Show simple item record

dc.contributor.advisorOrjuela-Cañón, Alvaro David 
dc.creatorNavas Luquez, Mateo
dc.descriptionEl presente trabajo propone una comparación de modelos de aprendizaje automático para la detección de células cancerígenas a partir de los antígenos del complejo MHC I. Utilizando protocolos de extracción de características físico-químicas de las proteínas y un proceso comparativo de las medidas de desempeño en la fase de validación y prueba de los modelos. Con este procedimiento se pretende determinar cuál modelo de aprendizaje automático presenta el mejor desempeño en la predicción de antígenos cancerígenos, utilizando propiedades fisicoquímicas como marcadores de entrada.
dc.description.abstractThe present work proposes a comparison of machine learning models for the detection of cancer cells from the MHC I complex antigens. Using protocols for the extraction of physical-chemical characteristics of proteins and a comparative process of performance measurements in the model validation and testing phase. This procedure aims to determine the machine learning model presenting the best performance in the prediction of carcinogenic antigens, using physicochemical properties as input markers.
dc.rightsAtribución 2.5 Colombia
dc.sourceinstname:Universidad del Rosario
dc.sourceinstname:Universidad del Rosario
dc.subjectAprendizaje automático
dc.subject.ddcIncidencia & prevención de la enfermedad 
dc.titleComparación de modelos de aprendizaje automático para la predicción de células cancerígenas a partir del complejo MHC I
dc.publisherUniversidad del Rosario
dc.creator.degreeIngeniero Biomédico
dc.publisher.programIngeniería Biomédica
dc.publisher.departmentEscuela de Medicina y Ciencias de la Salud
dc.title.alternativePredicción de células cancerígenas
dc.subject.keywordMachine Learning
dc.type.spaTrabajo de grado
dc.rights.accesoAbierto (Texto Completo)
dc.source.bibliographicCitationOMS, «Cáncer,» 12 septiembre 2018. [En línea]. Available:
dc.source.bibliographicCitationASCO, «American Society of Clinical Oncology,» Journal of Clinical Oncology, pp. 212-222, 20 Febrero 2017
dc.source.bibliographicCitationDANE, «Boletín Técnico,» 20 Diciembre 2019. [En línea]. Available: im_2019pr-20-diciembre-2019.pdf
dc.source.bibliographicCitationMinSalud, «PLAN DECENAL PARA EL CONTROL EN COLOMBIA,» 17 Marzo 2012. [En línea]. Available:
dc.source.bibliographicCitationMinSalud, «Cáncer,» Enero 25 2020. [En línea]. Available:
dc.source.bibliographicCitationA. L. L. T. G. Óscar, «Costos directos de la atención del cáncer,» Cancerol, vol. XX, nº 2, pp. 52-60, 2016
dc.source.bibliographicCitationJ. Greening, «The peptidome comes of age: Mass spectrometry-based characterization of the circulating cancer peptidome,» Enzymes, vol. 42, pp. 27-64, 2017
dc.source.bibliographicCitationS. Lou, «Automated detection of radiology reports that require follow-up imaging using natural language processing feature engineering and machine learning classification,» Journal of Digital Imaging, vol. 33, nº 1, pp. 131-136, 2020
dc.source.bibliographicCitationG. M. H. R. E. &. W. N. Cooper, La célula: Geoffrey M. Cooper y Robert E. Hausman, Madrid: Madrid: Marbán, 2014
dc.source.bibliographicCitationB. S. D. Lodish, Biología Celular y Molecular, 5 ed., Madrid: Panamericana, 2016, pp. 590-630
dc.source.bibliographicCitationS. I. Fox, FISIOLOGÍA HUMANA, vol. XII, New York: Pierce College, 2011, pp. 50- 90
dc.source.bibliographicCitationV. M. Saikumar P., Apoptosis and Cell Death. In: Allen T., vol. II, Boston: Molecular Pathology Library, 2009
dc.source.bibliographicCitationC. W. K. Murphy, ImmunBiology, 9 ed., vol. I, Bostom: Garlad Science, 2017, pp. 3-35
dc.source.bibliographicCitationW. R. Hanahan D, «Review: Hallmarks of Cancer,» 11 Junio 2011. [En línea]. Available: true&db=ed selp&AN=S0092867411001279&lang=es&site=eds-live&scope=site
dc.source.bibliographicCitationS. Gortzak-Uzan, «A Proteome Resource of Ovarian Cancer Ascites: Integrated Proteomic and Bioinformatic Analyses To Identify Putative Biomarkers,» Journal of Proteome Research, vol. VII, nº 1, p. 339–351, 2013
dc.source.bibliographicCitationH. Mattsson, «Improved pan-specific prediction of MHC class I peptide binding using a novel receptor clustering data partitioning strategy,» HLA Inmune Response Genetics, pp. 1-6, 2016
dc.source.bibliographicCitationR. J. A. N. M. N. H. V. I. Jurtz, «An introduction to Deep learning on biological sequence data – Examples and solutions,» Oxford University Press, 2017
dc.source.bibliographicCitationJ. &. V. A. &. C. S. &. D. N. Gauthier, «A Brief History of Bioinformatics. Briefings in Bioinformatics,» pp. 11-34, 2018
dc.source.bibliographicCitationB. C. R. S. C. B. J. G. I. I. Pedro Larrañaga, «Machine learning in bioinformatics,» p. 86–112, 2006
dc.source.bibliographicCitationS. R. J. Y. H. J. L. H. J. L. E. J. L. Kim, «Bioinformatic and metabolomic analysis reveals miR-155 regulates thiamine level in breast cancer,» Cancer Letters, vol. II, nº 357, p. 488–497, 2015
dc.source.bibliographicCitationG. B. V. C. D. F. &. S. S. Musumarra, «A Bioinformatic Approach to the Identification of Candidate Genes for the Development of New Cancer Diagnostics,» Biological Chemistry, vol. II, nº 384, pp. 391-398, 2004
dc.source.bibliographicCitationC. G. B. T. Y. C. S. Zhou. J, «Genetic and bioinformatic analyses of the expression and function of PI3K regulatory subunit PIK3R3 in an Asian patient gastric cancer library,» Medical Genomic, vol. V, nº 1, pp. 5-12, 2012
dc.source.bibliographicCitationJ. F. H. B. L. &. F. J. G. Beltrán Lissabet, «TTAgP 1.0: A computational tool for the specific prediction of tumor T cell antigens,» Computational Biology and Chemistry, nº 83, 2019
dc.source.bibliographicCitationD. Chicco, «Ten quick tips for machine learning in computational biology,» BioMed Central, vol. I, nº 10, pp. 1-17, 2017
dc.source.bibliographicCitationC. Bishop, PATTERN RECOGNITION AND MACHINE LEARNING, Primera ed., 2006, pp. 5-15
dc.source.bibliographicCitationO. Theobald, Machine Learning for Absolute Beginners, vol. 2, Independently Published, 2018, pp. 10-12
dc.source.bibliographicCitationA. M. D. A. A. L. Swan, «Application of Machine Learning to Proteomics Data: Classification and Biomarker Identification in Postgenomics Biology,» OMICS : a Journal of Integrative Biology, vol. XVII, nº 12, pp. 595-610, 2010
dc.source.bibliographicCitationJ. Ulintz, «Improved Classification of Mass Spectrometry Database Search Results Using Newer Machine Learning Approaches,» Molecular & Cellular Proteomics, vol. V, nº 3, pp. 97-509, 2005
dc.source.bibliographicCitationS. Jeet, «Machine Learning Biogeographic Processes from Biotic Patterns: A New Trait-Dependent Dispersal and Diversification Model with Model Choice By Simulation-Trained Discriminant Analysis,» Systematic Biology, vol. 65, nº 3, pp. 525-55, 2016
dc.source.bibliographicCitationS. Zhang, «PromPDD, a web-based tool for the prediction, deciphering and design of promiscuous peptides that bind to HLA class I molecules,» Journal of Immunological Methods, pp. 476-489, 2020
dc.source.bibliographicCitationK. D. R. N. Tomar, «Immunoinformatics: an integrated scenario,» British Society of Immunology, vol. 131, nº 2, p. 153–168, 2010
dc.source.bibliographicCitationK. D. H. Youngmahn, «Deep convolutional neural networks for pan-specific peptideMHC class I binding prediction,» BMC Bioinformatics, 2017
dc.source.bibliographicCitationE. Loan, «Building MHC Class II Epitope Predictor Using Machine Learning Approaches,» Springer, vol. 1268, pp. 67-73, 2015
dc.source.bibliographicCitationT. Alvarez, «NNAlign-MA; MHC peptidome deconvolution for accurate MHC binding motif characterization and improved t-cell epitode,» Molecular and Cellular Proteomic, vol. 18, nº 12, pp. 2459-2477, 2019
dc.source.bibliographicCitationM. M. H. &. B. M. Nosrati, «Introducing of an integrated artificial neural network and chou's pseudo amino acid composition approach for computational epitopemapping of crimean-congo haemorrhagic fever virus antigens,» International Immunopharmacology, nº 78, 2020
dc.source.bibliographicCitationS. X. Z. Weilong, «Systematically benchmarking peptide-MHC binding predictors: From synthetic to naturally processed epitopes,» Computacional Biology, pp. 1-28, 2018
dc.source.bibliographicCitationR. D. A.D. Irini, «VaxiJen: a server for prediction of protective antigens, tumour antigens and subunit vaccines,» BMC Bioinformatics, pp. 22-26, 2007
dc.source.bibliographicCitationF. F. W. J. T. Elias, «TIminer: NGS data mining pipeline for cancer immunology and immunotherapy,» Bioinformatics, vol. 33, nº 19, p. 3140–3141, 2017
dc.source.bibliographicCitationL. T. S. L. H. Olsen, «TANTIGEN: a comprehensive database of tumor T cell antigens,» Cancer Immunol Immunother, nº 66, 2017
dc.source.bibliographicCitationC. L. S. S. R. L. G. a. L. Pommié, «IMGT standardized criteria for statistical analysis of immunoglobulin V‐REGION amino acid properties,» IMGT, nº 17, pp. 17-32, 2004
dc.source.bibliographicCitationJ.-L. C. M. K. L. B. V. A. &. P. V. FAUCHÈRE, «Amino acid side chain parameters for correlation studies in biology and pharmacology,» International Journal of Peptide and Protein Research, nº 32(4), p. 269–278, 2009
dc.source.bibliographicCitationImMunoGeneTics, «Amino acids,» 20 04 2004. [En línea]. Available:
dc.source.bibliographicCitationQ. B. A. G. K. Maricel, «Optimization of a new score function for the detection of remote homologs,» Proteins: Structure, Function, and Bioinformatics, vol. XLI, nº 4, pp. 498-503, 2000
dc.source.bibliographicCitationk. S.-H. T. H. D. G. Eleni, «Verification and validation of bioinformatics software without a gold standard: a case study of BWA and Bowtie,» BMC Bioinformatics, vol. XV, nº 16, 2014
dc.source.bibliographicCitationR. T. J. F. T. Hastie, The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Segunda ed., Stanford, California: Springer, 2008
dc.source.bibliographicCitationG. Thomas, «Machine Learning Bias, Statistical Bias, and Statistical Variance of Decision Tree Algorithms,» 5 1995. [En línea]. Available:
dc.source.bibliographicCitationSciKit Learn, «sklearn.ensemble.RandomForestClassifier,» 2019. [En línea]. Available: ml
dc.source.bibliographicCitationS. Haykin, Neural Network and Learning Machines, Tercera ed., Boston: Person, 2009
dc.source.bibliographicCitationF. J. &. P.-M. C. Valverde-Albacete, «100% classification accuracy considered harmful: the normalized information transfer factor explains the accuracy paradox.,» Plos One, vol. IX, nº 1, 2014
dc.source.bibliographicCitationScikit Learn, «GridSearchCV,» 2 Enero 2020. [En línea]. Available: sklearn.model_selection.GridSearchCV
dc.source.bibliographicCitationC. C. H. S. M. S. Ciampi A., «Recursive Partition: A Versatile Method for Exploratory-Data Analysis in Biostatistics,» Springer, vol. XXXVII, 1999
dc.source.bibliographicCitationB. Y. B. James, «Random Search for Hyper-Parameter Optimization,» Journal of Machine Learning Research, vol. XIII, pp. 281-305, 2012
dc.source.bibliographicCitationT. S. H. T. A. ENDO, «Comparison of Seven Algorithms to Predict Breast Cancer Survival,» International Journal of Biomedical Soft Computing and Human Sciences: the official journal of the Biomedical Fuzzy Systems Association, vol. XIII, nº 2, pp. 11-16, 2008
dc.source.bibliographicCitationM. J. D. A. F.F. João, «PLEURAL TUBERCULOSIS DIAGNOSIS BASED ON ARTIFICIAL,» Sociedade Brasileira de Inteligência Computacional, 2011
dc.source.bibliographicCitationKakau, «ROC curves,» 17 06 2010. [En línea]. Available:
dc.source.bibliographicCitationSciKit Learn, «sklearn.neural_network.MLPClassifier,» 20 Enero 2020. [En línea]. Available: klearn.neural_network.MLPClassifier.predict_proba
dc.source.bibliographicCitationC. L. D. I. Seixas JM, «Relevance criteria for variable selection in classifier design. In: International conference on engineering applications of neural networks,» de International conference on engineering applications of neural networks, London, 1996
dc.source.bibliographicCitationF. S. T. R. C. P. J. V. K. A. L. S. J. M. &. M. F. C. Aguiar, «Development of two artificial neural network models to support the diagnosis of pulmonary tuberculosis in hospitalized patients in Rio de Janeiro,» Medical & biological engineering & computing, vol. 54, nº 11, pp. 1751-1759, 2016
dc.source.bibliographicCitationM. L. F. W. N.A Obuchowski, «ROC curves in clinical chemistry: uses, misuses, and possible solutions.,» Clenecal Chemistry, vol. L, nº 7, pp. 18-25, 2004
dc.source.bibliographicCitationN. Tkachev, «Flexible data trimming improves performance of global machine learning methods in omics-based personalized oncology,» International Journal of Molecular Sciences, vol. XXI, nº 3, 2020
dc.source.bibliographicCitationL. Breiman, «Random forests,» Springer Netherlands, vol. XLV, nº 1, pp. 5-32, 2001
dc.rights.licenciaEL AUTOR, manifiesta que la obra objeto de la presente autorización es original y la realizó sin violar o usurpar derechos de autor de terceros, por lo tanto la obra es de exclusiva autoría y tiene la titularidad sobre la misma.
dc.type.documentAnálisis de caso
dc.creator.degreetypeFull time
dc.title.TranslatedTitleComparison of machine learning models for the prediction of cancer cells from the MHC I complex

Files in this item


This item appears in the following Collection(s)

Show simple item record

Atribución 2.5 Colombia
Except where otherwise noted, this item's license is described as Atribución 2.5 Colombia