Mbl-2 gene polymorphisms in pediatric Burkitt lymphoma: an approach based on machine learning techniques

Jonathan Wagner de Medeiros; Anthony José da Cunha Carneiro Lins; Oluwarotimi Williams Samuel; Elker Lene Santos de Lima; Maria Luiza Tabosa de Carvalho Galvão; Bárbara Oliveira Silva; Giwellington Silva Albuquerque; Luísa Priscilla Oliveira de Lima; Maria Tereza Cartaxo Muniz

doi:10.33448/rsd-v10i12.20561

Autores

Jonathan Wagner de Medeiros University of Pernambuco https://orcid.org/0000-0002-9679-273X
Anthony José da Cunha Carneiro Lins Catholic University of Pernambuco https://orcid.org/0000-0002-7153-841X
Oluwarotimi Williams Samuel Chinese Academy of Sciences https://orcid.org/0000-0003-1945-1402
Elker Lene Santos de Lima University of Pernambuco https://orcid.org/0000-0002-7171-7418
Maria Luiza Tabosa de Carvalho Galvão University of Pernambuco https://orcid.org/0000-0002-4593-7636
Bárbara Oliveira Silva University of Pernambuco https://orcid.org/0000-0003-4158-5650
Giwellington Silva Albuquerque University of Pernambuco https://orcid.org/0000-0001-6610-963X
Luísa Priscilla Oliveira de Lima University of Pernambuco https://orcid.org/0000-0002-4119-0491
Maria Tereza Cartaxo Muniz University of Pernambuco https://orcid.org/0000-0001-9498-5223

DOI:

https://doi.org/10.33448/rsd-v10i12.20561

Palavras-chave:

Aprendizagem de máquina; Linfoma de Burkitt; MBL-2; Polimorfismo.

Resumo

Introdução: O linfoma de Burkitt pertence ao grupo dos linfomas não Hodgkin. Embora curável em 80% dos estágios menos avançados, se apresenta em estágios avançados em cerca de 75% dos casos no Nordeste brasileiro, necessitando de cuidados urgentes e intensivos nas primeiras fases do tratamento. Objetivos: afim de se obter mais informações sobre esta patologia, este trabalho teve como principal objetivo verificar a participação do gene MBL-2 no desenvolvimento do linfoma de Burkitt. Métodos: Neste artigo, foram implementadas abordagens computacionais baseadas na técnica de Aprendizado de Máquina, para a qual utilizamos os algoritmos Random Forest e KMeans para classificar padrões de indivíduos diagnosticados com a doença e, com estes, diferenciá-los de indivíduos saudáveis. Foi avaliado um grupo de 56 pacientes com linfoma de Burkitt, de 0 a 18 anos e um grupo controle composto por 150 amostras de indivíduos, todas testadas para polimorfismos do exon 1 e das regiões -221 e -550 do gene MBL2. Resultados: A classificação não supervisionada identificou como dois o número de grupos que melhor representam os dados presentes em nosso banco de dados, alcançando 72,81% de acerto na separação de pacientes e controles. Em seguida, foi realizada a classificação supervisionada, onde o classificador obteve uma taxa de sucesso de 70,97%, sendo possível atingir 75% de acerto na melhor configuração do GridSearch ao realizar uma validação cruzada. Conclusão: Neste estudo não foi possível concluir sobre a participação dos polimorfismos avaliados no desenvolvimento do LB, entretanto as técnicas computacionais utilizadas se mostraram bastante promissoras para realização de estudos desta natureza.

Referências

Aydin, B., Akyuz, C., Kalkan, N., Kurucu, N., Varan, A., Yalcin, B., & Kutluk, T. (2019). FAB LMB 96 Regimen for Newly Diagnosed Burkitt Lymphoma in Children: Single-center Experience. Journal of Pediatric Hematology/Oncology, 41(1), e7–e11. https://doi.org/10.1097/MPH.0000000000001270

Bergstra, J., & Bengio, Y. (2012). Random search for hyper-parameter optimization. Journal of machine learning research, 13(2).

Bland, M. (2015). An introduction to medical statistics. Oxford University Press (UK).

Boldt, A. B. W., Culpi, L., Tsuneto, L. T., De Souza, I. R., Kun, J. F. J., & Petzl-Erler, M. L. (2006). Diversity of the MBL2 gene in various Brazilian populations and the case of selection at the mannose-binding lectin locus. Human immunology, 67(9), 722–734.

Bouwman, L. H., Roep, B. O., & Roos, A. (2006). Mannose-binding lectin: Clinical implications for infection, transplantation, and autoimmunity. Human immunology, 67(4–5), 247–256.

Da Cruz, H. L. A., Da Silva, R. C., Segat, L., de Mendonça Gomes, M. S. Z., Brandão, L. A. C., Guimarães, R. L., Santos, F. C.

F., de Lira, L. A. S., Montenegro, L. M. L., & Schindler, H. C. (2013). MBL2 gene polymorphisms and susceptibility to tuberculosis in a northeastern Brazilian population. Infection, Genetics and Evolution, 19, 323–329.

Davidson, I. (2002). Understanding K-means non-hierarchical clustering. SUNY Albany Technical Report, 2, 2–14.

Derinkuyu, B. E., Boyunağa, Ö., Öztunalı, Ç., Tekkeşin, F., Damar, Ç., Alımlı, A. G., & Okur, A. (2016). Imaging features of Burkitt lymphoma in pediatric patients. Diagnostic and Interventional Radiology, 22(1), 95.

Division of Cancer Epidemiology and Genetics—National Cancer Institute (nciglobal,ncienterprise). (2018a, janeiro 1). [CgvHomeLanding]. https://dceg.cancer.gov/

Dozzo, M., Carobolante, F., Donisi, P. M., Scattolin, A., Maino, E., Sancetta, R., Viero, P., & Bassan, R. (2017). Burkitt lymphoma in adolescents and young adults: Management challenges. Adolescent health, medicine and therapeutics, 8, 11.

Eisen, D. P., & Minchinton, R. M. (2003). Impact of mannose-binding lectin on susceptibility to infectious diseases. Clinical Infectious Diseases, 37(11), 1496–1505.

Freedman, A. S., Aster, J. C., & Rosmarin, A. G. (2018). Epidemiology, clinical manifestations, pathologic features, and diagnosis of Burkitt lymphoma.

Graudal, N. A., Madsen, H. O., Tarp, U., Svejgaard, A., Jurik, A. G., Graudal, H. K., & Garred, P. (2000). The association of variant mannose-binding lectin genotypes with radiographic outcome in rheumatoid arthritis. Arthritis & Rheumatism: Official Journal of the American College of Rheumatology, 43(3), 515–521.

Hansen, T. K., Tarnow, L., Thiel, S., Steffensen, R., Parving, H.-H., & Flyvbjerg, A. (2004). Association between mannose-binding lectin and vascular complications in type 1 diabetes. Scandinavian Journal of Immunology, 59(6), 613–613.

Harrison, E., Singh, A., Morris, J., Smith, N. L., Fraczek, M. G., Moore, C. B., & Denning, D. W. (2012). Mannose-binding lectin genotype and serum levels in patients with chronic and allergic pulmonary aspergillosis. International journal of immunogenetics, 39(3), 224–232.

Hassan, R., Klumb, C. E., Felisbino, F. E., Guiretti, D. M., White, L. R., Stefanoff, C. G., Barros, M. H. M., Seuánez, H. N., &

Zalcberg, I. R. (2008). Clinical and demographic characteristics of Epstein-Barr virus-associated childhood Burkitt’s lymphoma in Southeastern Brazil: Epidemiological insights from an intermediate risk region. haematologica, 93(5), 780–783.

Hastie, T., Tibshirani, R., & Friedman, J. (2009). The elements of statistical learning: Data mining, inference, and prediction. Springer Science & Business Media.

Hecht, J. L., & Aster, J. C. (2000). Molecular biology of Burkitt’s lymphoma. Journal of Clinical Oncology, 18(21), 3707–3721.

Hladnik, U., Braida, L., Boniotto, M., Pirulli, D., Gerin, F., Amoroso, A., & Crovella, S. (2002). Single-tube genotyping of MBL-2 polymorphisms using melting temperature analysis. Clinical and experimental medicine, 2(2), 105–108.

Hsu, J. L., & Glaser, S. L. (2000). Epstein–Barr virus-associated malignancies: Epidemiologic patterns and etiologic implications. Critical reviews in oncology/hematology, 34(1), 27–53.

Jain, A. K., & Dubes, R. C. (1988). Algorithms for Clustering Data. Prentice-Hall, Englewood Cliffs, New Jersey.

Kakushadze, Z., & Yu, W. (2017). *K-means and cluster models for cancer signatures. Biomolecular Detection and Quantification, 13, 7–31. https://doi.org/10.1016/j.bdq.2017.07.001

Khan, S. A., & Rana, Z. A. (2019). Evaluating performance of software defect prediction models using area under precision-Recall curve (AUC-PR). 2019 2nd International Conference on Advancements in Computational Sciences (ICACS), 1–6.

Kilpatrick, D. C. (2002a). Mannan-binding lectin and its role in innate immunity. Transfusion Medicine, 12(6), 335–352.

Kilpatrick, D. C. (2002b). Mannan-binding lectin: Clinical significance and applications. Biochimica et Biophysica Acta (BBA)-General Subjects, 1572(2–3), 401–413.

Kuhn, M., & Johnson, K. (2013). Applied predictive modeling (Vol. 26). Springer.

Lee, K., Jeong, H., Lee, S., & Jeong, W.-K. (2019). CPEM: Accurate cancer type classification based on somatic alterations using an ensemble of a random forest and a deep neural network. Scientific Reports, 9(1), 16927. https://doi.org/10.1038/s41598-019-53034-3

Li, W., Cerise, J. E., Yang, Y., & Han, H. (2017). Application of t-SNE to human genetic data. Journal of Bioinformatics and Computational Biology. https://doi.org/10.1142/S0219720017500172

Lins, A. J. C. C., Muniz, M. T. C., Garcia, A. N. M., Gomes, A. V., Cabral, R. M., & Bastos-Filho, C. J. A. (2017). Using artificial neural networks to select the parameters for the prognostic of mild cognitive impairment and dementia in elderly individuals. Computer Methods and Programs in Biomedicine, 152, 93–104. https://doi.org/10.1016/j.cmpb.2017.09.013

Madsen, H. O., Garred, P., Thiel, S., Kurtzhals, J. A., Lamm, L. U., Ryder, L. P., & Svejgaard, A. (1995). Interplay between promoter and structural gene variants control basal serum level of mannan-binding protein. The Journal of Immunology, 155(6), 3013–3020.

Martín-Mateos, M. A., & Piquer Gibert, M. (2016). Primary immunodeficiencies and B-cell lymphomas. Boletín Médico Del Hospital Infantil de México, 73(1), 18–25. https://doi.org/10.1016/j.bmhimx.2015.11.009

Mendonça, T. F., Oliveira, M., Vasconcelos, L. R. S., Pereira, L., Moura, P., Bezerra, M. A. C., Santos, M. N. N., Araújo, A. S., & Cavalcanti, M. S. M. (2010). Association of variant alleles of MBL2 gene with vasoocclusive crisis in children with sickle cell anemia. Blood Cells, Molecules, and Diseases, 44(4), 224–228.

Molyneux, E. M., Rochford, R., Griffin, B., Newton, R., Jackson, G., Menon, G., Harrison, C. J., Israels, T., & Bailey, S. (2012). Burkitt’s lymphoma. The Lancet, 379(9822), 1234–1244.

Moslem, M., Mahmoudabadi, A. Z., Fatahinia, M., & Kheradmand, A. (2015). Mannose-binding lectin serum levels in patients with candiduria. Jundishapur Journal of Microbiology, 8(12).

MWer, S., Dykes, D., & Polesky, H. (1988). A simple salting out procedure for extracting DNA from human nucleated cells. Nucleic acids res, 16(3), 1215.

Niitsuma, H., & Okada, T. (2007). Covariance and PCA for Categorical Variables. arXiv:0711.4452 [cs]. http://arxiv.org/abs/0711.4452

Petersen, S. V., Thiel, S., & Jensenius, J. C. (2001). The mannan-binding lectin pathway of complement activation: Biology and disease association. Molecular immunology, 38(2–3), 133–149.

Prati, R. C., Batista, G., & Monard, M. C. (2008). Curvas ROC para avaliação de classificadores. Revista IEEE América Latina, 6(2), 215–222.

QIAamp® DNA Mini and Blood Mini Handbook. Sample & Assay Technologies. ([s.d.]).

Refaeilzadeh, P., Tang, L., & Liu, H. (2009). Cross-validation. Encyclopedia of database systems, 5, 532–538.

Rodrigues-Fernandes, C. I., Pérez-de-Oliveira, M. E., Aristizabal Arboleda, L. P., Fonseca, F. P., Lopes, M. A., Vargas, P. A., & Santos-Silva, A. R. (2020). Clinicopathological analysis of oral Burkitt’s lymphoma in pediatric patients: A systematic review. International Journal of Pediatric Otorhinolaryngology, 134, 110033. https://doi.org/10.1016/j.ijporl.2020.110033

Rousseeuw, P. J. (1987). Silhouettes: A graphical aid to the interpretation and validation of cluster analysis. Journal of Computational and Applied Mathematics, 20, 53–65. https://doi.org/10.1016/0377-0427(87)90125-7

Rugonfalvi-Kiss, S., Endrész, V., Madsen, H. O., Burián, K., Duba, J., Prohászka, Z., Karádi, I., Romics, L., Gönczöl, É., &

Füst, G. (2002). Association of Chlamydia pneumoniae with coronary artery disease and its progression is dependent on the modifying effect of mannose-binding lectin. Circulation, 106(9), 1071–1076.

Salma, M. U. (2016). Pso based fast k-means algorithm for feature selection from high dimensional medical data set. 2016 10th International Conference on Intelligent Systems and Control (ISCO), 1–6.

Sathya, R., & Abraham, A. (2013). Comparison of supervised and unsupervised learning algorithms for pattern classification. International Journal of Advanced Research in Artificial Intelligence, 2(2), 34–38.

Sharma, P. (2019). The Most Comprehensive Guide to K-Means Clustering You’ll Ever Need. URL: https://www. analyticsvidhya. com/blog/2019/08/comprehensiveguide-k-means-clustering.

Silva, J. C. da. (2018, março 13). O Algoritmo da Floresta Aleatória. Medium. https://medium.com/machina-sapiens/o-algoritmo-da-floresta-aleat%C3%B3ria-3545f6babdf8

Silva, W. F. da, Garibaldi, P. M. M., Rosa, L. I. da, Bellesso, M., Clé, D. V., Delamain, M. T., Rego, E. M., Pereira, J., & Rocha, V. (2020). Outcomes of HIV-associated Burkitt Lymphoma in Brazil: High treatment toxicity and refractoriness rates – A multicenter cohort study. Leukemia Research, 89, 106287. https://doi.org/10.1016/j.leukres.2019.106287

Soltani, A., RahmatiRad, S., Pourpak, Z., Alizadeh, Z., Saghafi, S., HajiBeigi, B., Zeidi, M., & Farazmand, A. (2014). Polymorphisms and serum level of mannose-binding lectin: An Iranian survey. Iranian Journal of Allergy, Asthma and Immunology, 428–432.

Swerdlow, S. H., Campo, E., Pileri, S. A., Harris, N. L., Stein, H., Siebert, R., Advani, R., Ghielmini, M., Salles, G. A., Zelenetz, A. D., & Jaffe, E. S. (2016). The 2016 revision of the World Health Organization classification of lymphoid neoplasms. Blood, 127(20), 2375–2390. https://doi.org/10.1182/blood-2016-01-643569

Tsutsumi, A., Ikegami, H., Takahashi, R., Murata, H., Goto, D., Matsumoto, I., Fujisawa, T., & Sumida, T. (2003). Mannose binding lectin gene polymorphism in patients with type I diabetes. Human Immunology, 64(6), 621–624. https://doi.org/10.1016/S0198-8859(03)00054-5

Van Der Aalst, W. (2016). Data science in action. In Process mining (p. 3–23). Springer.

Van der Maaten, L., & Hinton, G. (2008). Visualizing data using t-SNE. Journal of machine learning research, 9(11).

Vardiman, J. W., Arber, D. A., Brunning, R. D., Larson, R. A., Matutes, E., Baumann, I., Swerdlow, S. H., Campo, E., Harris, N. L., & Jaffe, E. S. (2008). WHO classification of tumours of haematopoietic and lymphoid tissues. Lyon: International Agency for Research on Cancer.

Watanabe, S. (1985). Pattern recognition: Human and mechanical. John Wiley & Sons, Inc.

White, L. R. (2004). Análise de polimorfismo do promotor dos genes da interleuccina 10 e do fator de necrose tumoral como fator de suscetibilidade genética em linfomas de Burkitt de crianças. 126–126.

Xu, R., & Wunsch, D. C. (2005). Survey of clustering algorithms.

Polimorfismos do gene MBL-2 no linfoma de Burkitt pediátrico: uma abordagem baseada em técnicas de aprendizagem de máquina

Autores

DOI:

Palavras-chave:

Resumo

Referências

Downloads

Publicado

Como Citar

Edição

Seção

Licença

JOURNAL METRICS

Idioma

Enviar Submissão