YE01-YE06.
[http://dx.doi.org/10.7860/JCDR/2016/18129.8744] [PMID: 27891446]
[35]
Kim, Y.; Kim, H-G.; Li, Z.; Choi, H-J. Avoiding overfitting in deep neural networks for clinical opinions generation from general blood test results. Stud. Health Technol. Inform., 2017, 245, 1274.
[PMID: 29295359]
[36]
Hu, Y.; Luo, S.; Han, L.; Pan, L.; Zhang, T. Deep supervised learning with mixture of neural networks. Artif. Intell. Med., 2020, 102, 101764.
[http://dx.doi.org/10.1016/j.artmed.2019.101764] [PMID: 31980101]
[37]
Ahmed, M.S.; Shahjaman, M.; Rana, M.M.; Mollah, M.N.H. Robustification of naïve bayes classifier and its application for microarray gene expression data analysis. BioMed Res. Int., 2017, 2017, 3020627.
[http://dx.doi.org/10.1155/2017/3020627] [PMID: 28848763]
[38]
Li, W.; Mo, W.; Zhang, X.; Squiers, J.J.; Lu, Y.; Sellke, E.W.; Fan, W.; DiMaio, J.M.; Thatcher, J.E. Outlier detection and removal improves accuracy of machine learning approach to multispectral burn diagnostic imaging. J. Biomed. Opt., 2015, 20(12), 121305.
[http://dx.doi.org/10.1117/1.JBO.20.12.121305] [PMID: 26305321]

Rights & Permissions Print Cite
Article Metrics
12
1
© 2024 Bentham Science Publishers | Privacy Policy