Machine learning approach to single nucleotide polymorphism-based asthma prediction


Autoři: Joverlyn Gaudillo aff001;  Jae Joseph Russell Rodriguez aff002;  Allen Nazareno aff001;  Lei Rigi Baltazar aff001;  Julianne Vilela aff003;  Rommel Bulalacao aff004;  Mario Domingo aff004;  Jason Albia aff001
Působiště autorů: Institute of Mathematical Sciences and Physics, University of the Philippines Los Baños, Philippines aff001;  Genetics and Molecular Biology Division, Institute of Biological Sciences, University of the Philippines Los Baños, Philippines aff002;  Philippine Genome Center Program for Agriculture, Office of the Vice Chancellor for Research and Extension, University of the Philippines Los Baños, Philippines aff003;  Domingo Artificial Intelligence Research Center, Los Baños, Philippines aff004;  Computational Interdisciplinary Research Laboratories (CINTERLabs), University of the Philippines Los Baños, Philippines aff005
Vyšlo v časopise: PLoS ONE 14(12)
Kategorie: Research Article
doi: 10.1371/journal.pone.0225574

Souhrn

Machine learning (ML) is poised as a transformational approach uniquely positioned to discover the hidden biological interactions for better prediction and diagnosis of complex diseases. In this work, we integrated ML-based models for feature selection and classification to quantify the risk of individual susceptibility to asthma using single nucleotide polymorphism (SNP). Random forest (RF) and recursive feature elimination (RFE) algorithm were implemented to identify the SNPs with high implication to asthma. K-nearest neighbor (kNN) and support vector machine (SVM) algorithms were trained to classify the identified SNPs whether associated with non-asthmatic or asthmatic samples. Feature selection step showed that RF outperformed RFE and the feature importance score derived from RF was consistently high for a subset of SNPs, indicating the robustness of RF in selecting relevant features associated with asthma. Model comparison showed that the integration of RF-SVM obtained the highest model performance with an accuracy, precision, and sensitivity of 62.5%, 65.3%, and 69%, respectively, when compared to the baseline, RF-kNN, and an external MeanDiff-kNN models. Furthermore, results show that the occurrence of asthma can be predicted with an Area under the Curve (AUC) of 0.62 and 0.64 for RF-SVM and RF-kNN models, respectively. This study demonstrates the integration of ML models to augment traditional methods in predicting genetic predisposition to multifactorial diseases such as asthma.

Klíčová slova:

Asthma – Genetics of disease – Genome-wide association studies – Machine learning – Machine learning algorithms – Molecular genetics – Support vector machines


Zdroje

1. Hancock DB, Romieu I, Shi M, Sienra-Monge JJ, Wu H, Chiu GY, et al. Genome-wide association study implicates chromosome 9q21.31 as a susceptibility locus for asthma in Mexican children. PLoS Genet. 2009; 5 (8): e1000623. doi: 10.1371/journal.pgen.1000623 19714205

2. Himes BE, Hunninghake GM, Baurley JW, Rafaels NM, Sleiman P, Strachan DP, et al. Genome-wide association analysis identifies PDE4D as an asthma-susceptibility gene Genet. 2009; 84(5): 581–593.

3. Moffatt MF, Kabesch M, Liang L, Dixon AL, Strachan D, Heath S, Depner M, et al. Genetic variants regulating ORMDL3 expression contribute to the risk of childhood asthma. Nature. 2007; 448(7152): 470–473. doi: 10.1038/nature06014 17611496

4. Li X, Howard TD, Zheng SL, Haselkorn T, Peters SP, Meyers DA, et al. Genome-wide association study of asthma identifies RAD50-IL13 and HLA-DR/DQ regions. J Allergy Clin Immunol. 2010; 125 (2): 328–335.e311. doi: 10.1016/j.jaci.2009.11.018 20159242

5. Sleiman PM, Flory J, Imielinski M, Bradfield JP, Annaiah K, Willis-Owen SA, et al. Variants of DENND1B associated with asthma in children. N Engl J Med. 2010; 362 (1): 36–44. doi: 10.1056/NEJMoa0901867 20032318

6. Duffy DL, Martin NG, Battistutta D, Hopper JL, Mathews JD. Genetics of asthma and hay fever in Australian twins. Am Rev Respir Dis 1990; 142:1351–1358. doi: 10.1164/ajrccm/142.6_Pt_1.1351 2252253

7. Nieminen MM, Kaprio J, Koskenvuo M. A population-based study of bronchialasthma in adult twin pairs. Chest 1991;100:70–75. doi: 10.1378/chest.100.1.70 2060393

8. König IR, Auerbach J, Gola D, Held E, Holzinger ER, Legault MA, et al. Machine learning and data mining in complex genomic data—a review on the lessons learned in Genetic Analysis Workshop 19. InBMC genetics 2016 Dec (Vol. 17, No. 2, p. S1). BioMed Central.

9. Savenije OE, John JM, Granell R, Kerkhof M, Dijk FN, de Jongste JC, et al. Association of IL33–IL-1 receptor—like 1 (IL1RL1) pathway polymorphisms with wheezing phenotypes and asthma in childhood. Journal of Allergy and Clinical Immunology. 2014 Jul 1;134(1):170–7. doi: 10.1016/j.jaci.2013.12.1080 24568840

10. Forno E, Celedón JC. Predicting asthma exacerbations in children. Current opinion in pulmonary medicine. 2012 Jan;18(1):63. doi: 10.1097/MCP.0b013e32834db288 22081091

11. Spycher BD, Henderson J, Granell R, Evans DM, Smith GD, Timpson NJ, et al. Genome-wide prediction of childhood asthma and related phenotypes in a longitudinal birth cohort. Journal of allergy and clinical immunology. 2012 Aug 1;130(2):503–9. doi: 10.1016/j.jaci.2012.06.002 22846752

12. Xu M, Tantisira KG, Wu A, Litonjua AA, Chu JH, Himes BE, et al. Genome Wide Association Study to predict severe asthma exacerbations in children using random forests classifiers. BMC medical genetics. 2011 Dec;12(1):90. doi: 10.1186/1471-2350-12-90 21718536

13. Mieth B, Kloft M, Rodríguez JA, Sonnenburg S, Vobruba R, Morcillo-Suárez C, et al. Combining multiple hypothesis testing with machine learning increases the statistical power of genome-wide association studies. Scientific reports. 2016 Nov 28;6:36671. doi: 10.1038/srep36671 27892471

14. Listgarten J, Damaraju S, Poulin B, Cook L, Dufour J, Driga A, et al. Predictive models for breast cancer susceptibility from multiple single nucleotide polymorphisms. Clinical cancer research. 2004 Apr 15;10(8):2725–37. doi: 10.1158/1078-0432.ccr-1115-03 15102677

15. Hajiloo M, Damavandi B, HooshSadat M, Sangi F, Mackey JR, Cass CE, et al. Breast cancer prediction using genome wide single nucleotide polymorphism data. BMC bioinformatics. 2013 Oct;14(13):S3. doi: 10.1186/1471-2105-14-S13-S3 24266904

16. Opensnp.org. (2018) openSNP. [online] Available at: https://opensnp.org/ [Accessed Mar. 2018].

17. Zeng P, Zhao Y, Qian C, Zhang L, Zhang R, Gou J, et al. Statistical analysis for genome-wide association study. Journal of biomedical research. 2015 Jul;29(4):285. doi: 10.7555/JBR.29.20140007 26243515

18. Graffelman J, Camarena JM. Graphical tests for Hardy-Weinberg equilibrium based on the ternary plot. Human heredity. 2008;65(2):77–84. doi: 10.1159/000108939 17898538

19. Saeys Y, Abeel T, Van de Peer Y. Robust feature selection using ensemble feature selection techniques. InJoint European Conference on Machine Learning and Knowledge Discovery in Databases 2008 Sep 15 (pp. 313–325). Springer, Berlin, Heidelberg.

20. Batnyam N, Gantulga A, Oh S. An efficient classification for single nucleotide polymorphism (SNP) dataset. InComputer and Information Science 2013 (pp. 171–185). Springer, Heidelberg.

21. Genecards.org. (2018). [online] Available at: http://www.genecards.org/ [Accessed Oct. 2018].

22. Snpedia.com. (2018). SNPedia. [online] Available at: https://www.snpedia.com/ [Accessed Oct. 2018].

23. Chen X, Ishwaran H. Random forests for genomic data analysis. Genomics. 2012 Jun 1;99(6):323–9. doi: 10.1016/j.ygeno.2012.04.003 22546560

24. Heidema AG, Boer JM, Nagelkerke N, Mariman EC, Feskens EJ. The challenge for genetic epidemiologists: how to analyze large numbers of SNPs in relation to complex diseases. BMC genetics. 2006 Dec;7(1):23. doi: 10.1186/1471-2156-7-23 16630340

25. Schwender H, Zucknick M, Ickstadt K, Bolt HM, GENICA network. A pilot study on the application of statistical classification procedures to molecular epidemiological data. Toxicology letters. 2004 Jun 15;151(1):291–9. doi: 10.1016/j.toxlet.2004.02.021 15177665

26. Lunetta K. L., Hayward L. B., Segal J., Van Eerdewegh P. Screening large-scale association study data: exploiting interactions using random forests. Toxicology letters. 2004 Jun 15;151(1):291–9.

27. Huang S, Cai N, Pacheco PP, Narandes S, Wang Y, Xu W. Applications of support vector machine (SVM) learning in cancer genomics. Cancer Genomics-Proteomics Cancer Genomics-Proteomics. 2018 Jan 1;15(1):41–51. doi: 10.21873/cgp.20063 29275361


Článek vyšel v časopise

PLOS One


2019 Číslo 12