Abstract
In this research work, we introduce several novel methods to identify the defective pathways in highly uncertain phenotype prediction problems. More specifically, we applied these methodologies for phenotype prediction associated with drug repositioning for rare diseases such as the Inclusion Body Myositis and obtained a better understanding of the disease mechanism. The novelty of our research is based on the fact that the classifiers utilized to build the genetic signatures were based on completely different approaches, namely; gene Fisher ratios, generation of random genetic networks or genetic network likelihoods to sample and relate the altered genes to possible drugs via the connectivity maps. This scheme provides a more effective drug design/repositioning since it helps to understand the disease mechanisms and to establish an optimum mechanism of action of the designed drugs. By comparing the different classifiers, we conclude that the Fisher’s ratio, Holdout and Random Forest samplers are the most effective, since they provide similar insights into the genetic mechanisms of the disease and bear low computational costs. Furthermore, our work supports the concept of Biological Invariance, assuming that the results of the analysis of the altered pathways should be independent of the sampling method utilized for the assessment of the inference. However, the effectiveness of the candidate drugs and the gene targets predicted by our approach should be pre-clinically studied and clinically tested.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Dalakas, M.C.: Polymyositis, dermatomyositis, and inclusion-body myositis. New Engl. J. Med. 325(21), 1487–1498 (1991)
Griggs, R.C., et al.: Inclusion body myositis and myopathies. Ann. Neurol. Official J. Am. Neurol. Assoc. Child Neurol. Soc. 38(5), 705–713 (1995)
Ghannam, K., et al.: Upregulation of immunoproteasome subunits in myositis indicates active inflammation with involvement of antigen presenting cells, CD8 T-cells and IFNγ. PLoS One 9(8), e104048 (2014)
Rose, M.R.: 188th ENMC international workshop: inclusion body myositis, 2–4 December 2011, Naarden the Netherlands. Neuromusc. Disord. 23(12), 1044–1055 (2013)
Machado, P., et al.: Lb0002 safety and tolerability of arimoclomol in patients with sporadic inclusion body myositis: a randomized, double-blind, placebo controlled, phase IIa proof-of-concept trial. Ann. Rheum. Dis. 72(Suppl 3), A164–A164 (2013)
Gualano, B., et al.: Resistance training with vascular occlusion in inclusion body myositis: a case study. Med. Sci. Sports Exerc. 42(2), 250–254 (2010)
Prevel, N., Allenbach, Y., Klatzmann, D., Salomon, B., Benveniste, O.: Beneficial role of rapamycin in experimental autoimmune myositis. PLoS One 8(11), e74450 (2013)
Mendell, J.R., et al.: Follistatin gene therapy for sporadic inclusion body myositis improves functional outcomes. Mol. Ther. 25(4), 870–879 (2017)
DiMasi, J.A., Grabowski, H.G., Hansen, R.W.: Innovation in the pharmaceutical industry: new estimates of R&D costs. J. Health Econ. 47, 20–33 (2016)
Cook, D., et al.: Lessons learned from the fate of AstraZeneca’s drug pipeline: a five-dimensional framework. Nature Rev. Drug Discov. 13(6), 419 (2014)
Scannell, J.W., Blanckley, A., Boldon, H., Warrington, B.: Diagnosing the decline in pharmaceutical R&D efficiency. Nature Rev. Drug Discov. 11(3), 191 (2012)
Álvarez-Machancoses, Ó., Fernández-Martínez, J.L.: Using artificial intelligence methods to speed up drug discovery. Expert Opin. Drug Discov. 14(8), 769–777 (2019)
de Andrés-Galiana, E.J., Fernández-Martínez, J.L., Sonis, S.T.: Design of biomedical robots for phenotype prediction problems. J. Comput. Biol. 23(8), 678–692 (2016)
Cernea, A., et al.: Sampling defective pathways in phenotype prediction problems via the Fisher’s ratio sampler. In: Rojas, I., Ortuño, F. (eds.) IWBBIO 2018. LNCS, vol. 10814, pp. 15–23. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-78759-6_2
Fernández-Martínez, J.L., Fernández-Muñoz, Z., Tompkins, M.J.: On the topography of the cost functional in linear and nonlinear inverse problems. Geophysics 77(1), W1–W15 (2012)
Fernández-Martínez, J.L., Fernández-Muñoz, Z., Pallero, J.L.G., Pedruelo-González, L.M.: From Bayes to Tarantola: new insights to understand uncertainty in inverse problems. J. Appl. Geophys. 98, 62–72 (2013)
de Andrés-Galiana, E.J., Fernández-Martínez, J.L., Sonis, S.T.: Sensitivity analysis of gene ranking methods in phenotype prediction. J. Biomed. Inform. 64, 255–264 (2016)
Fernández-Martínez, J.L., et al.: Sampling defective pathways in phenotype prediction problems via the holdout sampler. In: Rojas, I., Ortuño, F. (eds.) IWBBIO 2018. LNCS, vol. 10814, pp. 24–32. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-78759-6_3
Cernea, A., et al.: Comparison of different sampling algorithms for phenotype prediction. In: Rojas, I., Ortuño, F. (eds.) IWBBIO 2018. LNCS, vol. 10814, pp. 33–45. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-78759-6_4
Saligan, L.N., Fernández-Martínez, J.L., de Andrés-Galiana, E.J., Sonis, S.: Supervised classification by filter methods and recursive feature elimination predicts risk of radiotherapy-related fatigue in patients with prostate cancer. Cancer Inform. 13, CIN-S19745 (2014)
Altman, N.S.: An introduction to kernel and nearest-neighbor nonparametric regression. Am. Stat. 46(3), 175–185 (1992)
Huang, G.-B., Zhu, Q.-Y., Siew, C.-K.: Extreme learning machine: theory and applications. Neurocomputing 70(1–3), 489–501 (2006)
Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)
Lamb, J.: The connectivity map: a new tool for biomedical research. Nat. Rev. Cancer 7(1), 54 (2007)
Greenberg, S.A.: Molecular profiles of inflammatory myopathies. Neurology 59(8), 1170–1182 (2002)
Greenberg, S.A.: Proposed immunologic models of the inflammatory myopathies and potential therapeutic implications. Neurology 69(21), 2008–2019 (2007)
Pang, H., et al.: Pathway analysis using random forests classification and regression. Bioinformatics 22(16), 2028–2036 (2006)
Fernández-Martínez, J.L., Álvarez, Ó., de Andrés-Galiana, E.J., de la Viña, J.F.S., Huergo, L.: Robust sampling of altered pathways for drug repositioning reveals promising novel therapeutics for inclusion body myositis. J Rare Dis. Res. Treat 4(2), 7–15 (2019)
Kürthy, M., et al.: Effect of BRX-220 against peripheral neuropathy and insulin resistance in diabetic rat models. Ann. New York Acad. Sci. 967(1), 482–489 (2002)
McBride, W.G.: Thalidomide and congenital abnormalities. Lancet 278(7216), 1358 (1961). https://doi.org/10.1016/s0140-6736(61)90927-8
Sereda, D., Werth, V.P.: Improvement in dermatomyositis rash associated with the use of antiestrogen medication. Arch. Dermatol. 142(1), 70–72 (2006)
Acknowledgments
We acknowledge financial support from NSF grant DBI 1661391, and NIH grant R01 GM127701.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Álvarez-Machancoses, Ó., deAndrés-Galiana, E., Fernández-Martínez, J.L., Kloczkowski, A. (2020). The Utilization of Different Classifiers to Perform Drug Repositioning in Inclusion Body Myositis Supports the Concept of Biological Invariance. In: Rutkowski, L., Scherer, R., Korytkowski, M., Pedrycz, W., Tadeusiewicz, R., Zurada, J.M. (eds) Artificial Intelligence and Soft Computing. ICAISC 2020. Lecture Notes in Computer Science(), vol 12415. Springer, Cham. https://doi.org/10.1007/978-3-030-61401-0_55
Download citation
DOI: https://doi.org/10.1007/978-3-030-61401-0_55
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-61400-3
Online ISBN: 978-3-030-61401-0
eBook Packages: Computer ScienceComputer Science (R0)