Pathway analysis using XGBoost classification in Biomedical Data

ABSTRACT

Given the fact that our biological existence is rooted in a complex system within our cells with thousands of interactions among genes and metabolites, research community in biological and medical fields have shifted their interest to network-based approaches. This complexity is imprinted in networks which encode the relationships among system's components. This evolution has also led to the generation a new research fields, the Network Medicine, a combination of Network Science and Systems Biology applied to human diseases. Meanwhile, cutting-edge approaches towards this direction are the subpathway-based methods, identifying "active subpathways" - in the form of local sub-structures within pathways - related with a case under study.

Based on this, we propose a classification scheme based on XGBoost, a recent tree-based classification algorithm, in order to detect the most discriminative pathways related with a disease. Subsequently, we extract subpathways and rank them with regard to their ability to correctly classify samples from different experimental conditions. Our method is demonstrated on an aging gene expression dataset providing evidences that XGBoost outperforms other well-known classification methods in biological data, while results provided by our method include several established as well as recently reported longevity-associated pathways.

References

1. C. Mitsopoulos, A. C. Schierz, P. Workman, and B. Al-Lazikani. 2015. Distinctive behaviors of druggable proteins in cellular networks. PLoS computational biology, 11(12), e1004597.
2. M. A. García-Campos, J. Espinal-Enríquez, and E. Hernández-Lemus. 2015. Pathway analysis: state of the art. Frontiers in physiology, 6, 383.
3. P. Khatri, M. Sirota, and A. J. Butte. 2012. Ten years of pathway analysis: current approaches and outstanding challenges. PLoS computational biology, 8(2), e1002375.
4. C. Mitrea, Z. Taghavi, B. Bokanizad, S. Hanoudi, R. Tagett, M. Donato, C. Voichrţa, and S. Drăghici. 2013. Methods and approaches in the topology-based analysis of biological pathways. Frontiers in physiology, 4, 278.
5. A. L. Barabási. 2016. Network science. Cambridge university press.
6. J. Loscalzo (Ed.). 2017. Network Medicine. Harvard University Press.
7. A. L. Barabasi, N. Gulbahce, and J. Loscalzo. 2011. Network medicine: a network-based approach to human disease. Nature reviews genetics, 12(1), 56.
8. M. Caldera, P. Buphamalai, F. Müller, and J. Menche. 2017. Interactome-Based Approaches to Human Disease. Current Opinion in Systems Biology.
9. S. Chen, C. Li, B. Wu, C. Zhang, C. Liu, and E. Li. 2014. Identification of differentially expressed genes and their subpathways in recurrent versus primary bone giant cell tumors, Int. J. Oncol., 45, 3, 1133--1142.
10. S. Nam, H. R. Chang, K. T. Kim, M. C. Kook, D., Hong, C., Kwon, ... and T. Park. 2014. PATHOME: an algorithm for accurately detecting differentially expressed subpathways. Oncogene, 33(41), 4941.
11. A. G. Vrahatis, K. Dimitrakopoulou, P. Balomenos, A. K. Tsakalidis, and A. Bezerianos. 2015. CHRONOS: A time-varying method for microRNA-mediated subpathway enrichment analysis, Bioinformatics, 32, 6, 884--892.
12. L. Feng, Y. Xu, Y. Zhang, Z. Sun, J. Han, ... and X. Li. 2015. Subpathway-GMir: Identifying miRNA-mediated metabolic subpathways by integrating condition-specific genes, microRNAs, and pathway topologies, Oncotarget, 6, 36.
13. A. G. Vrahatis, P. Balomenos, A. K. Tsakalidis, and A. Bezerianos. 2016. DEsubs: an R package for flexible identification of differentially expressed subpathways using RNA-seq experiments, Bioinformatics, 32, 24, 3844--3846.
14. C. Feng, J. Zhang, X. Li, B. Ai, J. Han, Q. Wang, T. Wei, Y. Xu, M. Li, S. Li, C. Song, and C. Li. 2016. Subpathway-CorSP: Identification of metabolic subpathways via integrating expression correlations and topological features between metabolites and genes of interest within pathways, Sci. Rep., 6.
15. A. G. Vrahatis, K. Dimitrakopoulou, A. Kanavos, S. Sioutas, and A. Tsakalidis. 2017. Detecting Perturbed Subpathways towards Mouse Lung Regeneration Following H1N1 Influenza Infection. Computation, 5(2), 20.
16. Y. Xu, F. Li, T. Wu, Y. Xu, H. Yang, ... and X. Li. 2017. LncSubpathway: a novel approach for identifying dysfunctional subpathways associated with risk lncRNAs by integrating lncRNA and mRNA expression profiles and pathway topologies, Oncotarget, 8, 9, 15453--15469, 2017.
17. Y. Zhu, X. Shen, and W. Pan. 2009. Network-based support vector machine for classification of microarray samples. BMC bioinformatics, 10(1), S21.
18. H. Pang, A. Lin, M. Holford, B. E. Enerson, B. Lu, M. P. Lawton, ... and H. Zhao. 2006. Pathway analysis using random forests classification and regression. Bioinformatics, 22(16), 2028--2036.
19. G. N. Dimitrakopoulos, P. Balomenos, A. G. Vrahatis, K. Sgarbas, and A. Bezerianos. 2016. Identifying disease network perturbations through regression on gene expression and pathway topology analysis," in 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2016, 5969--5972.
20. T. Chen, and C. Guestrin. 2016. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, 785--794, ACM.
21. Y. Li, K. Kang, J. M. Krahn, N. Croutwater, K. Lee, D. M. Umbach, and L. Li. 2017. A comprehensive genomic pan-cancer classification using The Cancer Genome Atlas gene expression data. BMC genomics, 18(1), 508.
22. S. A. Babayan, W. Liu, G. Hamilton, E. Kilbride, E. Rynkiewicz, M. Clerc, and A. B. Pedersen. 2018. The immune and non-immune Pathways That Drive chronic gastrointestinal helminth Burdens in the Wild. Frontiers in Immunology, 9, 56.
23. E. M. Yasser. 2018. CCA based multi-view feature selection for multi-omics data integration. bioRxiv, 243733.
24. S. Melov M. A. Tarnopolsky K. Beckman, K. Felkey, and A. Hubbard. 2007. Resistance exercise reverses aging in human skeletal muscle. PLoS One, 2(5), e465.
25. M. Kanehisa, and S. Goto. 2000. KEGG: Kyoto Encyclopedia of Genes and Genomes. Nucleic Acids Research, 28(1), 27--30.
26. J. H. Friedman. 2001. Greedy function approximation: a gradient boosting machine. Annals of statistics, 1189--1232.
27. F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, ... and J. Vanderplas. 2011. Scikit-learn: Machine learning in Python. Journal of machine learning research, 12(Oct), 2825--2830.
28. D. W. Huang, B. T. Sherman, and R. A. Lempicki. 2008. Systematic and integrative analysis of large gene lists using DAVID bioinformatics resources. Nature protocols, 4(1), 44--57.
29. Y. L. Miao, K. Kikuchi, Q. Y. Sun, and H. Schatten. 2009. Oocyte aging: cellular and molecular changes, developmental potential and reversal possibility. Human reproduction update, 15(5), 573--585.
30. G. C. Kujoth, A. Hiona, T. D. Pugh, S. Someya, K. Panzer, ... and J. D. Morrow. 2005. Mitochondrial DNA mutations, oxidative stress, and apoptosis in mammalian aging. Science, 309(5733), 481--484.
31. R. V. Khapre, A. A. Kondratova, S. Patel, Y. Dubrovsky, M. Wrobel, M. P. Antoch, and R. V. Kondratov. 2014. BMAL1-dependent regulation of the mTOR signaling pathway delays aging. Aging (Albany NY), 6(1), 48.
32. K. Jia, D. Chen, and D. L. Riddle. 2004. The TOR pathway interacts with the insulin signaling pathway to regulate C. elegans larval development, metabolism and life span. Development, 131(16), 3897--3906.
33. M. Zerofsky, E. Harel, N. Silverman, and M. Tatar. 2005. Aging of the innate immune response in Drosophila melanogaster. Aging cell, 4(2), 103--108.
34. H. Bruunsgaard M. Pedersen, and B. K. Pedersen. 2001. Aging and proinflammatory cytokines. Current Opin. Hematol. 8, 131 -136.
35. T. Dechat, T. Shimi, S. A. Adam, A. E. Rusinol, D. A. Andres, ... and R. D. Goldman. 2007. Alterations in mitosis and cell cycle progression caused by a mutant lamin A known to accelerate human aging. Proceedings of the National Academy of Sciences, 104(12), 4955--4960.
36. O. M. Gutiérrez, M. Mannstadt, T. Isakova, J. A. Rauh-Hain, H. Tamez, ... and M. Wolf. 2008. Fibroblast growth factor 23 and mortality among patients undergoing hemodialysis. New England Journal of Medicine, 359(6), 584--592.
37. M. Villamiel, M. C. Polo, and M. V. Moreno-Arribas. 2008. Nitrogen compounds and polysaccharides changes during the biological ageing of sherry wines. LWT-Food Science and Technology, 41(10), 1842--1846.

Index Terms

• Applied computing

  • Life and medical sciences

    • Computational biology

    • Genetics

    • Systems biology

• Computing methodologies

  • Machine learning