Accurate and reliable modelling of protein–protein interaction networks for complex diseases such as colorectal cancer can help better understand mechanism of diseases and potentially discover new drugs. Different machine learning methods such as empirical mode decomposition combined with least square support vector machine, and discrete Fourier transform have been widely utilised as a classifier and for automatic discovery of biomarkers for the diagnosis of the disease. The existing methods are, however, less efficient as they tend to ignore interaction with the classifier. In this study, the authors propose a two-stage optimisation approach to effectively select biomarkers and discover interactions among them. At the first stage, particle swarm optimisation (PSO) and differential evolution (DE) are used to optimise parameters of support vector machine recursive feature elimination algorithm, and dynamic Bayesian network is then used to predict temporal relationship between biomarkers across two time points. Results show that 18 and 25 biomarkers selected by PSO and DE-based approach, respectively, yields the same accuracy of 97.3% and F1-score of 97.7 and 97.6%, respectively. The stratified analysis reveals that Alpha-2-HS-glycoprotein was a dominant hub gene with multiple interactions to other genes including Fibrinogen alpha chain, which is also a potential biomarker for colorectal cancer.

References

1. 1)
  - 53. Colucci, R., Blandizzi, C., Tanini, M., et al: ‘Gastrin promotes human colon cancer cell growth via CCK-2 receptor-mediated cyclooxygenase-2 induction and prostaglandin E2 production’, Br. J. Pharmacol., 2005, 144, (3), pp. 338–348 (doi: 10.1038/sj.bjp.0706053).
2. 2)
  - 29. Korb, K., Nicholson, A.: ‘Bayesian artificial intelligence’ (CRC press, 2011).
3. 3)
  - 19. Engelbrecht, A.: ‘Computational intelligence: an introduction’ (John Willey & Sons, 2007).
4. 4)
  - 37. R Core Team ‘R: A language and environment for statistical computing’, R Foundation for Statistical Computing, Vienna, Austria, 2014. Available at http://www.R-project.org/.
5. 5)
  - 15. Rogalsky, T., Derksen, R., Kocabiyik, S.: ‘Differential evolution in aerodynamic optimization’, Can. Aeronaut. Space J., 2000, 46, (4), pp. 183–190.
6. 6)
  - 48. Cao, W.H., Liu, H.M., Liu, X., et al: ‘Relaxin enhances in-vitro invasiveness of breast cancer cell lines by upregulation of S100A4/MMPs signaling’, Eur. Rev. Med. Pharmacol. Sci., 2013, 17, (5), pp. 609–617.
7. 7)
  - 30. Murphy, K.: ‘Machine learning: a probabilistic perspective’ (MIT press, 2012).
8. 8)
  - 54. Malouf, G., Sylvie, J., Valérie, P., et al: ‘Transcriptional profiling of pure fibrolamellar hepatocellular carcinoma reveals an endocrine signature’, Hepatology, 2014, 59, (6), pp. 2228–2237 (doi: 10.1002/hep.27018).
9. 9)
  - 12. Chang, C., Chih-Jen, L.: ‘LIBSVM: a library for support vector machines’, ACM Trans. Intell. Syst. Technol., 2011, 2, (3), pp. 1–27 (doi: 10.1145/1961189.1961199).
10. 10)
  - 25. Ooi, C.H., Patrick, T.: ‘Genetic algorithms applied to multi-class prediction for the analysis of gene expression data’, Bioinformatics, 2003, 19, (1), pp. 37–44 (doi: 10.1093/bioinformatics/19.1.37).
11. 11)
  - 17. Qin, A., Huang, V., Suganthan, P.: ‘Differential evolution algorithm with strategy adaptation for global numerical optimization’, IEEE Trans. Evol. Comput., 2009, 13, (2), pp. 398–417 (doi: 10.1109/TEVC.2008.927706).
12. 12)
  - 59. Paquin, M.C., Leblanc, C., Lemieux, E., et al: ‘Functional impact of colorectal cancer-associated mutations in the transcription factor E2F4’, Int. J. Oncol., 2013, 43, (6), pp. 2015–2022.
13. 13)
  - 38. Ling, C.X., Jin, H., Harry, Z.: ‘AUC: a better measure than accuracy in comparing learning algorithms’, in Yang, X., Brahim, C. (Eds.): ‘Advances in artificial intelligence’ (Springer, 2003), vol. 2671, pp. 329–341.
14. 14)
  - 45. Fernández-Grijalva, A., Aguilar-Lemarroy, A., Jave-Suarez, F., et al: ‘Alpha 2HS-glycoprotein, a tumor-associated antigen (TAA) detected in Mexican patients with early-stage breast cancer’, J. Proteomics, 2015, 112, pp. 301–312 (doi: 10.1016/j.jprot.2014.07.025).
15. 15)
  - 14. Storn, R., Price, K.: ‘Differential evolution – a simple and efficient heuristic for global optimization over continuous spaces’, J. Glob. Optim., 1997, 11, (4), pp. 341–359 (doi: 10.1023/A:1008202821328).
16. 16)
  - 26. Duan, K.B., Rajapakse, J.C., Wang, H., et al: ‘Multiple SVM-RFE for gene selection in cancer classification with expression data’, IEEE Trans. Nanobiosc., 2005, 4, (3), pp. 228–234 (doi: 10.1109/TNB.2005.853657).
17. 17)
  - 3. Rathore, S., Hussain, M., Ali, A., et al: ‘A recent survey on colon cancer detection techniques’, IEEE/ACM Trans. Comput. Biol. Bioinf., 2013, 10, (3), pp. 545–563 (doi: 10.1109/TCBB.2013.84).
18. 18)
  - 20. Saeys, Y., Inza, I., Larrañaga, P.: ‘A review of feature selection techniques in bioinformatics’, Bioinformatics, 2007, 23, pp. 2507–2517 (doi: 10.1093/bioinformatics/btm344).
19. 19)
  - 11. Cortes, C., Vladimir, V.: ‘Support-vector networks’, Mach. Learn., 1995, 20, (3), pp. 273–297.
20. 20)
  - 51. Poon, S.L., Lau, M., Hammond, G.L., et al: ‘Gonadotropin-releasing hormone-II increases membrane type I metalloproteinase production via beta-catenin signaling in ovarian cancer cells’, Endocrinology, 2011, 152, (3), pp. 764–772 (doi: 10.1210/en.2010-0942).
21. 21)
  - 39. Lebre, S.: original version 1.0 by Sophie Lebre and contribution of Julien Chiquet to version 2.0 (2013). G1DBN: a package performing dynamic Bayesian network inference. R package version 3.1.1. Available at http://CRAN.R-project.org/package=G1DBN.
22. 22)
  - 24. Jirapech-Umpai, T., Stuart, A.: ‘Feature selection and classification for microarray data analysis: evolutionary methods for identifying predictive genes’, BMC Bioinform., 2005, 6, (1), p. 148 (doi: 10.1186/1471-2105-6-148).
23. 23)
  - 16. Storn, R.: ‘On the usage of differential evolution for function optimization’. Proc. of Int. Conf. on North American Fuzzy Information Processing, Berkeley, CA, 1996, pp. 519–523.
24. 24)
  - 34. Tibshirani, R.: ‘Regression shrinkage and selection via the lasso’, J. R. Stat. Soc. Ser. B, Methodol., 1996, 58, (1), pp. 267–288.
25. 25)
  - 6. Rathore, S., Iftikhar, M., Hussain, M.: ‘A novel approach for automatic gene selection and classification of gene based colon cancer datasets’. Proc. of Int. Conf. on Emerging Technologies (ICET), Islamabad, December 2014, pp. 42–47.
26. 26)
  - 21. Lee, K., Kim, J.: ‘Multiobjective particle swarm optimization with preference-based sort and its application to path following footstep optimization for humanoid robots’, IEEE Trans. Evol. Comput., 2013, 17, (6), pp. 755–766 (doi: 10.1109/TEVC.2013.2240688).
27. 27)
  - 49. Pazaitou-Panayiotou, K., Chemonidou, C., Poupi, A., et al: ‘Gonadotropin-releasing hormone neuropeptides and receptor in human breast cancer: correlation to poor prognosis parameters’, Peptides, 2013, 42, pp. 15–24 (doi: 10.1016/j.peptides.2012.12.016).
28. 28)
  - 13. Guyon, I., Weston, J., Barnhill, S., et al: ‘Gene selection for cancer classification using support vector machines’, Mach. Learn., 2002, 46, (1–3), pp. 389–422 (doi: 10.1023/A:1012487302797).
29. 29)
  - 1. ‘The National Health Service (NHS) UK, Department of Health, Bowel Cancer’. Available at http://www.nhs.uk/conditions/Cancer-of-the-colon-rectum-or-bowel/Pages/Introduction.aspx, accessed February 2015.
30. 30)
  - 23. Liang, J.J., Qin, A.K., Suganthan, P.N., et al: ‘Comprehensive learning particle swarm optimizer for global optimization of multimodal functions’, IEEE Trans. Evol. Comput., 2006, 10, (3), pp. 281–295 (doi: 10.1109/TEVC.2005.857610).
31. 31)
  - 33. Nagarajan, R., Scutari, M., Lèbre, S.: ‘Bayesian networks in R –with applications in systems biology’ (Springer, 2013).
32. 32)
  - 32. Lèbre, S.: ‘Inferring dynamic genetic networks with low order independencies’, Stat. Appl. Genetics Mol. Biol., 2009, 8, (1), pp. 1–38 (doi: 10.2202/1544-6115.1294).
33. 33)
  - 52. Rachel, S., Adam, S., David, R.: ‘Pro-opiomelanocortin is a novel biomarker for small cell lung cancer’, Endocrine Abstr., 2010, 21, p. 221.
34. 34)
  - 23. Smoot, M.E., Ono, K., Ruscheinski, J., Wang, P.L., Ideker, T.: ‘Cytoscape 2.8: new features for data integration and network visualization’, Bioinformatics, 2011, 27, (3), pp. 431–432 (doi: 10.1093/bioinformatics/btq675).
35. 35)
  - 7. Alexandrov, T., Decker, J., Mertens, B., et al: ‘Biomarker discovery in MALDI-TOF serum protein profiles using discrete wavelet transformation’, Bioinformatics, 2009, 25, (5), pp. 643–649 (doi: 10.1093/bioinformatics/btn662).
36. 36)
  - 47. Wrangle, J., Machida, E., Danilova, L., et al: ‘Functional identification of cancer-specific methylation of CDO1, HOXA9, and TAC1 for the diagnosis of lung cancer’, Clin. Cancer Res., 2014, 20, (7), pp. 1856–1864 (doi: 10.1158/1078-0432.CCR-13-2109).
37. 37)
  - 58. Ji, D., Lu, Z.T., Li, Y.Q., et al: ‘MACC1 expression correlates with PFKFB2 and survival in hepatocellular carcinoma’, Asian Pac. J. Cancer Prev., 2014, 15, (2), pp. 999–1003 (doi: 10.7314/APJCP.2014.15.2.999).
38. 38)
  - 35. Vinh, N.X., Madhu, C., Ross, C., et al: ‘GlobalMIT: learning globally optimal dynamic Bayesian network with the mutual information test criterion’, Bioinformatics, 2011, 27, (19), pp. 2765–2766 (doi: 10.1093/bioinformatics/btr457).
39. 39)
  - 36. Swiss Institute of Bioinformatics SIB, Tagident Bioinformatics Resource Tool’. Available at http://web.expasy.org/tagident/, accessed June 2015.
40. 40)
  - 20. Zhu, Z., Zhou, J., Ji, Z., et al: ‘DNA sequence compression using adaptive particle swarm optimization-based memetic algorithm’, IEEE Trans. Evol. Comput., 2011, 15, (5), pp. 643–658 (doi: 10.1109/TEVC.2011.2160399).
41. 41)
  - 42. Lebre, S.: ‘Stochastic process analysis for genomics and dynamic Bayesian networks inference’. PhD thesis, Université d'Evry-Val d'Essonne, 2007.
42. 42)
  - 5. Hong, Y., Zeng-li, L., Wei, H.: ‘Research for the colon cancer based on the EMD and LS-SVM’. Proc. of Int. Conf. on Intelligent Computation Technology and Automation (ICICTA), Shenzhen, Guangdong, March 2011, pp. 888–891.
43. 43)
  - 41. Akutekwe, A., Seker, H.: ‘A hybrid dynamic Bayesian network approach for modelling temporal associations of gene expressions for hypertension diagnosis’. Proc. of Int. Conf. on Engineering in Medicine and Biology Society (EMBC), Chicago, USA, August 2014, pp. 804–807.
44. 44)
  - 27. Zhou, X., Tuck, D.P.: ‘MSVM-RFE: extensions of SVM-RFE for multiclass gene selection on DNA microarray data’, Bioinformatics, 2007, 23, (9), pp. 1106–1114 (doi: 10.1093/bioinformatics/btm036).
45. 45)
  - 18. Kennedy, J., Eberhart, R.: ‘Particle swarm optimization’. Proc. of Int. Conf. on IEEE Neural Networks, Piscataway, NJ, 1995, pp. 1942–1948.
46. 46)
  - 22. Shi, Y., Eberhart, R.: ‘A modified particle swarm optimizer’. Proc. of Int. Conf. on IEEE World Congress on Computational Intelligence, Anchorage, AK, May 1998, pp. 69–73.
47. 47)
  - 57. Muendlein, A., Hubalek, M., Geller-Rhomberg, S., et al: ‘Significant survival impact of MACC1 polymorphisms in HER2 positive breast cancer patients’, Eur. J. Cancer, 2014, 50, (12), pp. 2134–2141 (doi: 10.1016/j.ejca.2014.05.007).
48. 48)
  - 50. Poon, S.L., Klausen, C., Hammond, G.L., et al: ‘37-kDa laminin receptor precursor mediates GnRH-II-induced MMP-2 expression and invasiveness in ovarian cancer cells’, Mol. Endocrinol., 2010, 25, (2), pp. 327–338 (doi: 10.1210/me.2010-0334).
49. 49)
  - 55. Yamagishi, H., Deirdre, H., Fitzgerald, T.S., et al: ‘Saliva affects the antifungal activity of exogenously added histatin 3 towards Candida albicans’, FEMS Microbiol. Lett., 2005, 244, (1), pp. 207–212 (doi: 10.1016/j.femsle.2005.01.045).
50. 50)
  - 44. Fan, N., Rui, K., Ge, X., et al: ‘Identification alpha-2-HS-glycoprotein precursor and tubulin beta chain as serology diagnosis biomarker of colorectal cancer’, Diagn. Pathol., 2014, 9, pp. 1–53 (doi: 10.1186/1746-1596-9-53).
51. 51)
  - 10. de Noo, M.E., Bart, M., Aliye, O., et al: ‘Detection of colorectal cancer using MALDI-TOF serum protein profiling’, Eur. J. Cancer, 2006, 42, (8), pp. 1068–1076 (doi: 10.1016/j.ejca.2005.12.023).
52. 52)
  - 46. Son, H.J., Park, J.W., Chang, H.J., et al: ‘Preoperative plasma hyperfibrinogenemia is predictive of poor prognosis in patients with nonmetastatic colon cancer’, Ann. Surgical Oncol., 2013, 20, (9), pp. 2908–2913 (doi: 10.1245/s10434-013-2968-8).
53. 53)
  - 31. Liu, Z., Zhang, W., Horimoto, K., et al: ‘Gaussian graphical model for identifying significantly responsive regulatory networks from time course high-throughput data’, Syst. Biol., 2013, 7, (5), pp. 143–152.
54. 54)
  - 4. Thomas, G., Dixon, F., Smeeton, N., et al: ‘Observer variation in the histological grading of rectal carcinoma’, J. Clin. Pathol., 1983, 36, (4), pp. 385–391 (doi: 10.1136/jcp.36.4.385).
55. 55)
  - 2. ‘American Cancer Society, What is Colorectal Cancer’. Available at http://www.cancer.org/cancer/colonandrectumcancer/detailedguide/colorectal-cancer-key-statistics, accessed February 2015.
56. 56)
  - 9. Akutekwe, A., Seker, H.: ‘Particle swarm optimization-based bio-network discovery method for the diagnosis of colorectal cancer’. Proc. of Int. Conf. on IEEE Bioinformatics and Biomedicine (BIBM), Belfast, November 2014, pp. 8–13.
57. 57)
  - 56. The UniProt Consortium: ‘UniProt: a hub for protein information’, Nucleic Acids Research, 2015, gku989.
58. 58)
  - 40. Akutekwe, A., Seker, H.: ‘Two-stage computational bio-network discovery approach for metabolites: ovarian cancer as a case study’. Proc. of Int. Conf. on Biomedical and Health Informatics (BHI), June 2014, pp. 97–100.
59. 59)
  - 28. Russell, S., Norvig, P.: ‘Artificial intelligence: a modern approach’ (Prentice Hall, 2010).

In silico discovery of significant pathways in colorectal cancer metastasis using a two-stage optimisation approach

References

Related content